Nowotwór jamy ustnej
Rokowania, prognozy i postęp choroby

Nowotwór jamy ustnej charakteryzuje się złożonym rokowaniem zależnym od stadium choroby, grubości guza, marginesów chirurgicznych, inwazji okołonerwowej i naczyniowej oraz zajęcia węzłów chłonnych. Statystyki 5-letniego przeżycia różnią się znacząco w zależności od stadium: Stadium I – >85%, Stadium II – ~70%, Stadium III – >55%, Stadium IV – 35%. W przypadku inwazji kości 5-letni wskaźnik przeżycia wynosi około 50%, z resekcją chirurgiczną dającą 47%, a chemioterapią 56%. Nowoczesne modele prognostyczne, takie jak model accelerated failure time, oraz narzędzia typu Oral Cancer Survival Calculator uwzględniają współistniejące schorzenia i oferują bardziej precyzyjne przewidywania niż tradycyjne modele Coxa. Kluczowe czynniki prognostyczne obejmują również lokalizację guza, zróżnicowanie histopatologiczne oraz obecność nacieku okołonerwowego i extracapsular extension w węzłach chłonnych.

Podstawy prognozy nowotworu jamy ustnej

Nowotwór jamy ustnej (nowotwór jamy ustnej) to poważna choroba, której prognoza zależy od wielu złożonych czynników. Określenie rokowania wymaga uwzględnienia indywidualnej historii medycznej pacjenta, typu i stadium nowotworu, charakterystyki guza, wybranych metod leczenia oraz odpowiedzi na terapię. Tylko lekarz znający wszystkie te elementy może połączyć je ze statystykami przeżycia, aby przedstawić rzetelną prognozę.12

Warto zaznaczyć, że statystyki przeżycia są bardzo ogólnymi szacunkami i muszą być interpretowane ostrożnie. Ponieważ dane te opierają się na doświadczeniach grup pacjentów, nie mogą być używane do precyzyjnego przewidywania szans przeżycia konkretnej osoby.3 Ponadto, osoby obecnie diagnozowane z nowotworem jamy ustnej mogą mieć lepsze rokowanie niż pokazują statystyki, gdyż metody leczenia stale się poprawiają, a dostępne dane często opierają się na pacjentach zdiagnozowanych i leczonych co najmniej 5 lat wcześniej.4

Kluczowe czynniki prognostyczne

Stadium nowotworu jamy ustnej jest jednym z najważniejszych czynników rokowniczych. Im niższe stadium, tym lepsza prognoza. Stadium choroby odnosi się do jej rozmiaru i zaawansowania, określając czy doszło do rozprzestrzenienia się poza miejsce pierwotne.56

Grubość guza również odgrywa istotną rolę w prognozie. Cieńsze guzy mają lepsze rokowanie. Grubsze zmiany wiążą się z większym ryzykiem wznowy miejscowej oraz rozprzestrzenienia do węzłów chłonnych.7

Inne kluczowe czynniki prognostyczne obejmują:

  • Marginesy chirurgiczne – guzy z ujemnymi marginesami chirurgicznymi mają lepszą prognozę8
  • Inwazja okołonerwowa – gdy nowotwór wrasta w nerwy lub wokół nich, rokowanie może być gorsze9
  • Inwazja naczyniowa – rozprzestrzenienie do naczyń krwionośnych zwiększa ryzyko rozsiewu, co wiąże się z gorszą prognozą10
  • Zajęcie węzłów chłonnych – przerzuty do węzłów chłonnych znacząco pogarszają rokowanie; im więcej zajętych węzłów, tym wyższe ryzyko przerzutów odległych11
  • Naciekanie pozatorebkowe w węzłach chłonnych (extracapsular extension) – także wiąże się z gorszym rokowaniem12
  • Lokalizacja guza w jamie ustnej – różne umiejscowienia mogą wiązać się z odmiennym rokowaniem13
  • Zróżnicowanie guza – stopień zróżnicowania komórek nowotworowych14

Wskaźniki przeżycia w nowotworze jamy ustnej

Przeżycie różni się w zależności od stadium nowotworu jamy ustnej. Ogólnie rzecz biorąc, im wcześniej nowotwór zostanie zdiagnozowany i leczony, tym lepsze rokowanie.15

Statystyki przeżycia według stadium zaawansowania

Dane statystyczne wskazują na następujące wskaźniki 5-letniego przeżycia:

  • Stadium I: Ponad 85% pacjentów przeżyje 5 lat lub więcej po diagnozie16
  • Stadium II: Około 70% pacjentów przeżyje 5 lat lub więcej po diagnozie17
  • Stadium III: Ponad 55% pacjentów przeżyje 5 lat lub więcej po diagnozie18
  • Stadium IV: 35% pacjentów przeżyje 5 lat lub więcej po diagnozie19

Globalnie wskaźniki przeżycia wskazują, że około 60% pacjentów z nowotworem jamy ustnej przeżyje 5 lat lub więcej po diagnozie, natomiast około 80% przeżyje co najmniej rok.20 Warto jednak zauważyć, że ogólny wskaźnik 5-letniego przeżycia po diagnozie wynosi około 50%, co podkreśla potrzebę wczesnej diagnozy i lepszych metod prognozowania.21

W przypadkach nowotworu jamy ustnej z inwazją kości, 5-letni wskaźnik przeżycia wynosi około 50%, przy czym resekcja chirurgiczna daje 47% wskaźnik przeżycia, a chemioterapia 56%.22

Nowoczesne narzędzia i modele prognostyczne

W ostatnich latach opracowano zaawansowane narzędzia i modele, które pomagają w bardziej precyzyjnym przewidywaniu rokowania u pacjentów z nowotworem jamy ustnej.

Kalkulatory przeżycia i modele matematyczne

Oral Cancer Survival Calculator opracowany przez Narodowy Instytut Raka (NCI) wykorzystuje dane z programu Surveillance, Epidemiology and End Results (SEER) wraz z danymi Medicare do obliczania szacunków przeżycia. Narzędzie to kładzie równy nacisk na prawdopodobieństwo zgonu z powodu nowotworu jak i innych przyczyn, uwzględniając współistniejące schorzenia pacjenta do obliczenia oczekiwanej długości życia.23

Modele prognostyczne dla przewidywania przeżycia pacjentów z rakiem płaskonabłonkowym jamy ustnej (OSCC) są stale rozwijane i walidowane. Dokładne przewidywanie przeżycia jest niezwykle ważne dla poradnictwa, planowania leczenia, kontroli pooperacyjnej i oceny ryzyka pooperacyjnego.24

Model accelerated failure time zapewnia stosunkowo dokładną metodę prognozowania dla pacjentów z rakiem płaskonabłonkowym jamy ustnej i jest zalecany zamiast modelu Cox PH ze względu na jego lepsze możliwości predykcyjne. Badania podkreślają znaczenie stosowania zaawansowanych modeli statystycznych w celu poprawy prognozowania przeżycia i wyników leczenia pacjentów z nowotworem.25

Podejścia oparte na uczeniu maszynowym i sztucznej inteligencji

Uczenie maszynowe i sztuczna inteligencja rewolucjonizują prognozowanie w nowotworze jamy ustnej:

  • Klasyfikator Voting wykazał najlepszą ogólną skuteczność w klasyfikowaniu zarówno 3-letniego, jak i 5-letniego przeżycia pacjentów z nowotworem jamy ustnej. Najważniejszymi cechami predykcyjnymi były wiek w momencie diagnozy, lokalizacja administracyjna oraz zróżnicowanie guza.2627
  • Analiza radiomiczna MRI wspierana przez uczenie maszynowe wykazała doskonałą zdolność do przewidywania przerzutów do kości (AUC=0,999) i wczesnego wykrywania OSCC.28
  • Głębokie uczenie analizujące profile limfocytów naciekających guz (TILs) może stanowić nowe podejście do prognozowania nowotworu. Badania potwierdzają znaczenie TILs w mikrośrodowisku guza (TME) i wskazują kierunek wykorzystania głębokiego uczenia w prognozowaniu nowotworów.29

Biomarkery molekularne w prognozowaniu

Odkrycia w dziedzinie biologii molekularnej dostarczają nowych biomarkerów, które mogą pomagać w prognozowaniu przebiegu nowotworu jamy ustnej.

