Rak tarczycy
Rokowania, prognozy i postęp choroby

Rak brodawkowaty tarczycy (PTC), stanowiący około 80% przypadków raka tarczycy, charakteryzuje się bardzo dobrym rokowaniem, z 5-letnim przeżyciem netto na poziomie 97% i 10-letnim wskaźnikiem przeżycia sięgającym 80-95%. Mimo to, u 25-30% pacjentów obserwuje się przetrwałą chorobę strukturalną lub nawrót, a śmiertelność jest istotna zwłaszcza u pacjentów z przerzutami do węzłów chłonnych (11%) i przerzutami odległymi (57%). Kluczowe czynniki prognostyczne obejmują wiek (z punktami odcięcia 45 i 55 lat), płeć, wielkość guza, stopień zaawansowania TNM oraz obecność przerzutów do węzłów chłonnych, z LNR i stadium N jako istotnymi zmiennymi prognostycznymi. Systemy stratyfikacji ryzyka, takie jak ATA, oraz dynamiczne modele oceny odpowiedzi na leczenie (np. na podstawie poziomu tyreoglobuliny ≥63,1 ng/mL) poprawiają precyzję prognozowania i kierowanie terapią.

Rokowanie w raku tarczycy – przegląd ogólny

Rak tarczycy jest chorobą, która zwykle wiąże się z doskonałym rokowaniem. Dotyczy to szczególnie raka brodawkowatego tarczycy (PTC), który stanowi około 80% wszystkich przypadków nowotworów złośliwych tarczycy. Ogólnie rzecz biorąc, rokowanie w raku tarczycy jest bardzo pozytywne, a większość przypadków jest uleczalna przy odpowiednim leczeniu.12

Wskaźniki przeżycia w raku tarczycy są imponujące: w Kanadzie 5-letnie przeżycie netto wynosi 97%, a w przypadku raka brodawkowatego tarczycy (PTC) 10-letni wskaźnik przeżycia może sięgać 80-95%. Co więcej, wskaźnik 5-letniego przeżycia dla PTC w stadium zlokalizowanym (ograniczonym do gruczołu) wynosi prawie 100%, a nawet przy rozsiewie nowotworu wskaźnik przeżycia pozostaje wysoki, bliski 80%.345

Mimo doskonałego rokowania ogólnego, u około 25-30% pacjentów występuje przetrwała choroba strukturalna lub nawrót po początkowym standardowym leczeniu. Należy zauważyć, że znaczna część tych pacjentów (11% z przerzutami do węzłów chłonnych i 57% z przerzutami odległymi) umiera z powodu PTC.67

Wskaźniki przeżycia i czas przeżycia bez choroby

W badaniu retrospektywnym obejmującym 660 przypadków raka brodawkowatego tarczycy, 5-, 10- i 15-letnie przeżycie wolne od choroby (DFS) wynosiło odpowiednio 95,5%, 90,2% i 89,2%. Całkowite przeżycie (OS) w okresie 5, 10 i 15 lat było jeszcze wyższe, osiągając odpowiednio 99,7%, 99,2% i 99,1%.8

Należy jednak pamiętać, że statystyki przeżycia są ogólnymi szacunkami i muszą być interpretowane z dużą ostrożnością. Ponieważ opierają się na doświadczeniach grup pacjentów, nie mogą być używane do przewidywania szans przeżycia konkretnej osoby. Rokowanie zależy od wielu czynników, w tym od historii zdrowia pacjenta, typu raka, stadium, pewnych charakterystyk nowotworu, wybranych metod leczenia i odpowiedzi na leczenie.910

Ponadto, wskaźniki przeżycia odnoszą się tylko do stadium raka w momencie pierwszej diagnozy. Nie mają zastosowania w późniejszym okresie, jeśli rak rośnie, rozprzestrzenia się lub nawraca po leczeniu. Osoby obecnie diagnozowane z rakiem tarczycy mogą mieć lepsze rokowanie niż pokazują te liczby, ponieważ metody leczenia uległy poprawie z czasem.11

Genetyczne determinanty rokowania w raku brodawkowatym tarczycy

Badania wskazują, że różne markery molekularne odgrywają istotną rolę w przewidywaniu wyników leczenia pacjentów z rakiem brodawkowatym tarczycy (PTC).1213

Mutacje BRAF i TERT – kluczowe markery molekularne

Badania wykazały, że guzy z mutacją promotora TERT (TERTpmut) wiążą się ze znacznie niższym czasem przeżycia bez choroby strukturalnej (SDFS) i zwiększoną śmiertelnością specyficzną dla choroby (DSM). Pacjenci z guzami TERTpmut wykazują istotnie zwiększone ryzyko choroby strukturalnej (HR = 7,0, p < 0,001) i DSM (HR = 10,1, p = 0,001).1415

Analizując kombinacje mutacji, pacjenci z guzami BRAFwt/TERTpmut (HR = 24,2, p < 0,001) i BRAFmut/TERTpmut (HR = 11,5, p = 0,002) wykazywali zwiększone ryzyko choroby strukturalnej. Śmiertelność specyficzna dla choroby była znacząco zwiększona u pacjentów z TERTpmut niezależnie od statusu BRAF (BRAFmut/TERTpmut, log-rank p < 0,001; BRAFwt/TERTpmut, log-rank p < 0,001).16

Ponadto, guzy BRAFmut/TERTpwt były związane ze zwiększonym ryzykiem nawracającej/przetrwałej choroby. Te wyniki potwierdzają, że markery molekularne mogą odgrywać rolę w przewidywaniu wyniku leczenia pacjentów z PTC.17

Wzorce molekularne – BRAF-like, RAS-like i NBNR

Badania wieloośrodkowe wykazały, że wzorce alteracji molekularnych – BRAF-like, RAS-like i non-BRAF-non-RAS (NBNR) – mogą być związane z zachowaniem guza, lepiej przewidując agresywne cechy, takie jak przerzuty do węzłów chłonnych i naciekanie pozatarczycowe, niż sama wielkość guza.18

W obecnej erze poleganie wyłącznie na wielkości guza jako markerze prognostycznym w raku brodawkowatym tarczycy może być niewystarczające, ponieważ wcześnie wykryte małe guzy mogą nie wykazywać w pełni swojego agresywnego potencjału. Integracja profilowania molekularnego z praktyką kliniczną może zwiększyć precyzję strategii leczenia, szczególnie w przypadku wczesnego stadium, małych guzów.19

Kliniczne czynniki prognostyczne w raku tarczycy

Istnieje szereg klinicznych czynników prognostycznych, które wpływają na rokowanie pacjentów z rakiem tarczycy.20

