Rak piersi nawrotowy
Rokowania, prognozy i postęp choroby

Nawrotowy rak piersi może manifestować się miejscowo, regionalnie lub jako przerzuty odległe, z różnym rokowaniem zależnym od lokalizacji nawrotu oraz cech biologicznych guza. 10-letnie przeżycie po nawrocie miejscowym wynosi około 71%, a 15-letnie około 65%. Najlepsze rokowanie obserwuje się przy nawrocie miejscowym (5-letnie przeżycie 99%), gorsze przy nawrocie regionalnym (86%), a najgorsze przy przerzutach odległych (27%). Kluczowe czynniki prognostyczne to status receptora progesteronowego (ujemny PR wiąże się z gorszym rokowaniem), wiek pacjentki (<40 lat zwiększa ryzyko zgonu) oraz czas do nawrotu (nawrót przed 2 latami od diagnozy pierwotnej pogarsza prognozę). Ryzyko zgonu po nawrocie miejscowym waha się od 15% do 60%, zależnie od tych czynników. Podtypy nowotworu, takie jak zapalny rak piersi (IBC) i potrójnie ujemny rak piersi (TNBC), charakteryzują się wyższym ryzykiem nawrotu i gorszym rokowaniem, a w TNBC nawroty pojawiają się średnio po 2,6 roku od diagnozy.

Rak piersi nawrotowy – Prognoza (ocena rokowania)

Rak piersi nawrotowy (rak piersi nawracający) to nowotwór, który pojawia się ponownie po wcześniejszym leczeniu. Może wystąpić w miejscu pierwotnego guza, regionalnych węzłach chłonnych lub w odległych narządach. Ryzyko nawrotu oraz rokowanie zależą od wielu czynników, a prawidłowa ocena prognostyczna jest kluczowa dla planowania dalszego postępowania terapeutycznego.12

Wskaźniki przeżycia u pacjentów z nawrotowym rakiem piersi

Badania wskazują, że 10-letnie przeżycie pacjentów po wystąpieniu miejscowego nawrotu raka piersi wynosi około 71%, a 15-letnie przeżycie obniża się do około 65%. To pokazuje, że nawet po wystąpieniu nawrotu miejscowego, znaczna część pacjentów ma szansę na długotrwałe przeżycie.34

Różne typy nawrotu wiążą się z odmiennym rokowaniem:5

Ogólne wskaźniki 5-letniego przeżycia w zależności od lokalizacji nawrotu wynoszą:6

  • 99% dla nawrotu miejscowego
  • 86% dla nawrotu regionalnego
  • 27% dla przerzutów odległych

Główne czynniki prognostyczne wpływające na rokowanie

W analizie wieloczynnikowej zidentyfikowano kilka kluczowych czynników istotnie wpływających na ryzyko zgonu po miejscowym nawrocie raka piersi:78

  1. Status receptora progesteronowego (PR) – ujemny status PR wiąże się z gorszym rokowaniem
  2. Młody wiek w momencie diagnozy – pacjentki poniżej 40 roku życia mają wyższe ryzyko zgonu po nawrocie
  3. Czas do wystąpienia nawrotu – nawrót występujący przed upływem 2 lat od diagnozy pierwotnej wiąże się z gorszym rokowaniem

Ryzyko zgonu po nawrocie miejscowym waha się od 15% do 60%, w zależności od wieku pacjentki w momencie diagnozy, statusu receptora progesteronowego guza pierwotnego oraz czasu do wystąpienia nawrotu.910

Znaczenie czasu do wystąpienia nawrotu dla rokowania

Czas, jaki upłynął od diagnozy pierwotnej do wystąpienia nawrotu, ma istotne znaczenie prognostyczne. Im dłuższy okres bez nawrotu, tym lepsze rokowanie:1112

  • Nawroty występujące po upływie 5 lat od pierwotnej diagnozy wiążą się z lepszym rokowaniem niż nawroty wczesne (poniżej 2 lat)
  • Ryzyko zgonu z powodu raka piersi jest niższe u pacjentek z nawrotem występującym po 2 latach lub później w porównaniu do pacjentek z wcześniejszymi nawrotami (15-letnia śmiertelność z powodu raka piersi: 40% vs 55%)
  • Późne nawroty (>5 lat) są mniej agresywne i wiążą się z lepszym rokowaniem niż wczesne nawroty, co może stanowić pewne pocieszenie dla pacjentek doświadczających późnego nawrotu raka piersi

13

Podtypy raka piersi a ryzyko nawrotu

Ryzyko nawrotu różni się znacząco w zależności od podtypu raka piersi. Najwyższy odsetek nawrotów obserwuje się w przypadku:14

  • Zapalnego raka piersi (IBC) – ryzyko nawrotu miejscowego wynosi około 50%
  • Potrójnie ujemnego raka piersi (TNBC) – charakteryzuje się wyższym ryzykiem nawrotu niż nowotwory z ekspresją receptorów hormonalnych (HR+) i/lub HER2-dodatnie

W przypadku TNBC nawrót może wystąpić wcześniej niż w innych podtypach – średnio po około 2,6 roku od pierwotnej diagnozy.15