Metylacja DNA jako wskaźnik prognostyczny

Metylacja DNA okazuje się obiecującym narzędziem prognostycznym w nowotworze jamy ustnej. Wysokie poziomy metylacji genów ZNF582 i PAX1 w guzach znacznie częściej obserwuje się u pacjentów z gorszym rokowaniem w porównaniu do pacjentów z dobrym rokowaniem. Wskaźniki szans wynosiły 17,8 dla ZNF582m i 22,0 dla PAX1m (p=0,005 i 0,002). To sugeruje, że łączne wykorzystanie wysokich statusów metylacji ZNF582 i PAX1 może być rozwijane jako biomarkery do badań przesiewowych raka jamy ustnej w populacjach wysokiego ryzyka oraz jako predyktory potencjalnie złego rokowania.30

Badania nad wzorcem metylacji DNA w raku płaskonabłonkowym jamy ustnej doprowadziły do ustanowienia sygnatury prognostycznej genów różnicowo wyrażanych związanych z metylacją (mrDEGPS). Jest to istotny czynnik stratyfikacji przeżycia (P≤0.00001) niezależny od stadium klinicznego. Analiza porównawcza rokowań wykazała, że pacjenci z niskim ryzykiem mieli znacznie wyższe przeżycie całkowite (OS) (P=4.587e-10), przeżycie specyficzne dla choroby (DSS) (P=1.28e-07) i przeżycie wolne od progresji (PFS) (P=9.588e-6) niż pacjenci z wysokim ryzykiem.31

Markery limfocytów naciekających guz i fibroblastów związanych z nowotworem

Limfocyty naciekające guz (TILs) są ważnymi wskaźnikami mikrośrodowiska guza (TME) i mają istotny wpływ na prognozę:

  • Markery CD3, CD4 i CD8 wykazują znaczącą korelację zarówno z przeżyciem całkowitym, jak i przeżyciem wolnym od progresji w analizie jednowymiarowej.32
  • Niskie ekspresje CD4 (ale nie CD3 ani CD8) mogą identyfikować pacjentów z wczesnym stadium OSCC o wyjątkowo złym rokowaniu, podobnym do rokowania pacjentów z zaawansowanym stadium OSCC.3334
  • Tradycyjne wskaźniki, takie jak status węzłów chłonnych, zróżnicowanie guza i naciekanie okołonerwowe, pozostają silnymi markerami prognostycznymi dla pacjentów z OSCC.35

Fibroblasty związane z nowotworem (CAFs) również odgrywają istotną rolę w rokowaniu. Poprzez analizę transkryptomiczną zidentyfikowano sygnaturę czterech genów składającą się z TGFB2, TGFBR2, TGFBI i FN1, jako tzw. indeks CAF. Meta-analiza wykazała, że wysoki indeks CAF jest statystycznie związany z gorszym całkowitym przeżyciem. Indeks CAF przewyższał również wynik przejścia nabłonkowo-mezenchymalnego (EMT) w analizie modelu wielowymiarowego Coxa: indeks CAF (HR = 12,5; 95% CI, 2,08–74,9, p = 0,006) vs. wynik EMT (HR = 1,0; 95% CI, 0,24–4,2, p = 0,992).36

Radiomica w prognozowaniu nowotworu jamy ustnej

Radiomica, czyli analiza ilościowych cech obrazów diagnostycznych, staje się coraz bardziej znaczącym narzędziem w prognozowaniu nowotworu jamy ustnej.

Modele prognostyczne oparte na MRI

Rak płaskonabłonkowy głowy i szyi (HNSCC) wykazuje niezwykłą heterogeniczność między guzami, którą można uchwycić za pomocą różnorodnych ilościowych cech wyodrębnionych z obrazów diagnostycznych, nazwanych radiomiką. Badania nad modelami prognostycznymi opartymi na MRI wykazały obiecujące wyniki:

  • W raku jamy ustnej model radiomiczny wykazał indeks AUC wynoszący 0,69 (dla OS) i 0,70 (dla RFS) w kohorcie walidacyjnej.3738
  • Poprzez integrację zmiennych radiomicznych i klinicznych, zdefiniowano najbardziej dokładne modele (iAUC jamy ustnej, 0,72 (OS) i 0,74 (RFS)), a te połączone modele przewyższały modele prognostyczne oparte wyłącznie na standardowych zmiennych klinicznych (p≤0,001).3940

Radiomica MRI jest wykonalna w HNSCC pomimo znanej zmienności dostawców MRI i protokołów akwizycji, a cechy radiomiczne dodają informacje do modeli prognostycznych opartych na parametrach klinicznych. Radiomica MRI może przewidywać całkowite przeżycie i przeżycie wolne od nawrotu w raku jamy ustnej i HPV-ujemnym raku gardła.4142

Zmiany w dostawcach MRI i protokołach akwizycji nie wpływają na wydajność radiomicznych modeli prognostycznych, co jest istotną zaletą tej metody.4344

Ograniczenia i przyszłe kierunki badań

Pomimo znaczących postępów w prognozowaniu nowotworu jamy ustnej, istnieją pewne ograniczenia i wyzwania do pokonania w przyszłych badaniach.

Obecne wyzwania w modelach prognostycznych

Przegląd systematyczny modeli prognostycznych dla raka płaskonabłonkowego jamy ustnej ujawnił istotne różnice metodologiczne w rozwoju modeli. Większość modeli oceniała przeżycie całkowite u pacjentów z rakiem płaskonabłonkowym języka, niektóre oceniały wszystkie możliwe miejsca pojawienia się guza, a jeden model oceniał tylko raka błony śluzowej policzka.45

Walidacja wewnętrzna zapewnia lepsze oszacowanie wydajności modelu u nowych pacjentów, gdy jest wykonywana poprzez korygowanie nadmiernego dopasowania. Jednak jedna trzecia badanych modeli nie raportowała kalibracji modelu. Najczęściej stosowaną miarą dyskryminacji jest wskaźnik zgodności (C-index), który odzwierciedla prawdopodobieństwo, że dla dowolnej pary losowo wybranych osób, jednej z wynikiem i jednej bez, model przypisze wyższe prawdopodobieństwo osobie z wynikiem.46

Tylko cztery modele prognostyczne przeprowadziły walidację zewnętrzną, ale w żadnym z nich nie została konkretnie opisana populacja, w której przeprowadzono walidację, co negatywnie wpłynęło na ryzyko błędu.47

Perspektywy przyszłych badań

Przyszłe kierunki badań w dziedzinie prognozowania nowotworu jamy ustnej mogą obejmować:

  • Rozwijanie bardziej wszechstronnych modeli prognostycznych uwzględniających zarówno tradycyjne czynniki kliniczne, jak i nowe biomarkery molekularne oraz cechy radiomiczne.4849
  • Identyfikowanie dokładnych modeli prognostycznych i przeprowadzanie badań wpływu w celu zbadania ich wpływu na podejmowanie decyzji, wyniki pacjentów i koszty – fundamentalny element medycyny stratyfikowanej.50
  • Dalsze włączenie informacji kliniczno-patologicznych w celu poprawy wydajności dyskryminacyjnej modeli klasyfikacyjnych przed faktycznym wdrożeniem w środowisku klinicznym.51
  • Rozwijanie biomarkerów opartych na metylacji DNA, które mogą pomóc w przewidywaniu odpowiedzi na immunoterapię i chemioterapię, co ułatwi podejmowanie decyzji klinicznych u pacjentów z OSCC.52

Nowoczesne podejścia do prognozowania, takie jak sygnatury molekularne, radiomica i uczenie maszynowe, oferują obiecujące możliwości poprawy dokładności prognostycznej, co ostatecznie może prowadzić do bardziej spersonalizowanego podejścia w leczeniu pacjentów z nowotworem jamy ustnej.

Kolejne rozdziały

Zapraszamy do dalszego czytania naszego leksykonu.

Wybierz kolejny rozdział z menu poniżej, aby otworzyć nową podstronę kompedium wiedzy i uzyskać szczegółowe informację o leku, substancji lub chorobie.