Wiek i płeć

Wiek jest jednym z najważniejszych czynników prognostycznych w raku tarczycy. Badania wykazały, że wiek jest czynnikiem prognostycznym zarówno przy punkcie odcięcia 45 lat (HR 2,00, 95% CI: 1,17-3,42, P<0,05), jak i 55 lat (HR 2,76, 95% CI: 1,70-4,50, P<0,05).21

Płeć również wpływa na rokowanie, będąc jednym z niezależnych czynników ryzyka wpływających na przeżycie specyficzne dla raka (CSS) u pacjentów w średnim wieku z PTC.22

Charakterystyka guza i stadium zaawansowania

Wielkość guza, stopień zaawansowania TNM, stopień zróżnicowania guza są niezależnymi czynnikami ryzyka wpływającymi na CSS u pacjentów w średnim wieku z PTC.23

W analizie regresji wieloczynnikowej Coxa stwierdzono, że wiek i maksymalna wielkość przerzutowych węzłów chłonnych są znacząco związane z przeżyciem wolnym od choroby (DFS).24

Przerzuty do węzłów chłonnych

Współczynnik przerzutów do węzłów chłonnych (LNR) znalazł się wśród 2 najważniejszych zmiennych, a stadium N wśród 5 najważniejszych zmiennych według wszystkich modeli prognostycznych.25

W badaniach pediatrycznego raka brodawkowatego tarczycy (PPTC) wykazano, że wiek i przerzuty do węzłów chłonnych są ważnymi wskaźnikami prognostycznymi, co pokrywa się z wcześniejszymi ustaleniami.26

Systemy stratyfikacji ryzyka w raku tarczycy

System Stratyfikacji Ryzyka ATA (American Thyroid Association) jest szeroko stosowaną metodą szacowania rokowania i ryzyka nawrotu w oparciu o określone cechy i pomaga w ukierunkowaniu leczenia i obserwacji pacjentów z rakiem tarczycy.27

Modele dynamiczne oceny ryzyka

Aby przezwyciężyć ograniczenia systemów opartych na statycznych parametrach, większość wytycznych opracowała dynamiczny model prognostyczny, w którym ewolucja choroby, oceniana na podstawie poablacyjnych danych biochemicznych i morfologicznych, została dodana do parametrów statycznych.28

Zgodnie z takim podejściem, długoterminowe postępowanie w PTC jest określane przez tzw. ocenę odpowiedzi na początkową terapię, dynamiczną ocenę opartą na określeniu statusu choroby rozpoczynającą się 6-18 miesięcy po ablacji tarczycy i aktualizowaną przy każdej wizycie kontrolnej. Włączenie takiego parametru do oceny prognostycznej wykazało dramatyczną poprawę mocy stratyfikacji ryzyka.29

Opracowano model drzewa decyzyjnego, który jest w stanie dostarczyć wiarygodnych informacji na temat prawdopodobieństwa strukturalnie i/lub biochemicznie przetrwałego/nawrotowego zróżnicowanego raka tarczycy (DTC) po całkowitej tyreoidektomii. Badania wykazały, że wartości tyreoglobuliny (Tg) ≥63,1 ng/mL przewidywały krótszy czas przeżycia, ze zwiększonym DFS-SD dla wartości Tg ≥63,1 i ≥8,9 ng/mL.30

Wykorzystanie uczenia maszynowego w stratyfikacji ryzyka

Modele uczenia maszynowego, szczególnie wielowarstwowe perceptrony (MLP), wykorzystujące dane z dużych grup pacjentów z rakiem tarczycy, wykazały, że niespecjalistyczne i istniejące zapisy medyczne mogą być wiarygodnie przekształcone w moc predykcji, aby pomóc lekarzom podejmować świadome i zoptymalizowane decyzje dotyczące leczenia.31

Najdokładniejszy model, MLP-1, wykazał dokładność 94,49% (94,45% przypadków żyjących i 96,36% zgonów związanych z rakiem tarczycy). Pomimo nierównowagi klas, która zwykle wpływa na wydajność MLP, osiągnięto figury dokładności klasyfikacji dla obu klas, co oznacza, że znaleziono silne związki między zastosowanymi zmiennymi niezależnymi i zależnymi.32

W przypadku pediatrycznego raka brodawkowatego tarczycy (PPTC) model oparty na białkach (ProtRsf) osiągnął dokładność 88,24% w stratyfikacji pacjentów z PPTC na grupy o wysokim lub niskim ryzyku nawrotu.33

Model Random Forest (RF) osiągnął oczekiwaną wydajność predykcji z ogólnie dobrą dyskryminacją, kalibracją i interpretowalnością w badaniach dotyczących przewidywania nawrotu strukturalnego u pacjentów z PTC.3435

Obrazowanie w prognozowaniu wyników leczenia raka tarczycy

Rola PET/CT w przewidywaniu odpowiedzi na leczenie lenwatynibem

Lenwatynim jest szeroko stosowany w leczeniu nieoperacyjnych i zaawansowanych raków tarczycy. Badania wykazały, że efekty terapeutyczne lenwatynibu można wykryć wcześniej niż w przypadku CT, jako zmniejszenie wychwytu FDG (fluorodeoksyglukozy) w badaniu PET/CT.36

Badanie PET/CT wykonane 1 tydzień po rozpoczęciu leczenia lenwatynibem może przewidzieć wyniki leczenia u pacjentów ze zróżnicowanym rakiem tarczycy (DTC). Analiza krzywej ROC dała wartość AUC 0,714 dla SUVmax po 1 tygodniu leczenia lenwatynibem.37

Mediana przeżycia wolnego od progresji wynosiła 26,3 miesiąca u pacjentów z wartością poniżej wartości odcięcia i 19,7 miesiąca u pacjentów z wartością powyżej wartości odcięcia (P=0,078).38

Przyszłe kierunki w prognozowaniu raka tarczycy

W przyszłości zasada stojąca za podejściem opartym na uczeniu maszynowym może być wdrożona w celu przewidywania, podczas projektowania badań klinicznych, prawdopodobieństwa korzystnych efektów wśród określonych subpopulacji reprezentujących określone cechy, przy jednoczesnym minimalizowaniu ryzyka związanego z innymi podczas testowania nowych kandydatów na leki.39

Istnieje duża potrzeba danych z prospektywnych badań obserwacyjnych, aby dopracować rzeczywisty wpływ każdej cechy klinicznej na wynik choroby i poprawić narzędzia oceny ryzyka.40

Wyniki badań sugerują, że systemy uczenia maszynowego wykorzystujące duże bazy danych mogą poprawić przewidywanie przetrwania lub nawrotu raka tarczycy. Włączenie dodatkowych zmiennych niż te używane w obecnych systemach stratyfikacji ryzyka może poprawić ocenę ryzyka. Stanowi to ważny krok w kierunku medycyny precyzyjnej w przewidywaniu nawrotu raka tarczycy.41

Badania molekularne guzków tarczycy zapewniają dokładniejsze przewidywanie zachowania guza w porównaniu z samą wielkością guza. Sugeruje to, że przyszłe systemy oceny mogłyby skorzystać z włączenia wzorców alteracji molekularnych do swoich algorytmów.42

Podsumowanie

Rokowanie w raku tarczycy, a w szczególności w raku brodawkowatym tarczycy (PTC), jest ogólnie bardzo dobre, z wysokimi wskaźnikami przeżycia. Jednak identyfikacja pacjentów z większym ryzykiem nawrotu lub agresywnego przebiegu choroby pozostaje wyzwaniem klinicznym.