W przypadku hormono-zależnego raka piersi (HR+), w tym podtypów luminalnych A i B, wysoki odsetek limfocytów naciekających guz (TILs) wiąże się z gorszym rokowaniem. Podobnie, ekspresja CTLA-4 zarówno w komórkach nowotworowych, jak i w TILs, wiąże się z krótszym czasem przeżycia wolnego od choroby (DFS) i całkowitym przeżyciem (OS) w przypadku luminalnego B HER2-ujemnego raka piersi.16

Ryzyko nawrotu po różnych metodach leczenia pierwotnego

Ryzyko nawrotu różni się również w zależności od zastosowanego leczenia pierwotnego:17

  • Większość miejscowych nawrotów raka piersi po leczeniu oszczędzającym (lumpektomii) występuje w ciągu pierwszych 5 lat. Zastosowanie radioterapii po lumpektomii zmniejsza ryzyko nawrotu – szansa na nawrót w ciągu 10 lat wynosi 3-15% przy leczeniu skojarzonym
  • Po mastektomii wskaźniki nawrotu są zróżnicowane:
    • 6% ryzyko nawrotu w ciągu 5 lat, jeśli nie stwierdzono zajęcia węzłów chłonnych pachowych podczas pierwotnej operacji
    • 25% ryzyko nawrotu, jeśli węzły chłonne pachowe były zajęte przez nowotwór. Ryzyko to spada do 6% przy zastosowaniu radioterapii po mastektomii

Modele predykcyjne nawrotu raka piersi

W ostatnich latach opracowano liczne modele wykorzystujące uczenie maszynowe i sztuczną inteligencję do przewidywania ryzyka nawrotu raka piersi. Badania wskazują na wysoką skuteczność tych modeli:1819

  • Model oparty na algorytmie AdaBoost osiąga najlepszą dyskryminację z AUC=0,987, identyfikując cztery kluczowe czynniki: antygen rakowo-płodowy (CEA), antygen nowotworowy 125 (CA125), fibrynogen (Fbg) oraz średnicę guza
  • Modele wykorzystujące algorytmy Extra-Trees i Random Forest, uwzględniające cztery główne czynniki: wielkość guza, stopień kliniczny III, liczbę przerzutów do węzłów chłonnych oraz wiek, osiągają wysoką skuteczność (AUC odpowiednio 0,97 i 0,96)
  • Zaawansowane modele hybrydowe łączące głębokie uczenie z uczeniem maszynowym (BCR-HDL) wykazują 92% dokładności w przewidywaniu nawrotu w różnych przedziałach czasowych (poniżej 2 lat, między 2-4 lata, powyżej 4 lat)

202122

Warto zauważyć, że modele te mogą stanowić istotne narzędzie wspomagające decyzje kliniczne, pomagając w identyfikacji pacjentów z wysokim ryzykiem nawrotu.23

Znaczenie lokalizacji nawrotu dla rokowania

Badania wykazują, że lokalizacja miejscowego nawrotu ma istotne znaczenie prognostyczne:2425

  • U pacjentek z nawrotem w obrębie ściany klatki piersiowej obserwuje się wyższą częstość przerzutów odległych w porównaniu do pacjentek z nawrotem w miąższu piersi
  • Najważniejszymi czynnikami w przewidywaniu przerzutów odległych po nawrocie miejscowym są:
    • Czas między wykryciem pierwotnego raka piersi a wystąpieniem nawrotu
    • Lokalizacja nawrotu miejscowego (w pozostałym miąższu piersi lub poza nim)
    • Zastosowane leczenie nawrotu (chemioterapia lub jej brak)

Implikacje terapeutyczne na podstawie oceny prognostycznej

Dokładna ocena prognostyczna pacjentów z nawrotowym rakiem piersi ma istotne implikacje terapeutyczne:2627

  • Ryzyko zgonu z powodu raka piersi po nawrocie miejscowym przekracza próg kwalifikacji do chemioterapii adjuwantowej
  • Ryzyko śmiertelności wynoszące około 30% uzasadnia zastosowanie chemioterapii u pacjentów, którzy wcześniej jej nie otrzymali
  • Zapobieganie nawrotom miejscowym poprzez terapie miejscowe zastosowane w momencie diagnozy nie zmniejsza śmiertelności, jednak możliwe, że terapia systemowa zastosowana w momencie wystąpienia nawrotu miejscowego mogłaby być korzystna

28

Nowoczesne narzędzia prognostyczne

Wśród nowoczesnych narzędzi prognostycznych szczególną uwagę zwraca Oncotype DX Recurrence Score (RS) – test dla hormonozależnego wczesnego raka piersi o potwierdzonej wartości predykcyjnej i prognostycznej. Najnowsze badania wskazują, że multimodalne modele oparte na uczeniu maszynowym (np. Orpheus) mogą dokładniej przewidywać ryzyko nawrotu przerzutowego niż sam RS, szczególnie u pacjentek z niskim RS (średni czasozależny AUC 0,75 vs 0,49).2930