  1. 10.04.2026
  2. www.leksykon.com.pl

Materiały źródłowe

  • #1 Prognosis and survival for oral cancer | Canadian Cancer Society
    https://cancer.ca/en/cancer-information/cancer-types/oral/prognosis-and-survival
    If you have oral cancer, you may have questions about your prognosis. A prognosis is the doctors best estimate of how cancer will affect someone and how it will respond to treatment. Prognosis and survival depend on many factors. Only a doctor familiar with your medical history, the type and stage and other features of the cancer, the treatments chosen and the response to treatment can put all of this information together with survival statistics to arrive at a prognosis. […] The stage of oral cancer is an important prognostic factor. The lower the stage, the better the prognosis. […] Tumour thickness is also an important prognostic factor. A thin tumour has a better prognosis. A thicker tumour has a higher risk of coming back (recurring) in the same place (local recurrence). Thicker tumours are also more likely to have spread to the lymph nodes.
  • #2 Survival statistics for oral cancer | Canadian Cancer Society
    https://cancer.ca/en/cancer-information/cancer-types/oral/prognosis-and-survival/survival-statistics
    Survival statistics for oral cancer are very general estimates and must be interpreted very carefully. Because these statistics are based on the experience of groups of people, they cannot be used to predict a particular persons chances of survival. […] Survival varies with each stage of oral cancer. Generally, the earlier oral cancer is diagnosed and treated, the better the outcome. […] Talk to your doctor about your prognosis. A prognosis depends on many factors, including: your health history, the type of cancer, the stage, certain characteristics of the cancer, the treatments chosen, how the cancer responds to treatment. Only a doctor familiar with these factors can put all of this information together with survival statistics to arrive at a prognosis.
  • #3 Survival statistics for oral cancer | Canadian Cancer Society
    https://cancer.ca/en/cancer-information/cancer-types/oral/prognosis-and-survival/survival-statistics
    Survival statistics for oral cancer are very general estimates and must be interpreted very carefully. Because these statistics are based on the experience of groups of people, they cannot be used to predict a particular persons chances of survival. […] Survival varies with each stage of oral cancer. Generally, the earlier oral cancer is diagnosed and treated, the better the outcome. […] Talk to your doctor about your prognosis. A prognosis depends on many factors, including: your health history, the type of cancer, the stage, certain characteristics of the cancer, the treatments chosen, how the cancer responds to treatment. Only a doctor familiar with these factors can put all of this information together with survival statistics to arrive at a prognosis.
  • #4 Survival Rates for Oral Cavity and Oropharyngeal Cancer | American Cancer Society
    https://www.cancer.org/cancer/types/oral-cavity-and-oropharyngeal-cancer/detection-diagnosis-staging/survival-rates.html
    Survival rates can give you an idea of what percentage of people with the same type and stage of cancer are still alive a certain amount of time (usually 5 years) after they were diagnosed. […] Keep in mind that survival rates are estimates and are often based on previous outcomes of large numbers of people who had a specific cancer, but they cant predict what will happen in any particular persons case. […] These numbers apply only to the stage of the cancer when it is first diagnosed. They do not apply later on if the cancer grows, spreads, or comes back after treatment. […] People now being diagnosed with oral cavity or oropharyngeal cancer may have a better outlook than these numbers show. Treatments improve over time, and these numbers are based on people who were diagnosed and treated at least 5 years earlier.
  • #5 Prognosis and survival for oral cancer | Canadian Cancer Society
    https://cancer.ca/en/cancer-information/cancer-types/oral/prognosis-and-survival
    If you have oral cancer, you may have questions about your prognosis. A prognosis is the doctors best estimate of how cancer will affect someone and how it will respond to treatment. Prognosis and survival depend on many factors. Only a doctor familiar with your medical history, the type and stage and other features of the cancer, the treatments chosen and the response to treatment can put all of this information together with survival statistics to arrive at a prognosis. […] The stage of oral cancer is an important prognostic factor. The lower the stage, the better the prognosis. […] Tumour thickness is also an important prognostic factor. A thin tumour has a better prognosis. A thicker tumour has a higher risk of coming back (recurring) in the same place (local recurrence). Thicker tumours are also more likely to have spread to the lymph nodes.
  • #6 Survival For Mouth And Oropharyngeal Cancer | Cancer Research UK
    https://www.cancerresearchuk.org/about-cancer/mouth-cancer/survival
    Survival depends on many factors. No one can tell you exactly how long you will live. […] Your doctor can give you more information about your own outlook (prognosis). […] Your outlook (prognosis) depends on the stage of your cancer at diagnosis. […] The stage of a cancer tells you about its size and whether it has spread. Your outlook (prognosis) depends on the stage of your cancer at diagnosis. […] More than 85 out of 100 people (more than 85%) will survive their cancer for 5 years or more after diagnosis. […] Around 70 out of 100 people (around 70%) will survive their cancer for 5 years or more after diagnosis. […] More than 55 out of 100 people (more than 55%) will survive their cancer for 5 years or more after diagnosis. […] 35 out of 100 people (35%) will survive their cancer for 5 years or more after diagnosis.
  • #7 Prognosis and survival for oral cancer | Canadian Cancer Society
    https://cancer.ca/en/cancer-information/cancer-types/oral/prognosis-and-survival
    If you have oral cancer, you may have questions about your prognosis. A prognosis is the doctors best estimate of how cancer will affect someone and how it will respond to treatment. Prognosis and survival depend on many factors. Only a doctor familiar with your medical history, the type and stage and other features of the cancer, the treatments chosen and the response to treatment can put all of this information together with survival statistics to arrive at a prognosis. […] The stage of oral cancer is an important prognostic factor. The lower the stage, the better the prognosis. […] Tumour thickness is also an important prognostic factor. A thin tumour has a better prognosis. A thicker tumour has a higher risk of coming back (recurring) in the same place (local recurrence). Thicker tumours are also more likely to have spread to the lymph nodes.
  • #8 Prognosis and survival for oral cancer | Canadian Cancer Society
    https://cancer.ca/en/cancer-information/cancer-types/oral/prognosis-and-survival
    Tumours with negative surgical margins have a better prognosis. […] When oral cancer has grown into, around or along a nerve (called perineural invasion) the prognosis may be poorer. […] When oral cancer has spread to blood vessels (called vascular invasion) it may increase the risk of spread throughout the body. Cancer that has spread throughout the body has a poorer prognosis. […] Oral cancer that has spread to the lymph nodes has a poorer prognosis. The more lymph nodes the cancer reaches, the higher the risk of distant spread or metastasis. If cancer grows beyond the wall of a lymph node (called extracapsular extension), the prognosis is also poorer. […] Prognosis can also depend on the location of the oral cancer. […] Survival will vary with each stage of oral cancer. It usually responds well to treatment.
  • #9 Prognosis and survival for oral cancer | Canadian Cancer Society
    https://cancer.ca/en/cancer-information/cancer-types/oral/prognosis-and-survival
    Tumours with negative surgical margins have a better prognosis. […] When oral cancer has grown into, around or along a nerve (called perineural invasion) the prognosis may be poorer. […] When oral cancer has spread to blood vessels (called vascular invasion) it may increase the risk of spread throughout the body. Cancer that has spread throughout the body has a poorer prognosis. […] Oral cancer that has spread to the lymph nodes has a poorer prognosis. The more lymph nodes the cancer reaches, the higher the risk of distant spread or metastasis. If cancer grows beyond the wall of a lymph node (called extracapsular extension), the prognosis is also poorer. […] Prognosis can also depend on the location of the oral cancer. […] Survival will vary with each stage of oral cancer. It usually responds well to treatment.
  • #10 Prognosis and survival for oral cancer | Canadian Cancer Society
    https://cancer.ca/en/cancer-information/cancer-types/oral/prognosis-and-survival
    Tumours with negative surgical margins have a better prognosis. […] When oral cancer has grown into, around or along a nerve (called perineural invasion) the prognosis may be poorer. […] When oral cancer has spread to blood vessels (called vascular invasion) it may increase the risk of spread throughout the body. Cancer that has spread throughout the body has a poorer prognosis. […] Oral cancer that has spread to the lymph nodes has a poorer prognosis. The more lymph nodes the cancer reaches, the higher the risk of distant spread or metastasis. If cancer grows beyond the wall of a lymph node (called extracapsular extension), the prognosis is also poorer. […] Prognosis can also depend on the location of the oral cancer. […] Survival will vary with each stage of oral cancer. It usually responds well to treatment.