Badania wskazują, że markery molekularne, takie jak mutacje BRAF i TERT, wzorce molekularne (BRAF-like, RAS-like, NBNR), wraz z czynnikami klinicznymi (wiek, płeć, charakterystyka guza, przerzuty do węzłów chłonnych) odgrywają kluczową rolę w przewidywaniu rokowania.

Dynamiczne modele oceny ryzyka, uwzględniające ewolucję choroby, oraz zaawansowane metody uczenia maszynowego stanowią obiecujące podejścia do poprawy stratyfikacji ryzyka i personalizacji leczenia pacjentów z rakiem tarczycy. Integracja badań molekularnych z praktyką kliniczną może przyczynić się do dalszej poprawy wyników leczenia w tej chorobie.

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. 09.04.2026
  2. www.leksykon.com.pl

Materiały źródłowe

  • #1 Thyroid Cancer: Types, Symptoms, Causes & Treatment
    https://my.clevelandclinic.org/health/diseases/12210-thyroid-cancer
    Thyroid cancer, a type of endocrine cancer, is generally highly treatable, with an excellent cure rate. […] Treatments for most thyroid cancers are very successful. Still, about 2,000 people die from the disease every year. […] Overall, thyroid cancer prognosis (outlook) is positive. […] Eight out of 10 people who have thyroid cancer develop the papillary type. Papillary thyroid cancer has a five-year survival rate of almost 100% when the cancer is in their gland (localized). Even when the cancer spreads (metastasizes), the survival rate is close to 80%. […] Yes, most thyroid cancers are curable with treatment, especially if the cancer cells haven’t spread to distant parts of your body.
  • #2 Frontiers | Editorial: Papillary thyroid cancer: prognostic factors and risk assessment
    https://www.frontiersin.org/journals/endocrinology/articles/10.3389/fendo.2025.1578271/abstract
    Thyroid cancer is not only the most common endocrine malignancy, but its incidence has been continuously growing during the last 40 years, being more than triplicated. Among thyroid malignancies, papillary thyroid cancer (PTC) is by far the most common, reaching a prevalence of about 80%, and, notably, represents the unique responsible for the increased incidence. Upon thyroid ablation (thyroidectomy with or without iodine-131 administration), PTC has excellent prognosis with nearly 100% 5-years disease-specific survival and very low risk of disease recurrence. However, 25-30% of patients experience persistent structural disease/recurrence upon initial standard treatment, and a relevant portion of them (11 and 57% for those showing lymph node (LN) and distant metastases, respectively) die as related to PTC.
  • #3 Survival statistics for thyroid cancer | Canadian Cancer Society
    https://cancer.ca/en/cancer-information/cancer-types/thyroid/prognosis-and-survival/survival-statistics
    Survival statistics for thyroid 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. […] In Canada, the 5-year net survival for thyroid cancer is 97%. This means that, on average, about 97% of people diagnosed with thyroid cancer will survive for at least 5 years. […] Generally, the earlier thyroid cancer is diagnosed and treated, the better the outcome. […] Survival by stage and type of tumour for thyroid cancer is reported as 5-year relative survival. […] There are no specific Canadian statistics available for the different stages of thyroid cancer. […] All anaplastic thyroid cancers are stage 4. The 5-year relative survival is about 7%.
  • #4 Development and validation of a nomogram to predict cancer-specific survival in middle-aged patients with papillary thyroid cancer: A SEER database study
    https://pmc.ncbi.nlm.nih.gov/articles/PMC9958280/
    Thyroid cancer (TC) accounts for more than 90% of endocrine tumours and is a typical head and neck tumour in adults. The aim of this study was to develop a predictive tool to predict cancer-specific survival (CSS) in middle-aged patients with papillary thyroid carcinoma (PTC). […] The prognosis of PTC is generally good, with a 10-year survival rate of 80%95%. However, middle-aged PTC is prone to local lymphatic metastasis and distant metastasis. Among them, it is associated with poor prognosis. A study has shown that patients with distant metastatic PTC have a 10-year survival rate of 25%70%. […] Therefore, it is important to accurately predict the survival of middle-aged PTC patients, including cancer-specific survival (CSS). […] In this study, we found that the following parameters were independent risk factors affecting the CSS of patients: age, gender, tumour size, marriage, TNM stage, tumour grade, surgical method, and chemotherapy.
  • #5 Thyroid Cancer: Types, Symptoms, Causes & Treatment
    https://my.clevelandclinic.org/health/diseases/12210-thyroid-cancer
    Thyroid cancer, a type of endocrine cancer, is generally highly treatable, with an excellent cure rate. […] Treatments for most thyroid cancers are very successful. Still, about 2,000 people die from the disease every year. […] Overall, thyroid cancer prognosis (outlook) is positive. […] Eight out of 10 people who have thyroid cancer develop the papillary type. Papillary thyroid cancer has a five-year survival rate of almost 100% when the cancer is in their gland (localized). Even when the cancer spreads (metastasizes), the survival rate is close to 80%. […] Yes, most thyroid cancers are curable with treatment, especially if the cancer cells haven’t spread to distant parts of your body.
  • #6 Frontiers | Editorial: Papillary thyroid cancer: prognostic factors and risk assessment
    https://www.frontiersin.org/journals/endocrinology/articles/10.3389/fendo.2025.1578271/abstract
    Thyroid cancer is not only the most common endocrine malignancy, but its incidence has been continuously growing during the last 40 years, being more than triplicated. Among thyroid malignancies, papillary thyroid cancer (PTC) is by far the most common, reaching a prevalence of about 80%, and, notably, represents the unique responsible for the increased incidence. Upon thyroid ablation (thyroidectomy with or without iodine-131 administration), PTC has excellent prognosis with nearly 100% 5-years disease-specific survival and very low risk of disease recurrence. However, 25-30% of patients experience persistent structural disease/recurrence upon initial standard treatment, and a relevant portion of them (11 and 57% for those showing lymph node (LN) and distant metastases, respectively) die as related to PTC.
  • #7 Development and validation of prediction models for papillary thyroid cancer structural recurrence using machine learning approaches | BMC Cancer | Full Text
    https://bmccancer.biomedcentral.com/articles/10.1186/s12885-024-12146-4
    Although papillary thyroid cancer (PTC) patients are known to have an excellent prognosis, up to 30% of patients experience disease recurrence after initial treatment. […] Accurately predicting disease prognosis remains a challenge given that the predictive value of several predictors remains controversial. […] This study sheds light on the potential of ML approaches for improving the accuracy of risk stratification for PTC patients. […] Therefore, accurate risk stratification and individualized treatment and follow-up strategies are essential for detecting recurrent disease early and improving the prognosis of PTC patients. […] The RF model achieved the expected prediction performance with generally good discrimination, calibration and interpretability in this study. […] Thus, ML models may aid in treatment decision making and improve postoperative prognosis for PTC patients by accurately estimating the likelihood of structural recurrence and identifying patients at high risk of recurrence.