Podsumowanie prognostyczne dla nawrotowego raka piersi

Podsumowując, rokowanie w nawrotowym raku piersi zależy od wielu czynników, w tym podtypu nowotworu, czasu do nawrotu, lokalizacji nawrotu oraz zastosowanego leczenia. Najistotniejsze prognostycznie są:313233

  • Status receptora progesteronowego (PR)
  • Wiek w momencie diagnozy (szczególnie niekorzystne rokowanie u pacjentek <40 lat)
  • Czas do wystąpienia nawrotu (krótszy czas wiąże się z gorszym rokowaniem)
  • Lokalizacja nawrotu (miejscowy, regionalny, odległy)
  • Status węzłów chłonnych, wielkość guza i stopień złośliwości

Wyniki leczenia nawrotowego raka piersi są obecnie lepsze niż w przeszłości. Dzięki postępom w leczeniu, wiele osób z nawrotowym rakiem piersi może prowadzić długie i zdrowe życie, pomimo niekorzystnych czynników rokowniczych. Rozwój modeli predykcyjnych i spersonalizowanych strategii terapeutycznych daje nadzieję na dalszą poprawę wyników leczenia w tej grupie pacjentów.34

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 Breast Cancer Recurrence: Rates, Signs & Treatment
    https://my.clevelandclinic.org/health/diseases/8328-breast-cancer-recurrence
    Breast cancer recurrence is when cancer comes back after treatment. Recurrent breast cancer may develop where it started, or spread to nearby lymph nodes or to more distant areas of your body. Healthcare providers may use new or different treatments for recurrent breast cancer. They may also recommend clinical trials. […] Breast cancer recurrence is when you have breast cancer that comes back (recurs) after treatment. Breast cancer can come back months or years after you’ve finished treatment. Healthcare providers can treat recurrent breast cancer, but it can come back again. […] According to the American Cancer Society, inflammatory breast cancer (IBC) and triple-negative breast cancer (TNBC) are more likely to come back than other breast cancer types and subtypes. […] Its relatively uncommon, but the specific rate of recurrence depends on factors, like your breast cancer stage and treatment.
  • #2 Prognosis and survival for breast cancer | Canadian Cancer Society
    https://cancer.ca/en/cancer-information/cancer-types/breast/prognosis-and-survival
    A prognosis is the doctors best estimate of how cancer will affect you and how it will respond to treatment. Survival is the percentage of people with a disease who are alive at some point in time after their diagnosis. Prognosis and survival depend on many factors. […] Doctors use different prognostic and predictive factors for newly diagnosed and recurrent breast cancers. […] The longer the period of time before breast cancer comes back, the better the prognosis. If breast cancer comes back more than 5 years after diagnosis, the outcome is usually better than when it recurs less than 2 years after diagnosis. […] A local recurrence after lumpectomy and radiation therapy has a more favourable prognosis than cancer that comes back in other organs (called distant recurrence, or distant metastasis). […] A regional recurrence has a less favourable prognosis than a local recurrence and needs to be treated right away to stop cancer from spreading further. […] Breast cancer that comes back in these areas has a far worse prognosis than a local or regional recurrence.
  • #3 Prognosis after Local Recurrence in Patients with Early-Stage Breast Cancer Treated without Chemotherapy
    https://pmc.ncbi.nlm.nih.gov/articles/PMC10136458/
    Background: Many women with early-stage breast cancer are predicted to be at sufficiently low risk for recurrence that they may forego chemotherapy. Nevertheless, some low-risk women will experience a local recurrence, and for them the risk of death increases significantly thereafter. […] The ten-year breast cancer survival post local recurrence was 71% and the 15-year survival was 65%. In a multivariate analysis, it was found that factors that were significantly associated with death after local recurrence were (1) PR-negative status, (2) young age at diagnosis (40 years) and (3) time to local recurrence less than 2 years. […] The risk of breast cancer death after a local recurrence in unselected patients exceeds the threshold for the delivery of adjuvant chemotherapy. In the present study, the mortality risk of 30% appears to justify the use of chemotherapy in chemotherapy-nave patients at the time of local recurrence, but to our knowledge few patients are referred to the medical oncologist at this time point.
  • #4 Prognosis after Local Recurrence in Patients with Early-Stage Breast Cancer Treated without Chemotherapy
    https://www.mdpi.com/1718-7729/30/4/290?type=check_update&version=1
    Prognosis after Local Recurrence in Patients with Early-Stage Breast Cancer Treated without Chemotherapy: Background: Many women with early-stage breast cancer are predicted to be at sufficiently low risk for recurrence that they may forego chemotherapy. Nevertheless, some low-risk women will experience a local recurrence, and for them the risk of death increases significantly thereafter. […] The ten-year breast cancer survival post local recurrence was 71% and the 15-year survival was 65%. In a multivariate analysis, it was found that factors that were significantly associated with death after local recurrence were (1) PR-negative status, (2) young age at diagnosis (<40 years) and (3) time to local recurrence less than 2 years. [...] The risk of breast cancer death after a local recurrence in unselected patients exceeds the threshold for the delivery of adjuvant chemotherapy. In the present study, the mortality risk of 30% appears to justify the use of chemotherapy in chemotherapy-naïve patients (i.e., for those who did not reach the threshold for treatment at diagnosis) at the time of local recurrence.
  • #5 Prognosis and survival for breast cancer | Canadian Cancer Society