  • #11 Prognosis and survival for oral cancer | Canadian Cancer Society
    https://cancer.ca/en/cancer-information/cancer-types/oral/prognosis-and-survival
    Tumours with negative surgical margins have a better prognosis. […] When oral cancer has grown into, around or along a nerve (called perineural invasion) the prognosis may be poorer. […] When oral cancer has spread to blood vessels (called vascular invasion) it may increase the risk of spread throughout the body. Cancer that has spread throughout the body has a poorer prognosis. […] Oral cancer that has spread to the lymph nodes has a poorer prognosis. The more lymph nodes the cancer reaches, the higher the risk of distant spread or metastasis. If cancer grows beyond the wall of a lymph node (called extracapsular extension), the prognosis is also poorer. […] Prognosis can also depend on the location of the oral cancer. […] Survival will vary with each stage of oral cancer. It usually responds well to treatment.
  • #12 Prognosis and survival for oral cancer | Canadian Cancer Society
    https://cancer.ca/en/cancer-information/cancer-types/oral/prognosis-and-survival
    Tumours with negative surgical margins have a better prognosis. […] When oral cancer has grown into, around or along a nerve (called perineural invasion) the prognosis may be poorer. […] When oral cancer has spread to blood vessels (called vascular invasion) it may increase the risk of spread throughout the body. Cancer that has spread throughout the body has a poorer prognosis. […] Oral cancer that has spread to the lymph nodes has a poorer prognosis. The more lymph nodes the cancer reaches, the higher the risk of distant spread or metastasis. If cancer grows beyond the wall of a lymph node (called extracapsular extension), the prognosis is also poorer. […] Prognosis can also depend on the location of the oral cancer. […] Survival will vary with each stage of oral cancer. It usually responds well to treatment.
  • #13 Prognosis and survival for oral cancer | Canadian Cancer Society
    https://cancer.ca/en/cancer-information/cancer-types/oral/prognosis-and-survival
    Tumours with negative surgical margins have a better prognosis. […] When oral cancer has grown into, around or along a nerve (called perineural invasion) the prognosis may be poorer. […] When oral cancer has spread to blood vessels (called vascular invasion) it may increase the risk of spread throughout the body. Cancer that has spread throughout the body has a poorer prognosis. […] Oral cancer that has spread to the lymph nodes has a poorer prognosis. The more lymph nodes the cancer reaches, the higher the risk of distant spread or metastasis. If cancer grows beyond the wall of a lymph node (called extracapsular extension), the prognosis is also poorer. […] Prognosis can also depend on the location of the oral cancer. […] Survival will vary with each stage of oral cancer. It usually responds well to treatment.
  • #14 Prognostic Role of Tumor-Infiltrating Lymphocytes in Oral Squamous Cell Carcinoma | BMC Cancer | Full Text
    https://bmccancer.biomedcentral.com/articles/10.1186/s12885-024-12539-5
    CD3, CD4, and CD8 were found to be significantly associated with both overall survival and progression-free survival using univariate analysis. […] However, none of these markers were found to independently predict the survival outcomes of OSCC using multivariate analysis. […] Only conventional factors such as nodal status, tumor differentiation and perineural invasion (PNI) were independent predictors of survival outcomes, with nodal status being the strongest independent predictor. […] Additionally, low CD4 (but not CD3 or CD8) expression was found to identify early-stage OSCC patients with exceptionally poor prognosis which was similar to that of advanced staged OSCC patients. […] TIL markers such as CD3, CD4, CD8, and FOXP3 can predict the survival outcomes of OSCC patients, but do not serve as independent prognostic markers as found with conventional factors (i.e. nodal status, tumor differentiation and PNI).
  • #15 Survival statistics for oral cancer | Canadian Cancer Society
    https://cancer.ca/en/cancer-information/cancer-types/oral/prognosis-and-survival/survival-statistics
    Survival statistics for oral cancer are very general estimates and must be interpreted very carefully. Because these statistics are based on the experience of groups of people, they cannot be used to predict a particular persons chances of survival. […] Survival varies with each stage of oral cancer. Generally, the earlier oral cancer is diagnosed and treated, the better the outcome. […] Talk to your doctor about your prognosis. A prognosis depends on many factors, including: your health history, the type of cancer, the stage, certain characteristics of the cancer, the treatments chosen, how the cancer responds to treatment. Only a doctor familiar with these factors can put all of this information together with survival statistics to arrive at a prognosis.
  • #16 Survival For Mouth And Oropharyngeal Cancer | Cancer Research UK
    https://www.cancerresearchuk.org/about-cancer/mouth-cancer/survival
    Survival depends on many factors. No one can tell you exactly how long you will live. […] Your doctor can give you more information about your own outlook (prognosis). […] Your outlook (prognosis) depends on the stage of your cancer at diagnosis. […] The stage of a cancer tells you about its size and whether it has spread. Your outlook (prognosis) depends on the stage of your cancer at diagnosis. […] More than 85 out of 100 people (more than 85%) will survive their cancer for 5 years or more after diagnosis. […] Around 70 out of 100 people (around 70%) will survive their cancer for 5 years or more after diagnosis. […] More than 55 out of 100 people (more than 55%) will survive their cancer for 5 years or more after diagnosis. […] 35 out of 100 people (35%) will survive their cancer for 5 years or more after diagnosis.
  • #17 Survival For Mouth And Oropharyngeal Cancer | Cancer Research UK
    https://www.cancerresearchuk.org/about-cancer/mouth-cancer/survival
    Survival depends on many factors. No one can tell you exactly how long you will live. […] Your doctor can give you more information about your own outlook (prognosis). […] Your outlook (prognosis) depends on the stage of your cancer at diagnosis. […] The stage of a cancer tells you about its size and whether it has spread. Your outlook (prognosis) depends on the stage of your cancer at diagnosis. […] More than 85 out of 100 people (more than 85%) will survive their cancer for 5 years or more after diagnosis. […] Around 70 out of 100 people (around 70%) will survive their cancer for 5 years or more after diagnosis. […] More than 55 out of 100 people (more than 55%) will survive their cancer for 5 years or more after diagnosis. […] 35 out of 100 people (35%) will survive their cancer for 5 years or more after diagnosis.
  • #18 Survival For Mouth And Oropharyngeal Cancer | Cancer Research UK
    https://www.cancerresearchuk.org/about-cancer/mouth-cancer/survival
    Survival depends on many factors. No one can tell you exactly how long you will live. […] Your doctor can give you more information about your own outlook (prognosis). […] Your outlook (prognosis) depends on the stage of your cancer at diagnosis. […] The stage of a cancer tells you about its size and whether it has spread. Your outlook (prognosis) depends on the stage of your cancer at diagnosis. […] More than 85 out of 100 people (more than 85%) will survive their cancer for 5 years or more after diagnosis. […] Around 70 out of 100 people (around 70%) will survive their cancer for 5 years or more after diagnosis. […] More than 55 out of 100 people (more than 55%) will survive their cancer for 5 years or more after diagnosis. […] 35 out of 100 people (35%) will survive their cancer for 5 years or more after diagnosis.
  • #19 Survival For Mouth And Oropharyngeal Cancer | Cancer Research UK
    https://www.cancerresearchuk.org/about-cancer/mouth-cancer/survival
    Survival depends on many factors. No one can tell you exactly how long you will live. […] Your doctor can give you more information about your own outlook (prognosis). […] Your outlook (prognosis) depends on the stage of your cancer at diagnosis. […] The stage of a cancer tells you about its size and whether it has spread. Your outlook (prognosis) depends on the stage of your cancer at diagnosis. […] More than 85 out of 100 people (more than 85%) will survive their cancer for 5 years or more after diagnosis. […] Around 70 out of 100 people (around 70%) will survive their cancer for 5 years or more after diagnosis. […] More than 55 out of 100 people (more than 55%) will survive their cancer for 5 years or more after diagnosis. […] 35 out of 100 people (35%) will survive their cancer for 5 years or more after diagnosis.
  • #20 Survival For Mouth And Oropharyngeal Cancer | Cancer Research UK
    https://www.cancerresearchuk.org/about-cancer/mouth-cancer/survival
    Around 75 out of 100 people (around 75%) will survive their cancer for 5 years or more after diagnosis. […] More than 70 out of 100 people (more than 70%) will survive their cancer for 5 years or more after diagnosis. […] 75 out of 100 people (75%) will survive their cancer for 5 years or more after diagnosis. […] Almost 65 out of 100 people (almost 65%) will survive their cancer for 5 years or more after diagnosis. […] The survival figures on this page are not based on the HPV status of oropharyngeal cancers. […] Around 80 out of every 100 (around 80%) will survive their cancer for 1 year or more after they are diagnosed. […] Around 60 out of every 100 (around 60%) will survive their cancer for 5 years or more after diagnosis. […] Almost 85 out of every 100 (almost 85%) will survive their cancer for 1 year or more after they are diagnosed. […] 65 out of every 100 (65%) will survive their cancer for 5 years or more after diagnosis.