  • #8 Prognostic evaluation model for papillary thyroid cancer: a retrospective study of 660 cases – Cao – Gland Surgery
    https://gs.amegroups.org/article/view/72888/html
    Prognostic evaluation model for papillary thyroid cancer is very important for guiding the personalized treatment and follow-up strategy. […] The prognosis of papillary thyroid cancer is very good after appropriate treatment. Age and the dimension of lymph nodes involved were independent influence factors of disease-free survival for papillary thyroid cancer. A prognostic prediction model for Chinese population was established with moderate predictive value. […] The clinical biological behavior of PTC is relatively inert, and the 10-year survival rate can reach more than 90% after reasonable treatment. However, postoperative recurrence or metastasis cannot be avoided in some patients. […] The 5-, 10- and 15-year DFS were 95.5%, 90.2% and 89.2%, respectively. The OS at 5, 10 and 15 years were 99.7%, 99.2% and 99.1%, respectively.
  • #9 Survival statistics for thyroid cancer | Canadian Cancer Society
    https://cancer.ca/en/cancer-information/cancer-types/thyroid/prognosis-and-survival/survival-statistics
    Survival statistics for thyroid 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. […] In Canada, the 5-year net survival for thyroid cancer is 97%. This means that, on average, about 97% of people diagnosed with thyroid cancer will survive for at least 5 years. […] Generally, the earlier thyroid cancer is diagnosed and treated, the better the outcome. […] Survival by stage and type of tumour for thyroid cancer is reported as 5-year relative survival. […] There are no specific Canadian statistics available for the different stages of thyroid cancer. […] All anaplastic thyroid cancers are stage 4. The 5-year relative survival is about 7%.
  • #10 Survival statistics for thyroid cancer | Canadian Cancer Society
    https://cancer.ca/en/cancer-information/cancer-types/thyroid/prognosis-and-survival/survival-statistics
    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.
  • #11 Thyroid Cancer Survival Rates | American Cancer Society
    https://www.cancer.org/cancer/types/thyroid-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 one 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. […] These numbers dont take everything into account. Survival rates are grouped based on how far the cancer has spread, but your age and overall health, the type of thyroid cancer you have, how well the cancer responds to treatment, and other factors can also affect your outlook. […] People now being diagnosed with thyroid cancer may have a better outlook than these numbers show. Treatments have improved over time, and these numbers are based on people who were diagnosed and treated at least five years earlier.
  • #12 Genetic Determinants for Prediction of Outcome of Patients with Papillary Thyroid Carcinoma
    https://pmc.ncbi.nlm.nih.gov/articles/PMC8122921/
    Aggressive metastatic disease is rare in papillary thyroid carcinoma (PTC), a neoplasia that usually carries an excellent prognosis. […] We aimed to determine the role of genetic alterations in PTC patient outcomes (recurrent/persistent disease, structural disease, and disease-specific mortality (DSM)). […] Our results indicate that different molecular markers play a distinct role in predicting PTC patient outcomes. […] Patients with tumors BRAFwt/TERTpmut (HR = 24.2, p 0.001) and BRAFmut/TERTpmut (HR = 11.5, p = 0.002) showed increased risk of structural disease. […] DSM was significantly increased in patients with TERTpmut regardless of BRAF status (BRAFmut/TERTpmut, log-rank p 0.001; BRAFwt/TERTpmut, log-rank p 0.001). […] Our results indicate that molecular markers may have a role in predicting PTC patients outcome.
  • #13 Genetic Determinants for Prediction of Outcome of Patients with Papillary Thyroid Carcinoma
    https://www.mdpi.com/2072-6694/13/9/2048
    Genetic Determinants for Prediction of Outcome of Patients with Papillary Thyroid Carcinoma […] Aggressive metastatic disease is rare in papillary thyroid carcinoma (PTC), a neoplasia that usually carries an excellent prognosis. […] We performed Sanger sequencing on a series of 241 PTCs to determine the role of genetic mutations (BRAF, RAS, and TERTp) in PTC patient outcomes. […] Our results indicate that different molecular markers play a distinct role in predicting PTC patient outcomes. […] Papillary thyroid carcinoma (PTC) usually presents an excellent prognosis, but some patients present with aggressive metastatic disease. […] The series included 241 PTC patients submitted to surgery, between 2002–2015, in a single hospital. […] Isolated TERTpmut showed increased risk of structural disease (HR = 7.0, p < 0.001) and DSM (HR = 10.1, p = 0.001). [...] Our results indicate that molecular markers may have a role in predicting PTC patients’ outcome.
  • #14 Genetic Determinants for Prediction of Outcome of Patients with Papillary Thyroid Carcinoma
    https://www.mdpi.com/2072-6694/13/9/2048
    Genetic Determinants for Prediction of Outcome of Patients with Papillary Thyroid Carcinoma […] Aggressive metastatic disease is rare in papillary thyroid carcinoma (PTC), a neoplasia that usually carries an excellent prognosis. […] We performed Sanger sequencing on a series of 241 PTCs to determine the role of genetic mutations (BRAF, RAS, and TERTp) in PTC patient outcomes. […] Our results indicate that different molecular markers play a distinct role in predicting PTC patient outcomes. […] Papillary thyroid carcinoma (PTC) usually presents an excellent prognosis, but some patients present with aggressive metastatic disease. […] The series included 241 PTC patients submitted to surgery, between 2002–2015, in a single hospital. […] Isolated TERTpmut showed increased risk of structural disease (HR = 7.0, p < 0.001) and DSM (HR = 10.1, p = 0.001). [...] Our results indicate that molecular markers may have a role in predicting PTC patients’ outcome.
  • #15 Genetic Determinants for Prediction of Outcome of Patients with Papillary Thyroid Carcinoma
    https://www.mdpi.com/2072-6694/13/9/2048
    In our study, TERTpmut tumors were associated with significantly lower structural disease-free survival (SDFS) (log-rank p < 0.001) than patients without TERTpmut. [...] Furthermore, patients with TERTpmut tumors presented a significantly increased risk of structural disease and of DSM, after adjustment for age and gender, suggesting that TERTpmut may contribute to worse prognosis in PTC patients. [...] We realize that our series has advantages and disadvantages; the positive aspect resides in the fact that it is a consecutive real-life series obtained from a single hospital and not a selected series. [...] Summing up, our results indicate that molecular markers can play a role in predicting the outcome of PTC patients.
  • #16 Genetic Determinants for Prediction of Outcome of Patients with Papillary Thyroid Carcinoma