    https://cancer.ca/en/cancer-information/cancer-types/breast/prognosis-and-survival
    A prognosis is the doctors best estimate of how cancer will affect you and how it will respond to treatment. Survival is the percentage of people with a disease who are alive at some point in time after their diagnosis. Prognosis and survival depend on many factors. […] Doctors use different prognostic and predictive factors for newly diagnosed and recurrent breast cancers. […] The longer the period of time before breast cancer comes back, the better the prognosis. If breast cancer comes back more than 5 years after diagnosis, the outcome is usually better than when it recurs less than 2 years after diagnosis. […] A local recurrence after lumpectomy and radiation therapy has a more favourable prognosis than cancer that comes back in other organs (called distant recurrence, or distant metastasis). […] A regional recurrence has a less favourable prognosis than a local recurrence and needs to be treated right away to stop cancer from spreading further. […] Breast cancer that comes back in these areas has a far worse prognosis than a local or regional recurrence.
  • #6 Breast Cancer Recurrence: Rates, Signs & Treatment
    https://my.clevelandclinic.org/health/diseases/8328-breast-cancer-recurrence
    In general, your chances of being alive five years after diagnosis are: 99% for localized breast cancer. 86% for regional breast cancer. 27% for distant (metastatic) breast cancer. […] It’s important to remember most cancer survival rates are estimates based on the experiences of large groups of people with the same condition.
  • #7 Prognosis after Local Recurrence in Patients with Early-Stage Breast Cancer Treated without Chemotherapy
    https://pmc.ncbi.nlm.nih.gov/articles/PMC10136458/
    Background: Many women with early-stage breast cancer are predicted to be at sufficiently low risk for recurrence that they may forego chemotherapy. Nevertheless, some low-risk women will experience a local recurrence, and for them the risk of death increases significantly thereafter. […] The ten-year breast cancer survival post local recurrence was 71% and the 15-year survival was 65%. In a multivariate analysis, it was found that factors that were significantly associated with death after local recurrence were (1) PR-negative status, (2) young age at diagnosis (40 years) and (3) time to local recurrence less than 2 years. […] The risk of breast cancer death after a local recurrence in unselected patients exceeds the threshold for the delivery of adjuvant chemotherapy. In the present study, the mortality risk of 30% appears to justify the use of chemotherapy in chemotherapy-nave patients at the time of local recurrence, but to our knowledge few patients are referred to the medical oncologist at this time point.
  • #8 Prognosis after Local Recurrence in Patients with Early-Stage Breast Cancer Treated without Chemotherapy
    https://www.mdpi.com/1718-7729/30/4/290?type=check_update&version=1
    Prognosis after Local Recurrence in Patients with Early-Stage Breast Cancer Treated without Chemotherapy: Background: Many women with early-stage breast cancer are predicted to be at sufficiently low risk for recurrence that they may forego chemotherapy. Nevertheless, some low-risk women will experience a local recurrence, and for them the risk of death increases significantly thereafter. […] The ten-year breast cancer survival post local recurrence was 71% and the 15-year survival was 65%. In a multivariate analysis, it was found that factors that were significantly associated with death after local recurrence were (1) PR-negative status, (2) young age at diagnosis (<40 years) and (3) time to local recurrence less than 2 years. [...] The risk of breast cancer death after a local recurrence in unselected patients exceeds the threshold for the delivery of adjuvant chemotherapy. In the present study, the mortality risk of 30% appears to justify the use of chemotherapy in chemotherapy-naïve patients (i.e., for those who did not reach the threshold for treatment at diagnosis) at the time of local recurrence.
  • #9 Prognosis after Local Recurrence in Patients with Early-Stage Breast Cancer Treated without Chemotherapy
    https://pmc.ncbi.nlm.nih.gov/articles/PMC10136458/
    The risk of death post local recurrence in the current study ranged from 15% to 60% depending on the age of diagnosis, PR status of primary and time to local recurrence. […] The risk of death was also reduced in patients who developed a local recurrence two or more years after primary tumour diagnosis, compared to those with earlier recurrences (15-year breast cancer mortality 40% vs. 55%). […] Currently, local control with surgery or radiotherapy is the mainstay of treatment for an isolated local or locoregional recurrence. […] It is hoped that other prospective studies will be conducted on similar cohorts in order to define with accuracy the impact of chemotherapy on survival for chemo-nave women with local recurrence.
  • #10 Prognosis after Local Recurrence in Patients with Early-Stage Breast Cancer Treated without Chemotherapy
    https://www.mdpi.com/1718-7729/30/4/290?type=check_update&version=1
    The risk of death post local recurrence in the current study ranged from 15% to 60% depending on the age of diagnosis, PR status of primary and time to local recurrence. […] The risk of death from breast cancer from the time of diagnosis for a cohort of women with small node-negative breast tumours treated with surgery alone is 10–15%. […] In conclusion, this study has demonstrated that women who experience a local recurrence within a 20-year period after diagnosis of low-risk breast cancer have a long-term risk of subsequent mortality of 15–30% or more. Preventing local recurrence with local therapies given at the time of diagnosis does not reduce mortality, however it is possible that systemic therapy given at the time of local recurrence might be beneficial.