  • #21 Predicting Overall Survival Using Machine Learning Algorithms in Oral Cavity Squamous Cell Carcinoma | Anticancer Research
    https://ar.iiarjournals.org/content/42/12/5859
    Globally, 5-year overall survival rates post-diagnosis remains poor, and only around 50% of patients survive for more than five years (1). […] Early diagnosis and better prognosis prediction are still the ultimate goals for better overall and disease-specific prognosis, especially for high-risk oral cancer patients (2, 3). […] The Voting Classifier demonstrated the best overall performance in classifying both 3- and 5-year overall survival of oral cancer patients in Queensland. […] Overall, age at diagnosis as a variable was observed to be the most important feature in the Voting Classifier predicting 3-year and 5-year overall survival. […] The top most important predictive features were age at diagnosis, LGAs and tumour differentiation for the prediction of 3-year overall survival in OSCC patients.
  • #22
    https://link.springer.com/article/10.1007/s00405-024-08862-z
    Diagnosing OSCC often occurs in advanced stages due to its rapid growth despite the absence of initial clinical symptoms. […] Detecting bone invasion in OSCC significantly impacts the patients prognosis and is crucial for surgical planning and determining the necessity of adjuvant therapy. […] In cases of OSCC with bone invasion, the 5-year survival rate is approximately 50%, with surgical resection yielding a 47% survival rate and chemotherapy yielding a 56% survival rate. […] The ability to predict bone metastasis (AUC=0.999) was found to be excellent. […] Our study underscores the potential of MRI-based radiomics aided by machine learning in early OSCC detection and bone metastasis prediction, showcasing an exceptional AUC of 0.999.
  • #23 Oral Cancer Survival Calculator
    https://seer.cancer.gov/survivalcalculator/
    This calculator uses data from the NCIs Surveillance, Epidemiology and End Results (SEER) Program with Medicare data to calculate survival estimates. […] The Oral Cancer Survival Calculator puts equal focus on the chance of dying of cancer and other causes. […] The tool includes a calculator that uses your coexisting conditions to compute what would your life expectancy be if you had not been diagnosed with cancer. […] The calculator produces survival estimates that are helpful for clinicians, people diagnosed with oral cancer, researchers, and policymakers.
  • #24 Development and Validation of Prognostic Models for Oral Squamous Cell Carcinoma: A Systematic Review and Appraisal of the Literature
    https://pmc.ncbi.nlm.nih.gov/articles/PMC8616042/
    Prognostic models to choose the right treatment schedule are needed in order to translate into practice a personalized approach. None of these models have been still entered into the clinical practice for what concern oral squamous cell carcinoma (OSCC). […] An accurate prediction of cancer survival is very important for counseling, treatment planning, follow-up, and postoperative risk assessment in patients with Oral Squamous Cell Carcinoma (OSCC). […] Based on the results of this systematic review, it is possible to state that it is necessary to carry out internal validation and shrinkage to correct overfitting and provide an adequate performance for optimism. […] This systematic review has yielded a detailed picture of prognostic models for predicting OS in patients with OSCC. […] The majority of models assessed OS in patients with squamous cell carcinoma of the tongue, two assessed all possible sites of tumor onset, and one model only assessed the buccal mucosa cancer.
  • #25 Development and validation of accelerated failure time model for cause-specific survival and prognostication of oral squamous cell carcinoma: SEER data analysis | PLOS One
    https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0309214
    Oral Squamous Cell Carcinoma is the most prevalent malignancies affecting the oral cavity. Despite progress in studies and treatment options its outlook remains grim with survival prospects greatly affected by demographic and clinical factors. Precisely predicting survival rates and prognosis plays a role in making treatment choices for the best achievable overall health outcomes. […] The accelerated failure time model provides a relatively accurate method to predict the prognosis of oral squamous cell carcinoma patients and is recommended over the Cox PH model for its superior predictive capabilities. This study also underscores the importance of using advanced statistical models to improve survival predictions and outcomes for cancer patients.
  • #26 Predicting Overall Survival Using Machine Learning Algorithms in Oral Cavity Squamous Cell Carcinoma | Anticancer Research
    https://ar.iiarjournals.org/content/42/12/5859
    Globally, 5-year overall survival rates post-diagnosis remains poor, and only around 50% of patients survive for more than five years (1). […] Early diagnosis and better prognosis prediction are still the ultimate goals for better overall and disease-specific prognosis, especially for high-risk oral cancer patients (2, 3). […] The Voting Classifier demonstrated the best overall performance in classifying both 3- and 5-year overall survival of oral cancer patients in Queensland. […] Overall, age at diagnosis as a variable was observed to be the most important feature in the Voting Classifier predicting 3-year and 5-year overall survival. […] The top most important predictive features were age at diagnosis, LGAs and tumour differentiation for the prediction of 3-year overall survival in OSCC patients.
  • #27 Predicting Overall Survival Using Machine Learning Algorithms in Oral Cavity Squamous Cell Carcinoma | Anticancer Research
    https://ar.iiarjournals.org/content/42/12/5859
    For the predication of 5-year overall survival, age at diagnosis, tumour sites and LGAs were more important predictive features. […] This study calls for further inclusion of clinicopathological information to improve discriminative performances of the Voting Classifier before actual implementation in the clinical setting in Queensland.
  • #28
    https://link.springer.com/article/10.1007/s00405-024-08862-z
    Diagnosing OSCC often occurs in advanced stages due to its rapid growth despite the absence of initial clinical symptoms. […] Detecting bone invasion in OSCC significantly impacts the patients prognosis and is crucial for surgical planning and determining the necessity of adjuvant therapy. […] In cases of OSCC with bone invasion, the 5-year survival rate is approximately 50%, with surgical resection yielding a 47% survival rate and chemotherapy yielding a 56% survival rate. […] The ability to predict bone metastasis (AUC=0.999) was found to be excellent. […] Our study underscores the potential of MRI-based radiomics aided by machine learning in early OSCC detection and bone metastasis prediction, showcasing an exceptional AUC of 0.999.
  • #29 Novel deep learning-based survival prediction for oral cancer by analyzing tumor-infiltrating lymphocyte profiles through CIBERSORT
    https://pmc.ncbi.nlm.nih.gov/articles/PMC8018482/
    The tumor microenvironment (TME) within mucosal neoplastic tissue in oral cancer (ORCA) is greatly influenced by tumor-infiltrating lymphocytes (TILs). […] This new approach confirms the importance of TILs in the TME and provides a direction for the use of a novel deep-learning approach for cancer prognosis. […] The importance of tumor-infiltrating lymphocyte (TIL) information has previously been reported, as TIL levels identify high-risk groups of patients with oral tongue squamous cell carcinoma. […] In particular, balanced levels of CD8 + T cells and regulatory T cells (Tregs) directly affect the survival rate of patients with oral cancer (ORCA). […] The TME is an important indicator of the clinical and prognostic factors of cancer. […] As a result of this effort, a few patients with HNSC, whose survival rates were extremely low, were successfully identified.
  • #30 DNA methylation confers clinical potential to predict the oral cancer prognosis
    https://www.oatext.com/dna-methylation-confers-clinical-potential-to-predict-the-oral-cancer-prognosis.php
    Oral squamous cell carcinoma (OSCC) has high incidence worldwide and poor prognosis for the past few decades. […] The high methylation levels of both genes in tumors were more commonly observed in poor prognosis patients compared to those with well prognoses. […] In conclusion, high methylation levels of ZNF582 and PAX1 in tumors and NCMT can be potential biomarkers in predicting OSCC prognosis, and can lead to optimal clinical management for OSCC patients. […] The methylation levels of ZNF582 or PAX1 in tumor and NCMT from the individual patient were represented in each dot on the diagram. […] The M-indexes of ZNF582m and PAX1 min poor prognoses patients were 2.15 and 1.95-fold higher than in patients having well prognoses. […] The odds ratios were 17.8 for ZNF582m and 22.0 for PAX1m (p=0.005 and 0.002, respectively). […] Our data suggested that combinational use of high methylation statuses of ZNF582 and PAX1 can be developed as biomarkers for oral cancer screening in high-risk populations and for predictors of potential poor prognostic conditions.