    https://pmc.ncbi.nlm.nih.gov/articles/PMC8122921/
    Aggressive metastatic disease is rare in papillary thyroid carcinoma (PTC), a neoplasia that usually carries an excellent prognosis. […] We aimed to determine the role of genetic alterations in PTC patient outcomes (recurrent/persistent disease, structural disease, and disease-specific mortality (DSM)). […] Our results indicate that different molecular markers play a distinct role in predicting PTC patient outcomes. […] Patients with tumors BRAFwt/TERTpmut (HR = 24.2, p 0.001) and BRAFmut/TERTpmut (HR = 11.5, p = 0.002) showed increased risk of structural disease. […] DSM was significantly increased in patients with TERTpmut regardless of BRAF status (BRAFmut/TERTpmut, log-rank p 0.001; BRAFwt/TERTpmut, log-rank p 0.001). […] Our results indicate that molecular markers may have a role in predicting PTC patients outcome.
  • #17 Genetic Determinants for Prediction of Outcome of Patients with Papillary Thyroid Carcinoma
    https://pmc.ncbi.nlm.nih.gov/articles/PMC8122921/
    TERTpmut tumors were associated with significantly lower SDFS and significantly increased DSM. […] Given previous studies showing a frequent concomitant BRAFmut and TERTpmut in thyroid cancer, we tested the possible relationship of molecular status combinations and different outcomes. […] We observed that BRAFmut/TERTpwt tumors were associated with an increased risk of recurrent/persistent disease. […] These results should be evaluated with caution also due to the low number of patients with some genotypes. […] Summing up, our results indicate that molecular markers can play a role in predicting the outcome of PTC patients.
  • #18 Molecular alteration patterns predict tumor behavior in papillary thyroid carcinoma independent of tumor size: insights from an international multicenter retrospective study | Thyroid Research | Full Text
    https://thyroidresearchjournal.biomedcentral.com/articles/10.1186/s13044-025-00231-0
    Molecular testing of thyroid nodules provides a more accurate prediction of tumor behavior compared to tumor size alone. These findings suggest that future staging systems could benefit from incorporating molecular alteration patterns into their algorithms. […] This large retrospective multi-institutional international study showed that molecular alterations patterns, BRAF-like, RAS-like, and non-BRAF-non-RAS (NBNR), may be associated with tumor behavior, predicting aggressive features such as nodal metastasis and extrathyroidal extension better than tumor size. […] Interestingly, our study also has mostly young patients with small tumors, as the median tumor size was 15 mm (interquartile range 1024 mm). In other words, only a few patients were staged T3 because of tumor size alone. […] In conclusion, in the current era, relying solely on tumor size as a prognostic marker in papillary thyroid carcinoma may be inadequate, as early-detected small tumors might not fully exhibit their aggressive potential. Our findings suggest that molecular alteration patterns such as BRAF-like, RAS-like, and NBNR provide a more accurate prediction of aggressive behavior. Integrating molecular profiling into clinical practice could enhance the precision of treatment strategies, particularly for early-stage, small tumors. The additional certainty regarding the prognosis is expected to translate to decreased stress and reduced anxiety in patients.
  • #19 Molecular alteration patterns predict tumor behavior in papillary thyroid carcinoma independent of tumor size: insights from an international multicenter retrospective study | Thyroid Research | Full Text
    https://thyroidresearchjournal.biomedcentral.com/articles/10.1186/s13044-025-00231-0
    Molecular testing of thyroid nodules provides a more accurate prediction of tumor behavior compared to tumor size alone. These findings suggest that future staging systems could benefit from incorporating molecular alteration patterns into their algorithms. […] This large retrospective multi-institutional international study showed that molecular alterations patterns, BRAF-like, RAS-like, and non-BRAF-non-RAS (NBNR), may be associated with tumor behavior, predicting aggressive features such as nodal metastasis and extrathyroidal extension better than tumor size. […] Interestingly, our study also has mostly young patients with small tumors, as the median tumor size was 15 mm (interquartile range 1024 mm). In other words, only a few patients were staged T3 because of tumor size alone. […] In conclusion, in the current era, relying solely on tumor size as a prognostic marker in papillary thyroid carcinoma may be inadequate, as early-detected small tumors might not fully exhibit their aggressive potential. Our findings suggest that molecular alteration patterns such as BRAF-like, RAS-like, and NBNR provide a more accurate prediction of aggressive behavior. Integrating molecular profiling into clinical practice could enhance the precision of treatment strategies, particularly for early-stage, small tumors. The additional certainty regarding the prognosis is expected to translate to decreased stress and reduced anxiety in patients.
  • #20 Development and validation of a nomogram to predict cancer-specific survival in middle-aged patients with papillary thyroid cancer: A SEER database study
    https://pmc.ncbi.nlm.nih.gov/articles/PMC9958280/
    Thyroid cancer (TC) accounts for more than 90% of endocrine tumours and is a typical head and neck tumour in adults. The aim of this study was to develop a predictive tool to predict cancer-specific survival (CSS) in middle-aged patients with papillary thyroid carcinoma (PTC). […] The prognosis of PTC is generally good, with a 10-year survival rate of 80%95%. However, middle-aged PTC is prone to local lymphatic metastasis and distant metastasis. Among them, it is associated with poor prognosis. A study has shown that patients with distant metastatic PTC have a 10-year survival rate of 25%70%. […] Therefore, it is important to accurately predict the survival of middle-aged PTC patients, including cancer-specific survival (CSS). […] In this study, we found that the following parameters were independent risk factors affecting the CSS of patients: age, gender, tumour size, marriage, TNM stage, tumour grade, surgical method, and chemotherapy.
  • #21 Prognostic evaluation model for papillary thyroid cancer: a retrospective study of 660 cases – Cao – Gland Surgery
    https://gs.amegroups.org/article/view/72888/html
    The results showed age (HR 2.00, 95% CI: 1.173.42, P0.05) and maximum size of metastatic lymph node (HR 1.75, 95% CI: 1.122.74, P0.05) were significantly correlated with DFS. […] Our results showed age as a prognosis factor both with the cut-off point of 45 (HR 2.00, 95% CI: 1.173.42, P0.05) and 55 (HR 2.76, 95% CI: 1.704.50, P0.05). […] In Cox multivariate regression analysis, age and maximum size of metastatic lymph nodes were found to be significantly associated with DFS. […] To test the prediction value of the nomogram model, the consistency index (C-index) was calculated to be 0.71 (95% CI: 0.570.84), suggesting the model has medium predictive value.
  • #22 Development and validation of a nomogram to predict cancer-specific survival in middle-aged patients with papillary thyroid cancer: A SEER database study