  • #11 Prognosis and survival for breast cancer | Canadian Cancer Society
    https://cancer.ca/en/cancer-information/cancer-types/breast/prognosis-and-survival
    A prognosis is the doctors best estimate of how cancer will affect you and how it will respond to treatment. Survival is the percentage of people with a disease who are alive at some point in time after their diagnosis. Prognosis and survival depend on many factors. […] Doctors use different prognostic and predictive factors for newly diagnosed and recurrent breast cancers. […] The longer the period of time before breast cancer comes back, the better the prognosis. If breast cancer comes back more than 5 years after diagnosis, the outcome is usually better than when it recurs less than 2 years after diagnosis. […] A local recurrence after lumpectomy and radiation therapy has a more favourable prognosis than cancer that comes back in other organs (called distant recurrence, or distant metastasis). […] A regional recurrence has a less favourable prognosis than a local recurrence and needs to be treated right away to stop cancer from spreading further. […] Breast cancer that comes back in these areas has a far worse prognosis than a local or regional recurrence.
  • #12 Prognosis after Local Recurrence in Patients with Early-Stage Breast Cancer Treated without Chemotherapy
    https://pmc.ncbi.nlm.nih.gov/articles/PMC10136458/
    The risk of death post local recurrence in the current study ranged from 15% to 60% depending on the age of diagnosis, PR status of primary and time to local recurrence. […] The risk of death was also reduced in patients who developed a local recurrence two or more years after primary tumour diagnosis, compared to those with earlier recurrences (15-year breast cancer mortality 40% vs. 55%). […] Currently, local control with surgery or radiotherapy is the mainstay of treatment for an isolated local or locoregional recurrence. […] It is hoped that other prospective studies will be conducted on similar cohorts in order to define with accuracy the impact of chemotherapy on survival for chemo-nave women with local recurrence.
  • #13 Late Breast Cancer Recurrence Less Aggressive and Associated
    https://www.esmo.org/oncology-news/late-breast-cancer-recurrence-less-aggressive-and-associated-with-better-prognosis-compared-to-early-recurrence
    In a first large population-based cohort study to investigate the impact of late breast cancer recurrence on mortality, to evaluate prognostic factors, and to compare survival after late recurrence with survival after early recurrence, women who developed late recurrence had better prognosis compared with those with early recurrence. […] The authors concluded that patients with late recurrence had more favourable prognosis than patients with early recurrence. […] As late breast cancer recurrence appears to be less aggressive and is associated with better prognosis compared with early recurrence, this may provide some reassurance to patients who develop late breast cancer recurrence and may affect quality of life after a late recurrence.
  • #14 Breast cancer recurrence rates: Types and outlook
    https://www.medicalnewstoday.com/articles/breast-cancer-types-recurrence-rates
    The risk of breast cancer recurrence varies depending on the type of breast cancer, the stage of the cancer at diagnosis, and the persons age and health. Inflammatory breast cancer and triple-negative breast cancer have the highest recurrence rates. […] After treatment, some people may experience breast cancer recurrence, which is the return of cancer cells in the breast or nearby areas. […] All types of breast cancer can recur, but aggressive subtypes, such as inflammatory breast cancer (IBC) and triple-negative breast cancer (TNBC), are more likely to return. […] IBC has a 50% chance of recurring in the same area of the breast it was initially. […] TNBC is another aggressive subtype of breast cancer with a higher likelihood of recurrence than other subtypes. […] The risk of recurrence is higher for some subtypes of breast cancer than for others. For example, the risk of recurrence is higher for TNBC than for cancers that are hormone receptor-positive (HR+), HER2-positive, or both HR+ and HER2-positive.
  • #15 Breast cancer recurrence rates: Types and outlook
    https://www.medicalnewstoday.com/articles/breast-cancer-types-recurrence-rates
    The risk of recurrence is higher for people with advanced breast cancer at the time of their initial diagnosis than those with early-stage breast cancer. […] The risk of recurrence is also higher for younger people or people with other health conditions, such as a heart attack, stroke, or diabetes. […] The average time for breast cancer recurrence varies depending on the breast cancer subtype. For example, most local breast cancer recurrence occurs within the first 5 years after diagnosis. […] However, people with TNBC have a higher risk of recurrence, and their cancer may return as early as 2.6 years after diagnosis. […] The outlook for recurrent breast cancer is generally better than it used to be. With advances in treatment, many people with recurrent breast cancer can live long and healthy lives. […] The relative 5-year survival rate for people with recurrent breast cancer is about 25%. […] The risk of recurrence is higher for those with IBC, TNBC, or other risk factors.
  • #16
    https://link.springer.com/article/10.1007/s40291-021-00525-7