  • #31 Prognostic and therapeutic prediction by screening signature combinations from transcriptome–methylome interactions in oral squamous cell carcinoma | Scientific Reports
    https://www.nature.com/articles/s41598-022-15534-7
    DNA methylation pattern in oral squamous cell carcinoma (OSCC) remains poorly described. […] According to the prognostic analysis, the prognostic signature of methylation-related differentially expressed genes (mrDEGPS) was established. […] mrDEGPS was a significant stratification factor of survival (P0.00001) irrespective of the clinical stage. […] In conclusion, the transcriptomemethylome interaction pattern in OSCC is complex. mrDEGPS can predict patient survival and responses to immunotherapy and chemotherapy and facilitate clinical decision-making in patients with OSCC. […] However, stratifying the patient survival remained significantly challenging. […] The mrDEGPS for each patient was calculated using the following formula: […] Prognosis comparison showed that low-risk patients had significantly higher overall survival (OS) (P=4.587e10), disease-specific survival (DSS) (P=1.28e07), and progression-free survival (PFS) (P=9.588e6) than that in high-risk patients.
  • #32 Prognostic Role of Tumor-Infiltrating Lymphocytes in Oral Squamous Cell Carcinoma | BMC Cancer | Full Text
    https://bmccancer.biomedcentral.com/articles/10.1186/s12885-024-12539-5
    CD3, CD4, and CD8 were found to be significantly associated with both overall survival and progression-free survival using univariate analysis. […] However, none of these markers were found to independently predict the survival outcomes of OSCC using multivariate analysis. […] Only conventional factors such as nodal status, tumor differentiation and perineural invasion (PNI) were independent predictors of survival outcomes, with nodal status being the strongest independent predictor. […] Additionally, low CD4 (but not CD3 or CD8) expression was found to identify early-stage OSCC patients with exceptionally poor prognosis which was similar to that of advanced staged OSCC patients. […] TIL markers such as CD3, CD4, CD8, and FOXP3 can predict the survival outcomes of OSCC patients, but do not serve as independent prognostic markers as found with conventional factors (i.e. nodal status, tumor differentiation and PNI).
  • #33 Prognostic Role of Tumor-Infiltrating Lymphocytes in Oral Squamous Cell Carcinoma | BMC Cancer | Full Text
    https://bmccancer.biomedcentral.com/articles/10.1186/s12885-024-12539-5
    CD3, CD4, and CD8 were found to be significantly associated with both overall survival and progression-free survival using univariate analysis. […] However, none of these markers were found to independently predict the survival outcomes of OSCC using multivariate analysis. […] Only conventional factors such as nodal status, tumor differentiation and perineural invasion (PNI) were independent predictors of survival outcomes, with nodal status being the strongest independent predictor. […] Additionally, low CD4 (but not CD3 or CD8) expression was found to identify early-stage OSCC patients with exceptionally poor prognosis which was similar to that of advanced staged OSCC patients. […] TIL markers such as CD3, CD4, CD8, and FOXP3 can predict the survival outcomes of OSCC patients, but do not serve as independent prognostic markers as found with conventional factors (i.e. nodal status, tumor differentiation and PNI).
  • #34 Prognostic Role of Tumor-Infiltrating Lymphocytes in Oral Squamous Cell Carcinoma | BMC Cancer | Full Text
    https://bmccancer.biomedcentral.com/articles/10.1186/s12885-024-12539-5
    CD4 expression may assist with risk stratification in early-stage OSCC patients which may influence treatment planning and decision making for early-stage OSCC patients. […] Overall, our results confirm that conventional indicators such as lymph node metastasis, tumor differentiation, and PNI remain strong prognostic markers for OSCC patients. […] Evaluating TIL markers such as CD3, CD4, and CD8 can be useful in predicting patient survival, but should be used carefully in combination with the above conventional indicators given their lack of independent prognostic value. […] Finally, the expression of CD4 in particular may be helpful to identify early-stage OSCC patients with high or low risk of cancer recurrence and/or progression.
  • #35 Prognostic Role of Tumor-Infiltrating Lymphocytes in Oral Squamous Cell Carcinoma | BMC Cancer | Full Text
    https://bmccancer.biomedcentral.com/articles/10.1186/s12885-024-12539-5
    CD4 expression may assist with risk stratification in early-stage OSCC patients which may influence treatment planning and decision making for early-stage OSCC patients. […] Overall, our results confirm that conventional indicators such as lymph node metastasis, tumor differentiation, and PNI remain strong prognostic markers for OSCC patients. […] Evaluating TIL markers such as CD3, CD4, and CD8 can be useful in predicting patient survival, but should be used carefully in combination with the above conventional indicators given their lack of independent prognostic value. […] Finally, the expression of CD4 in particular may be helpful to identify early-stage OSCC patients with high or low risk of cancer recurrence and/or progression.
  • #36 Index of Cancer-Associated Fibroblasts Is Superior to the Epithelial–Mesenchymal Transition Score in Prognosis Prediction
    https://www.mdpi.com/2072-6694/12/7/1718
    By comparative transcriptomic analysis of NOG xenografts derived from OSCC cells with high and low EMT scores, the present study identified a four-gene signature consisting of TGFB2, TGFBR2, TGFBI, and FN1, as the CAF index. […] Meta-analysis of a betel-quid OSCC dataset and the TCGA pan-cancer cohort indicated that a high CAF index is statistically associated with poor overall survival. […] Collectively, these meta-analyses suggest that in a given tissue, aggregated expression of FN1, TGFBR2, TGFB2, and TGFBI might serve as an index for the extent of cancer-associated fibroblasts (CAFs). […] The index of CAFs also outperformed the EMT score in multivariate Cox model analysis, i.e., CAF index (HR = 12.5; 95% CI, 2.08–74.9, p = 0.006) vs. EMT score (HR = 1.0; 95% CI, 0.24–4.2, p = 0.992). […] As CAF emerged as a critical factor for treatment failures, our results might provide new thoughts for curative medicine in clinical oncology.
  • #37 Outcome prediction of head and neck squamous cell carcinoma by MRI radiomic signatures
    https://www.repository.cam.ac.uk/items/af325140-7966-474a-8a3f-f1005da705af
    Head and neck squamous cell carcinoma (HNSCC) shows a remarkable heterogeneity between tumors, which may be captured by a variety of quantitative features extracted from diagnostic images, termed radiomics. […] The aim of this study was to develop and validate MRI-based radiomic prognostic models in oral and oropharyngeal cancer. […] In oral cancer, the radiomic model showed an iAUC of 0.69 (OS) and 0.70 (RFS) in the validation cohort, whereas the iAUC in the oropharyngeal cancer validation cohort was 0.71 (OS) and 0.74 (RFS). […] By integration of radiomic and clinical variables, the most accurate models were defined (iAUC oral cavity, 0.72 (OS) and 0.74 (RFS); iAUC oropharynx, 0.81 (OS) and 0.78 (RFS)), and these combined models outperformed prognostic models based on standard clinical variables only (p 0.001).
  • #38
    https://link.springer.com/article/10.1007/s00330-020-06962-y
    Head and neck squamous cell carcinoma (HNSCC) shows a remarkable heterogeneity between tumors, which may be captured by a variety of quantitative features extracted from diagnostic images, termed radiomics. The aim of this study was to develop and validate MRI-based radiomic prognostic models in oral and oropharyngeal cancer. […] In oral cancer, the radiomic model showed an iAUC of 0.69 (OS) and 0.70 (RFS) in the validation cohort, whereas the iAUC in the oropharyngeal cancer validation cohort was 0.71 (OS) and 0.74 (RFS). By integration of radiomic and clinical variables, the most accurate models were defined (iAUC oral cavity, 0.72 (OS) and 0.74 (RFS); iAUC oropharynx, 0.81 (OS) and 0.78 (RFS)), and these combined models outperformed prognostic models based on standard clinical variables only (p 0.001).
  • #39 Outcome prediction of head and neck squamous cell carcinoma by MRI radiomic signatures
    https://www.repository.cam.ac.uk/items/af325140-7966-474a-8a3f-f1005da705af
    Head and neck squamous cell carcinoma (HNSCC) shows a remarkable heterogeneity between tumors, which may be captured by a variety of quantitative features extracted from diagnostic images, termed radiomics. […] The aim of this study was to develop and validate MRI-based radiomic prognostic models in oral and oropharyngeal cancer. […] In oral cancer, the radiomic model showed an iAUC of 0.69 (OS) and 0.70 (RFS) in the validation cohort, whereas the iAUC in the oropharyngeal cancer validation cohort was 0.71 (OS) and 0.74 (RFS). […] By integration of radiomic and clinical variables, the most accurate models were defined (iAUC oral cavity, 0.72 (OS) and 0.74 (RFS); iAUC oropharynx, 0.81 (OS) and 0.78 (RFS)), and these combined models outperformed prognostic models based on standard clinical variables only (p 0.001).
  • #40
    https://link.springer.com/article/10.1007/s00330-020-06962-y