    https://pmc.ncbi.nlm.nih.gov/articles/PMC9958280/
    Thyroid cancer (TC) accounts for more than 90% of endocrine tumours and is a typical head and neck tumour in adults. The aim of this study was to develop a predictive tool to predict cancer-specific survival (CSS) in middle-aged patients with papillary thyroid carcinoma (PTC). […] The prognosis of PTC is generally good, with a 10-year survival rate of 80%95%. However, middle-aged PTC is prone to local lymphatic metastasis and distant metastasis. Among them, it is associated with poor prognosis. A study has shown that patients with distant metastatic PTC have a 10-year survival rate of 25%70%. […] Therefore, it is important to accurately predict the survival of middle-aged PTC patients, including cancer-specific survival (CSS). […] In this study, we found that the following parameters were independent risk factors affecting the CSS of patients: age, gender, tumour size, marriage, TNM stage, tumour grade, surgical method, and chemotherapy.
  • #23 Development and validation of a nomogram to predict cancer-specific survival in middle-aged patients with papillary thyroid cancer: A SEER database study
    https://pmc.ncbi.nlm.nih.gov/articles/PMC9958280/
    Thyroid cancer (TC) accounts for more than 90% of endocrine tumours and is a typical head and neck tumour in adults. The aim of this study was to develop a predictive tool to predict cancer-specific survival (CSS) in middle-aged patients with papillary thyroid carcinoma (PTC). […] The prognosis of PTC is generally good, with a 10-year survival rate of 80%95%. However, middle-aged PTC is prone to local lymphatic metastasis and distant metastasis. Among them, it is associated with poor prognosis. A study has shown that patients with distant metastatic PTC have a 10-year survival rate of 25%70%. […] Therefore, it is important to accurately predict the survival of middle-aged PTC patients, including cancer-specific survival (CSS). […] In this study, we found that the following parameters were independent risk factors affecting the CSS of patients: age, gender, tumour size, marriage, TNM stage, tumour grade, surgical method, and chemotherapy.
  • #24 Prognostic evaluation model for papillary thyroid cancer: a retrospective study of 660 cases – Cao – Gland Surgery
    https://gs.amegroups.org/article/view/72888/html
    The results showed age (HR 2.00, 95% CI: 1.173.42, P0.05) and maximum size of metastatic lymph node (HR 1.75, 95% CI: 1.122.74, P0.05) were significantly correlated with DFS. […] Our results showed age as a prognosis factor both with the cut-off point of 45 (HR 2.00, 95% CI: 1.173.42, P0.05) and 55 (HR 2.76, 95% CI: 1.704.50, P0.05). […] In Cox multivariate regression analysis, age and maximum size of metastatic lymph nodes were found to be significantly associated with DFS. […] To test the prediction value of the nomogram model, the consistency index (C-index) was calculated to be 0.71 (95% CI: 0.570.84), suggesting the model has medium predictive value.
  • #25 Development and validation of prediction models for papillary thyroid cancer structural recurrence using machine learning approaches | BMC Cancer | Full Text
    https://bmccancer.biomedcentral.com/articles/10.1186/s12885-024-12146-4
    Overall, we suggested that the RF model, which showed overall good performance and interpretability, could be used to predict structural recurrence in patients with PTC. […] The LNR was among the 2 most important variables, and the N stage was among the 5 most important variables according to all the models. […] The underlying mechanism between metabolism-related predictors and poor prognosis in PTC patients is less clear. […] This study demonstrated that the RF model achieved the expected prediction performance with generally good discrimination, calibration and interpretability.
  • #26 An individualized protein-based prognostic model to stratify pediatric patients with papillary thyroid carcinoma | Nature Communications
    https://www.nature.com/articles/s41467-024-47926-w
    Our results showed that age, TLNN, and LLNN may be risk factors for recurrence in pediatric patients. […] The model could correctly predict the prognosis of 75 cases of our 85 PM patients with an accuracy of 88.24%. […] In our study, we found age and lymph node metastases were important prognostic indicators of PPTC which are matched with previous findings. […] The high expression of LGALS3 might promote cancer invasion and impede the function of the immune system to make the cell apoptosis, leading to cancer recurrence. […] Based on the 19-protein panel, our ProtRsf model achieved an accuracy of 88.24% in stratifying PPTC patients into groups with a high or low risk of recurrence. […] The findings of this study have to be seen in the light of some limitations. This is a retrospective study in a single center; therefore, future studies will validate the model on preoperative prospective samples in more centers to cover the diversity of the samples.
  • #27 Predicting thyroid cancer outcomes using machine learning: a move toward precision medicine
    https://www.thyroid.org/patient-thyroid-information/ct-for-patients/april-2024/vol-17-issue-4-p-11-12/
    Thyroid cancer has an excellent overall prognosis with a low recurrence rate and very few patients actually die from the disease. This is because the cancer is very slow growing and we have very effective treatments, including surgery and radioactive iodine therapy. […] The ATA Risk Stratification System is a widely used method to estimate the prognosis and recurrence risk based on specific features and helps to guide treatment and follow-up for thyroid cancer patients. […] The two decision-tree models showed better performance as compared with the ATA Risk Stratification System. […] Several factors not included in the ATA risk stratification system, such as age, gender, body-mass index (BMI), circumstance of cancer diagnosis, family history of thyroid cancer, surgical method, presurgical cytology result from thyroid nodule biopsy were found to affect the prediction of thyroid cancer persistence or recurrence.
  • #28 Frontiers | Editorial: Papillary thyroid cancer: prognostic factors and risk assessment
    https://www.frontiersin.org/journals/endocrinology/articles/10.3389/fendo.2025.1578271/abstract
    In order to overcome these limitations, the majority of guidelines elaborated a prognostic dynamic model, where disease evolution, as assessed by post-ablative biochemical and morphological data, was added to static parameters. According to such approach, long-term PTC management is determined by the so-called response to initial therapy assessment, a dynamic evaluation based on the determination of disease status starting 6-18 months after thyroid ablation, and updated at each follow-up visit. The incorporation of such parameter in the prognostic staging has demonstrated dramatic improvement of the risk stratification power. […] However, an improvement of PTC risk stratification, as based on initial clinico-pathological features, is still required for optimizing clinical management, especially in some challenging settings, such as the heterogeneous category of subjects at intermediate risk of recurrence and the micro-PTC. Aim of the present Research Topic was to refine the risk assessment of PTC, also focalizing on specific pathological features and PTC settings.