    Hormone-receptor positive (HR+) breast cancer (BC) (including the luminal A and the luminal B subtypes) is the most common type of tumor in women diagnosed with early-stage BC (EBC). […] A high proportion of tumor-infiltrating lymphocytes (TILs) reflecting a spontaneous and pre-existing immune response to the tumor has been linked to a worse prognosis in HR+ EBC. […] In luminal/HER2-negative tumors, a high proportion of tumor-infiltrating lymphocytes was a negative prognostic factor. […] Despite all these efforts, adjuvant CT is not able to reduce late recurrences in HR+ EBC. […] Therefore, we return to the question of (1) how to identify patients with a high risk of late recurrence, and (2) how to treat them. […] In summary, TME has a peculiar role in HR+ BC which seems to differ from other BC subtypes. In particular, in luminal/HER2-negative tumors, high TIL extent was a negative prognostic factor, and the total number of infiltrating CD8+ cells was not significantly associated with patient outcome. Conversely, high tumor-infiltrating FOXP3+ T cells has been associated with shorter OS, identifying patients with high risk of late-relapse within this subgroup. […] CTLA-4 expression in both tumor cells and TILs was associated with worse DFS and OS in luminal B HER2-negative BC. […] Similarly, PD-L1 expression was associated with poor DFS. […] Several studies suggest that the downregulation of Fas in HR+ EBC is also associated with worse prognosis.
  • #17 Breast Cancer Recurrence: Rates, Signs & Treatment
    https://my.clevelandclinic.org/health/diseases/8328-breast-cancer-recurrence
    Most local recurrences of breast cancer occur within five years of a lumpectomy. You can lower your risk by getting radiation therapy afterward. You have a 3% to 15% chance of breast cancer recurrence within 10 years with this combined treatment. Based on genetic testing, your provider may recommend additional treatments to further reduce your risk. […] Recurrence rates for people who have mastectomies vary: There’s a 6% chance that cancer will recur within five years if healthcare providers didn’t find cancer in your axillary lymph nodes during your original surgery. There’s a 25% chance of cancer recurrence if your axillary lymph nodes are cancerous. This risk drops to 6% if you receive radiation therapy after a mastectomy. […] Breast cancer recurrence happens when treatment doesn’t kill all the cancer cells in your breast. Breast cancer treatments are effective, but breast cancer cells can be tricky: Treatment can shrink breast cancer tumors to the point that tests don’t detect weakened cancer cells. But the cells are still there, and over time, they can return stronger, start to grow and create tumors.
  • #18 Clinical decision support tool for breast cancer recurrence prediction using SHAP value in cooperative game theory
    https://pmc.ncbi.nlm.nih.gov/articles/PMC10835316/
    Recurrence remains the primary cause of death in patients with breast cancer. […] The proposed explainable ensemble learning method shows promising results in predicting breast cancer recurrence, outperforming existing methods with high accuracy and transparency. […] Accurate early prediction of breast cancer recurrence risk is crucial to ease patient tension, enhance quality of life, and guide subsequent treatment decisions in cases of recurrence. […] By utilizing four key factors, namely, tumor size, clinical stage III, number of lymph node metastases, and age, our decision support tool for predicting breast cancer recurrence achieved significant improvements. […] The extra-tree model exhibited an increased area under the receiver operating characteristic curve (AUC) of 0.97, while the Random Forest model demonstrated an improved AUC of 0.96.
  • #19 Machine learning-based models for the prediction of breast cancer recurrence risk | BMC Medical Informatics and Decision Making | Full Text
    https://bmcmedinformdecismak.biomedcentral.com/articles/10.1186/s12911-023-02377-z
    Breast cancer is the most common malignancy diagnosed in women worldwide. The prevalence and incidence of breast cancer is increasing every year; therefore, early diagnosis along with suitable relapse detection is an important strategy for prognosis improvement. This study aimed to compare different machine algorithms to select the best model for predicting breast cancer recurrence. […] International studies suggest that approximately 30% of women will develop recurrence after the primary treatment for BC. Patients with HR+breast cancer are at risk of recurrent disease even multiple decades after primary diagnosis. […] Hence, the development of models to predict BC recurrence is important to aid in diagnosis and monitoring. […] Our study is the first to use the SHAP method to improve the interpretability of clinicians to predict the recurrence model of breast cancer based on the AdaBoost algorithm. The AdaBoost algorithm offers a clinical decision support model and successfully identifies the recurrence of breast cancer.
  • #20 Machine learning-based models for the prediction of breast cancer recurrence risk | BMC Medical Informatics and Decision Making | Full Text
    https://bmcmedinformdecismak.biomedcentral.com/articles/10.1186/s12911-023-02377-z
    The prediction performances of these eleven ML models were compared, and the most accurate prediction model was chosen. The model obtained by AdaBoost had the best discrimination (AUC=0.987). […] The AdaBoost algorithm was adopted in the establishment of the prediction model. […] The top 4 features [carcinoma antigen 125 (CA125), carcinoembryonic antigen (CEA), fibrinogen (Fbg) and tumor diameter] were assessed as the most important variables. […] In this study, an AdaBoost-based model was trained and tested as a decision-making tool, which is expected to predict the recurrence risk of BC. […] With this type of analysis, clinicians can use the model established by the proposed algorithm to identify BC patients with high recurrence risk, and it is expected to improve the risk stratification of patients in clinical practice. […] To our knowledge, we used AdaBoost in combination with SHAP for the first time to predict the recurrence of BC. […] AdaBoost could be a helpful tool for physicians to predict BC recurrence.