    Head and neck squamous cell carcinoma (HNSCC) shows a remarkable heterogeneity between tumors, which may be captured by a variety of quantitative features extracted from diagnostic images, termed radiomics. The aim of this study was to develop and validate MRI-based radiomic prognostic models in oral and oropharyngeal cancer. […] In oral cancer, the radiomic model showed an iAUC of 0.69 (OS) and 0.70 (RFS) in the validation cohort, whereas the iAUC in the oropharyngeal cancer validation cohort was 0.71 (OS) and 0.74 (RFS). By integration of radiomic and clinical variables, the most accurate models were defined (iAUC oral cavity, 0.72 (OS) and 0.74 (RFS); iAUC oropharynx, 0.81 (OS) and 0.78 (RFS)), and these combined models outperformed prognostic models based on standard clinical variables only (p 0.001).
  • #41 Outcome prediction of head and neck squamous cell carcinoma by MRI radiomic signatures
    https://www.repository.cam.ac.uk/items/af325140-7966-474a-8a3f-f1005da705af
    MRI radiomics is feasible in HNSCC despite the known variability in MRI vendors and acquisition protocols, and radiomic features added information to prognostic models based on clinical parameters. […] MRI radiomics can predict overall survival and relapse-free survival in oral and HPV-negative oropharyngeal cancer. […] MRI radiomics provides additional prognostic information to known clinical variables, with the best performance of the combined models. […] Variation in MRI vendors and acquisition protocols did not influence performance of radiomic prognostic models.
  • #42
    https://link.springer.com/article/10.1007/s00330-020-06962-y
    MRI radiomics is feasible in HNSCC despite the known variability in MRI vendors and acquisition protocols, and radiomic features added information to prognostic models based on clinical parameters. […] MRI radiomics can predict overall survival and relapse-free survival in oral and HPV-negative oropharyngeal cancer. […] MRI radiomics provides additional prognostic information to known clinical variables, with the best performance of the combined models. […] Variation in MRI vendors and acquisition protocols did not influence performance of radiomic prognostic models.
  • #43 Outcome prediction of head and neck squamous cell carcinoma by MRI radiomic signatures
    https://www.repository.cam.ac.uk/items/af325140-7966-474a-8a3f-f1005da705af
    MRI radiomics is feasible in HNSCC despite the known variability in MRI vendors and acquisition protocols, and radiomic features added information to prognostic models based on clinical parameters. […] MRI radiomics can predict overall survival and relapse-free survival in oral and HPV-negative oropharyngeal cancer. […] MRI radiomics provides additional prognostic information to known clinical variables, with the best performance of the combined models. […] Variation in MRI vendors and acquisition protocols did not influence performance of radiomic prognostic models.
  • #44
    https://link.springer.com/article/10.1007/s00330-020-06962-y
    MRI radiomics is feasible in HNSCC despite the known variability in MRI vendors and acquisition protocols, and radiomic features added information to prognostic models based on clinical parameters. […] MRI radiomics can predict overall survival and relapse-free survival in oral and HPV-negative oropharyngeal cancer. […] MRI radiomics provides additional prognostic information to known clinical variables, with the best performance of the combined models. […] Variation in MRI vendors and acquisition protocols did not influence performance of radiomic prognostic models.
  • #45 Development and Validation of Prognostic Models for Oral Squamous Cell Carcinoma: A Systematic Review and Appraisal of the Literature
    https://pmc.ncbi.nlm.nih.gov/articles/PMC8616042/
    Prognostic models to choose the right treatment schedule are needed in order to translate into practice a personalized approach. None of these models have been still entered into the clinical practice for what concern oral squamous cell carcinoma (OSCC). […] An accurate prediction of cancer survival is very important for counseling, treatment planning, follow-up, and postoperative risk assessment in patients with Oral Squamous Cell Carcinoma (OSCC). […] Based on the results of this systematic review, it is possible to state that it is necessary to carry out internal validation and shrinkage to correct overfitting and provide an adequate performance for optimism. […] This systematic review has yielded a detailed picture of prognostic models for predicting OS in patients with OSCC. […] The majority of models assessed OS in patients with squamous cell carcinoma of the tongue, two assessed all possible sites of tumor onset, and one model only assessed the buccal mucosa cancer.
  • #46 Development and Validation of Prognostic Models for Oral Squamous Cell Carcinoma: A Systematic Review and Appraisal of the Literature
    https://pmc.ncbi.nlm.nih.gov/articles/PMC8616042/
    This systematic review showed methodological differences in model development. […] Internal validation provides a better estimate of model performance in new patients when done by adjusting overfitting, that is the difference between the accuracy of the apparent prediction and the accuracy of the prediction measured on an independent test set. […] Another important finding from our review is that one-third of the studies did not report on model calibration. […] The most used measure for discrimination is the Concordance Index (C-index), which reflects the probability that for any pair of individuals randomly, one with and one without the outcome, the model assigns a higher probability to the individual with the outcome. […] In the end, only four prognostic models performed external validation, in none of these the population in which the validation was performed was specifically reported and this data also negatively influenced the risk of bias.
  • #47 Development and Validation of Prognostic Models for Oral Squamous Cell Carcinoma: A Systematic Review and Appraisal of the Literature
    https://pmc.ncbi.nlm.nih.gov/articles/PMC8616042/
    Identifying accurate prognostic models and performing impact studies to investigate their influence on decision making, patient outcomes and costs is a fundamental component of stratified medicine because it contributes evidence at multiple stages in translation. […] All included prognostic models used nomogram as model presentation, yet none of the prognostic models reported the original mathematical regression formula. […] The recognition of the methodological limitations found in the developed models and their external validation were evaluated as a high risk of bias, as indicated in the PROBAST.
  • #48 Outcome prediction of head and neck squamous cell carcinoma by MRI radiomic signatures
    https://www.repository.cam.ac.uk/items/af325140-7966-474a-8a3f-f1005da705af
    MRI radiomics is feasible in HNSCC despite the known variability in MRI vendors and acquisition protocols, and radiomic features added information to prognostic models based on clinical parameters. […] MRI radiomics can predict overall survival and relapse-free survival in oral and HPV-negative oropharyngeal cancer. […] MRI radiomics provides additional prognostic information to known clinical variables, with the best performance of the combined models. […] Variation in MRI vendors and acquisition protocols did not influence performance of radiomic prognostic models.
  • #49
    https://link.springer.com/article/10.1007/s00330-020-06962-y
    MRI radiomics is feasible in HNSCC despite the known variability in MRI vendors and acquisition protocols, and radiomic features added information to prognostic models based on clinical parameters. […] MRI radiomics can predict overall survival and relapse-free survival in oral and HPV-negative oropharyngeal cancer. […] MRI radiomics provides additional prognostic information to known clinical variables, with the best performance of the combined models. […] Variation in MRI vendors and acquisition protocols did not influence performance of radiomic prognostic models.
  • #50 Development and Validation of Prognostic Models for Oral Squamous Cell Carcinoma: A Systematic Review and Appraisal of the Literature
    https://pmc.ncbi.nlm.nih.gov/articles/PMC8616042/
    Identifying accurate prognostic models and performing impact studies to investigate their influence on decision making, patient outcomes and costs is a fundamental component of stratified medicine because it contributes evidence at multiple stages in translation. […] All included prognostic models used nomogram as model presentation, yet none of the prognostic models reported the original mathematical regression formula. […] The recognition of the methodological limitations found in the developed models and their external validation were evaluated as a high risk of bias, as indicated in the PROBAST.
  • #51 Predicting Overall Survival Using Machine Learning Algorithms in Oral Cavity Squamous Cell Carcinoma | Anticancer Research
    https://ar.iiarjournals.org/content/42/12/5859
    For the predication of 5-year overall survival, age at diagnosis, tumour sites and LGAs were more important predictive features. […] This study calls for further inclusion of clinicopathological information to improve discriminative performances of the Voting Classifier before actual implementation in the clinical setting in Queensland.
  • #52 Prognostic and therapeutic prediction by screening signature combinations from transcriptome–methylome interactions in oral squamous cell carcinoma | Scientific Reports
    https://www.nature.com/articles/s41598-022-15534-7
    The validation analysis in a small sample size (n=97) demonstrated that patients in the high-risk group had poorer overall survival (P=3.098e2) than those patients in the low-risk group. […] In summary, mrDEGPS screened from complex transcriptomemethylome interactions could facilitate the prediction of survival and immunotherapeutic efficacy in patients with OSCC.