  • #29 Frontiers | Editorial: Papillary thyroid cancer: prognostic factors and risk assessment
    https://www.frontiersin.org/journals/endocrinology/articles/10.3389/fendo.2025.1578271/abstract
    In order to overcome these limitations, the majority of guidelines elaborated a prognostic dynamic model, where disease evolution, as assessed by post-ablative biochemical and morphological data, was added to static parameters. According to such approach, long-term PTC management is determined by the so-called response to initial therapy assessment, a dynamic evaluation based on the determination of disease status starting 6-18 months after thyroid ablation, and updated at each follow-up visit. The incorporation of such parameter in the prognostic staging has demonstrated dramatic improvement of the risk stratification power. […] However, an improvement of PTC risk stratification, as based on initial clinico-pathological features, is still required for optimizing clinical management, especially in some challenging settings, such as the heterogeneous category of subjects at intermediate risk of recurrence and the micro-PTC. Aim of the present Research Topic was to refine the risk assessment of PTC, also focalizing on specific pathological features and PTC settings.
  • #30 Thyroglobulin measurement is the most powerful outcome predictor in differentiated thyroid cancer: a decision tree analysis in a European multicenter series
    https://www.degruyter.com/document/doi/10.1515/cclm-2024-0405/html?lang=en
    An accurate prognostic assessment is pivotal to adequately inform and individualize follow-up and management of patients with differentiated thyroid cancer (DTC). […] We developed a simple, accurate and reproducible decision tree model able to provide reliable information on the probability of structurally and/or biochemically persistent/relapsed DTC after a TTA. […] Notably, Tg values 63.1ng/mL predicted a shorter survival time, with increased DFS-SD for Tg values 63.1 and 8.9ng/mL, respectively. […] A comparable model was generated for biochemical disease (BD), albeit different DFS were predicted by slightly different Tg cutoff values (41.2 and 8.8ng/mL) compared to DFS-SD.
  • #31 Machine Learning and Feature Selection Applied to SEER Data to Reliably Assess Thyroid Cancer Prognosis | Scientific Reports
    https://www.nature.com/articles/s41598-020-62023-w
    Utilizing historical clinical datasets to guide future treatment choices is beneficial for patients and physicians. […] By properly optimizing supervised neural networks, specifically multilayer perceptrons, using data from large groups of thyroid cancer patients (between 6,756 and 20,344 for different models), we demonstrate that unspecialized and existing medical recording can be reliably turned into power of prediction to help doctors make informed and optimized treatment decisions, as distinguishing patients in terms of prognosis has been achieved with 94.5% accuracy. […] Our study has led to the most accurate method to date utilized to predict thyroid cancer survival using data compiled from the SEER program registry. […] Consequently, we believe our findings reveal the need for change in current thyroid cancer assessment standards, coinciding with new studies in the field.
  • #32 Machine Learning and Feature Selection Applied to SEER Data to Reliably Assess Thyroid Cancer Prognosis | Scientific Reports
    https://www.nature.com/articles/s41598-020-62023-w
    The ability to model tumour behaviour has large implications in the staging and prognostication of cancer. […] Our most accurate model, MLP-1, showed an accuracy of 94.49% (94.45% of alive cases and 96.36% of thyroid cancer related death; Table 3). […] Despite this fact, which typically affects the performance of MLPs, remarkable classification accuracies are achieved for both classes, signifying that strong relationships have been found between the independent and dependent variables employed. […] Our MLP-1 and MLP-2 have validated the relevance of extrathyroidal spread leading to more accurate prognostic modelling by allowing it to have variable weighting depending on the value of other clinical variables, most notably age and location of positive nodes. […] The prediction of thyroid cancer outcomes was still possible, while maintaining a strong statistical performance in terms of global accuracy (from 94.5% (MLP-1) to 91.1% (MLP-2); Table 3), although the correct estimation of COD-TC cases (sensitivity) was slightly lower (from 96.4% to 91.4%; Table 3).
  • #33 An individualized protein-based prognostic model to stratify pediatric patients with papillary thyroid carcinoma | Nature Communications
    https://www.nature.com/articles/s41467-024-47926-w
    Our results showed that age, TLNN, and LLNN may be risk factors for recurrence in pediatric patients. […] The model could correctly predict the prognosis of 75 cases of our 85 PM patients with an accuracy of 88.24%. […] In our study, we found age and lymph node metastases were important prognostic indicators of PPTC which are matched with previous findings. […] The high expression of LGALS3 might promote cancer invasion and impede the function of the immune system to make the cell apoptosis, leading to cancer recurrence. […] Based on the 19-protein panel, our ProtRsf model achieved an accuracy of 88.24% in stratifying PPTC patients into groups with a high or low risk of recurrence. […] The findings of this study have to be seen in the light of some limitations. This is a retrospective study in a single center; therefore, future studies will validate the model on preoperative prospective samples in more centers to cover the diversity of the samples.
  • #34 Development and validation of prediction models for papillary thyroid cancer structural recurrence using machine learning approaches | BMC Cancer | Full Text
    https://bmccancer.biomedcentral.com/articles/10.1186/s12885-024-12146-4
    Although papillary thyroid cancer (PTC) patients are known to have an excellent prognosis, up to 30% of patients experience disease recurrence after initial treatment. […] Accurately predicting disease prognosis remains a challenge given that the predictive value of several predictors remains controversial. […] This study sheds light on the potential of ML approaches for improving the accuracy of risk stratification for PTC patients. […] Therefore, accurate risk stratification and individualized treatment and follow-up strategies are essential for detecting recurrent disease early and improving the prognosis of PTC patients. […] The RF model achieved the expected prediction performance with generally good discrimination, calibration and interpretability in this study. […] Thus, ML models may aid in treatment decision making and improve postoperative prognosis for PTC patients by accurately estimating the likelihood of structural recurrence and identifying patients at high risk of recurrence.
  • #35 Development and validation of prediction models for papillary thyroid cancer structural recurrence using machine learning approaches | BMC Cancer | Full Text
    https://bmccancer.biomedcentral.com/articles/10.1186/s12885-024-12146-4