  • #21 Clinical decision support tool for breast cancer recurrence prediction using SHAP value in cooperative game theory
    https://pmc.ncbi.nlm.nih.gov/articles/PMC10835316/
    The inclusion of age as a feature significantly improved the performance of the Extra Trees and Random Forest models. […] The AUC for the Extra Trees model increased to 0.97, while that of the Random Forest model improved to 0.96. […] Our findings not only demonstrate the predictive power of the four features but also provide transparency and interpretability in the decision-making process.
  • #22
    https://link.springer.com/article/10.1007/s42452-025-06512-5
    Breast cancer and its recurrence are significant health concerns, emphasizing the critical importance of early detection and personalized treatment strategies for improved outcomes. […] The BCR-HDL frameworks unique contributions include its ability to predict not only diagnostic outcomes but also prognostic and recurrence timing, offering a comprehensive solution for breast cancer management. […] Moreover, the Hybrid ResNet+SVM and ResNet+RF models demonstrated impressive performance in multi-classifying recurrence into different time intervals, achieving 92% accuracy in predicting recurrence within 2 years, between 2 to 4 years, and beyond 4 years. […] The framework demonstrates impressive accuracy (92%) in multi-classifying cancer recurrence within different time intervals. […] The proposed Hybrid deep learning models provide a fusion of Deep Learning (DL) models like Multi-Layer Perceptron (MLP), Visual Geometry Group (VGG), ResNet, and Xception with machine learning (ML) models like Support Vector Machine (SVM), Decision Trees (DT), Random Forest (RF), and Logistic Regression (LR).
  • #23
    https://link.springer.com/article/10.1007/s42452-025-06512-5
    The proposed framework provides multifaceted predictions, covering diagnostic, prognostic, and critical insight into the time of breast cancer recurrence. […] The results unambiguously demonstrate the superiority of the BCR-HDL framework in terms of diagnostic, prognostic, and time of recurrence predictions compared to existing methods. […] The proposed BCR-HDL framework achieves acceptable accuracy and offers 16 hybrid models showcasing accurate diagnostic, prognostic, and time-of-recurrence prediction capabilities.
  • #24 Machine learning prediction of breast cancer local recurrence localization, and distant metastasis after local recurrences | Scientific Reports
    https://www.nature.com/articles/s41598-025-89339-9
    According to important studies, LR are biologically inhomogeneous diseases; tumors with favorable and unfavorable prognosis could be separated. […] Comparing genetic features of true recurrences and newly formed primaries to the original PT or comparing different features of the recurrences occurring in different localizations could further clarify disease biology differences, but such studies are scarce. […] While, ML models are more and more used in predicting breast cancer recurrence and distant metastases, studies that consider the different localization of local recurrences (LRs) and distinct tumor features of both primary cancers and their corresponding recurrences are still lacking. […] We also predicted the occurrence of DM after LR based on PT and LR features. […] The performance of predicting DM after LR was 0.78.
  • #25 Machine learning prediction of breast cancer local recurrence localization, and distant metastasis after local recurrences | Scientific Reports
    https://www.nature.com/articles/s41598-025-89339-9
    The model used 32 features, and the most important features of the prediction were the elapsed time between the detection of PT and the occurrence of LR, the localization of the LR (in the remaining breast parenchyma or not), and the therapy of the LR (chemotherapy or not). […] Early recurrences are significantly associated with worse DMFS. […] Patients presenting with local recurrence in the chest wall faced a higher incidence of distant metastases compared to the patients presenting with LR in breast parenchyma. […] Our results demonstrate that the localization of LR matters and has a prognostic significance. […] Traditional prognostic factors and ML tools, combined with tumor genetic analyses could establish predictive models that based on high patient number cohort analysis may provide data in the risk assessment of patients with LR.
  • #26 Prognosis after Local Recurrence in Patients with Early-Stage Breast Cancer Treated without Chemotherapy
    https://pmc.ncbi.nlm.nih.gov/articles/PMC10136458/
    Background: Many women with early-stage breast cancer are predicted to be at sufficiently low risk for recurrence that they may forego chemotherapy. Nevertheless, some low-risk women will experience a local recurrence, and for them the risk of death increases significantly thereafter. […] The ten-year breast cancer survival post local recurrence was 71% and the 15-year survival was 65%. In a multivariate analysis, it was found that factors that were significantly associated with death after local recurrence were (1) PR-negative status, (2) young age at diagnosis (40 years) and (3) time to local recurrence less than 2 years. […] The risk of breast cancer death after a local recurrence in unselected patients exceeds the threshold for the delivery of adjuvant chemotherapy. In the present study, the mortality risk of 30% appears to justify the use of chemotherapy in chemotherapy-nave patients at the time of local recurrence, but to our knowledge few patients are referred to the medical oncologist at this time point.