    Overall, we suggested that the RF model, which showed overall good performance and interpretability, could be used to predict structural recurrence in patients with PTC. […] The LNR was among the 2 most important variables, and the N stage was among the 5 most important variables according to all the models. […] The underlying mechanism between metabolism-related predictors and poor prognosis in PTC patients is less clear. […] This study demonstrated that the RF model achieved the expected prediction performance with generally good discrimination, calibration and interpretability.
  • #36 Early prediction of treatment outcome for lenvatinib using 18F-FDG PET/CT in patients with unresectable or advanced thyroid carcinoma refractory to radioiodine treatment: a prospective, multicentre, non-randomised study | EJNMMI Research | Full Text
    https://ejnmmires.springeropen.com/articles/10.1186/s13550-023-01019-9
    Lenvatinib is widely used to treat unresectable and advanced thyroid carcinomas. We aimed to determine whether 18F-fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) performed 1 week after lenvatinib treatment initiation could predict treatment outcomes. […] The therapeutic effects of lenvatinib were detected earlier than those of CT because of decreased FDG uptake on PET/CT. PET/CT examination 1 week after the initiation of lenvatinib treatment may predict treatment outcomes in patients with DTC. […] The primary endpoint was to evaluate the discrimination power of maximum standardised uptake value (SUVmax) obtained by PET/CT compared to that obtained by contrast-enhanced CT. […] The ROC curve analysis yielded an AUC of 0.714 for SUVmax after 1 week of lenvatinib treatment.
  • #37 Early prediction of treatment outcome for lenvatinib using 18F-FDG PET/CT in patients with unresectable or advanced thyroid carcinoma refractory to radioiodine treatment: a prospective, multicentre, non-randomised study | EJNMMI Research | Full Text
    https://ejnmmires.springeropen.com/articles/10.1186/s13550-023-01019-9
    Lenvatinib is widely used to treat unresectable and advanced thyroid carcinomas. We aimed to determine whether 18F-fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) performed 1 week after lenvatinib treatment initiation could predict treatment outcomes. […] The therapeutic effects of lenvatinib were detected earlier than those of CT because of decreased FDG uptake on PET/CT. PET/CT examination 1 week after the initiation of lenvatinib treatment may predict treatment outcomes in patients with DTC. […] The primary endpoint was to evaluate the discrimination power of maximum standardised uptake value (SUVmax) obtained by PET/CT compared to that obtained by contrast-enhanced CT. […] The ROC curve analysis yielded an AUC of 0.714 for SUVmax after 1 week of lenvatinib treatment.
  • #38 Early prediction of treatment outcome for lenvatinib using 18F-FDG PET/CT in patients with unresectable or advanced thyroid carcinoma refractory to radioiodine treatment: a prospective, multicentre, non-randomised study | EJNMMI Research | Full Text
    https://ejnmmires.springeropen.com/articles/10.1186/s13550-023-01019-9
    The median progression-free survival was 26.3 months in patients with an under-cut-off value and 19.7 months in patients with an over-cut-off value (P=0.078). […] In conclusion, the therapeutic effects of lenvatinib can be detected earlier than those of CT as a decrease in FDG uptake. FDG PET/CT examination 1 week after the initiation of lenvatinib treatment may predict treatment outcomes in patients with DTC. This result warrants further study to prevent adverse effects and high treatment costs.
  • #39 Machine Learning and Feature Selection Applied to SEER Data to Reliably Assess Thyroid Cancer Prognosis | Scientific Reports
    https://www.nature.com/articles/s41598-020-62023-w
    In the future, the principle behind our machine learning approach can be implemented to predict, during the design of clinical trials, the likelihood of beneficial effects among certain subpopulations representing certain traits, while minimizing the risks associated with others when testing new drug candidates.
  • #40 Frontiers | Editorial: Papillary thyroid cancer: prognostic factors and risk assessment
    https://www.frontiersin.org/journals/endocrinology/articles/10.3389/fendo.2025.1578271/abstract
    This Research Topic provides news insights about the prediction of specific pathological features affecting PTC outcome, such as the development of LN metastases, and about the risk assessment in the context of specific clinical settings, such as elderly and pediatric PTC, micro-PTC, and PTC at intermediate risk of recurrence. The main limit of the studies included in the Research Topic, similarly to the vast majority of publications about PTC prognostics, is the retrospective nature. Hence, there is a great need of data from prospective observational studies, in order to refine the actual impact of each clinical features on disease outcome and to improve the risk assessment tools.
  • #41 Predicting thyroid cancer outcomes using machine learning: a move toward precision medicine
    https://www.thyroid.org/patient-thyroid-information/ct-for-patients/april-2024/vol-17-issue-4-p-11-12/
    This study’s results suggest that machine learning systems using large databases can improve prediction of thyroid cancer persistence or recurrence. Inclusion of additional variables than those used in current risk-stratification systems can improve the risk assessment. This represents an important step towards precision medicine in predicting thyroid cancer recurrence.
  • #42 Molecular alteration patterns predict tumor behavior in papillary thyroid carcinoma independent of tumor size: insights from an international multicenter retrospective study | Thyroid Research | Full Text
    https://thyroidresearchjournal.biomedcentral.com/articles/10.1186/s13044-025-00231-0
    Molecular testing of thyroid nodules provides a more accurate prediction of tumor behavior compared to tumor size alone. These findings suggest that future staging systems could benefit from incorporating molecular alteration patterns into their algorithms. […] This large retrospective multi-institutional international study showed that molecular alterations patterns, BRAF-like, RAS-like, and non-BRAF-non-RAS (NBNR), may be associated with tumor behavior, predicting aggressive features such as nodal metastasis and extrathyroidal extension better than tumor size. […] Interestingly, our study also has mostly young patients with small tumors, as the median tumor size was 15 mm (interquartile range 1024 mm). In other words, only a few patients were staged T3 because of tumor size alone. […] In conclusion, in the current era, relying solely on tumor size as a prognostic marker in papillary thyroid carcinoma may be inadequate, as early-detected small tumors might not fully exhibit their aggressive potential. Our findings suggest that molecular alteration patterns such as BRAF-like, RAS-like, and NBNR provide a more accurate prediction of aggressive behavior. Integrating molecular profiling into clinical practice could enhance the precision of treatment strategies, particularly for early-stage, small tumors. The additional certainty regarding the prognosis is expected to translate to decreased stress and reduced anxiety in patients.