  • #27 Prognosis after Local Recurrence in Patients with Early-Stage Breast Cancer Treated without Chemotherapy
    https://www.mdpi.com/1718-7729/30/4/290?type=check_update&version=1
    Prognosis after Local Recurrence in Patients with Early-Stage Breast Cancer Treated without Chemotherapy: Background: Many women with early-stage breast cancer are predicted to be at sufficiently low risk for recurrence that they may forego chemotherapy. Nevertheless, some low-risk women will experience a local recurrence, and for them the risk of death increases significantly thereafter. […] The ten-year breast cancer survival post local recurrence was 71% and the 15-year survival was 65%. In a multivariate analysis, it was found that factors that were significantly associated with death after local recurrence were (1) PR-negative status, (2) young age at diagnosis (<40 years) and (3) time to local recurrence less than 2 years. [...] The risk of breast cancer death after a local recurrence in unselected patients exceeds the threshold for the delivery of adjuvant chemotherapy. In the present study, the mortality risk of 30% appears to justify the use of chemotherapy in chemotherapy-naïve patients (i.e., for those who did not reach the threshold for treatment at diagnosis) at the time of local recurrence.
  • #28 Prognosis after Local Recurrence in Patients with Early-Stage Breast Cancer Treated without Chemotherapy
    https://www.mdpi.com/1718-7729/30/4/290?type=check_update&version=1
    The risk of death post local recurrence in the current study ranged from 15% to 60% depending on the age of diagnosis, PR status of primary and time to local recurrence. […] The risk of death from breast cancer from the time of diagnosis for a cohort of women with small node-negative breast tumours treated with surgery alone is 10–15%. […] In conclusion, this study has demonstrated that women who experience a local recurrence within a 20-year period after diagnosis of low-risk breast cancer have a long-term risk of subsequent mortality of 15–30% or more. Preventing local recurrence with local therapies given at the time of diagnosis does not reduce mortality, however it is possible that systemic therapy given at the time of local recurrence might be beneficial.
  • #29 Multimodal histopathologic models stratify hormone receptor-positive early breast cancer | Nature Communications
    https://www.nature.com/articles/s41467-025-57283-x
    The Oncotype DX Recurrence Score (RS) is an assay for hormone receptor-positive early breast cancer with extensively validated predictive and prognostic value. […] Furthermore, in patients with RS25, Orpheus ascertains risk of metastatic recurrence more accurately than the RS itself (0.75 vs 0.49 mean time-dependent AUC). […] A patient is considered high-risk with a molecular RS25, following TAILORx. […] This work advances a multimodal machine learning paradigm in precision oncology, applies it to accurately infer the ODX RS from routine histopathology images, and outperforms the ODX RS in identifying the risk of metastatic recurrence in patients with low ODX RS. […] This study has the potential to extend access to the established and exploratory applications of the well-validated Recurrence Score and to refine sub-stratification for patients treated using the current standard paradigm.
  • #30 Multimodal histopathologic models stratify hormone receptor-positive early breast cancer | Nature Communications
    https://www.nature.com/articles/s41467-025-57283-x
    Orpheus accurately identifies patients with high-risk diseases, as defined by TAILORx, with a high degree of confidence. […] This approach could streamline treatment decisions and reduce the need for additional testing, ultimately improving patient care and resource allocation. […] Furthermore, for patients who are treated per TAILORx with adjuvant chemoendocrine or endocrine therapy based on ODX RS results, Orpheus identifies distant metastatic recurrences more accurately than ODX RS itself in the test set. […] Taken together, this study advances an improved platform to approximate the ODX RS from routine histopathologic WSIs, outperforming a leading existing method in the identification of high-risk disease and critically identifying metastatic recurrences for cases with low ODX RS values more accurately than the ODX RS itself.
  • #31 Prognosis after Local Recurrence in Patients with Early-Stage Breast Cancer Treated without Chemotherapy
    https://pmc.ncbi.nlm.nih.gov/articles/PMC10136458/
    The risk of death post local recurrence in the current study ranged from 15% to 60% depending on the age of diagnosis, PR status of primary and time to local recurrence. […] The risk of death was also reduced in patients who developed a local recurrence two or more years after primary tumour diagnosis, compared to those with earlier recurrences (15-year breast cancer mortality 40% vs. 55%). […] Currently, local control with surgery or radiotherapy is the mainstay of treatment for an isolated local or locoregional recurrence. […] It is hoped that other prospective studies will be conducted on similar cohorts in order to define with accuracy the impact of chemotherapy on survival for chemo-nave women with local recurrence.
  • #32 Prognosis after Local Recurrence in Patients with Early-Stage Breast Cancer Treated without Chemotherapy
    https://www.mdpi.com/1718-7729/30/4/290?type=check_update&version=1
    The risk of death post local recurrence in the current study ranged from 15% to 60% depending on the age of diagnosis, PR status of primary and time to local recurrence. […] The risk of death from breast cancer from the time of diagnosis for a cohort of women with small node-negative breast tumours treated with surgery alone is 10–15%. […] In conclusion, this study has demonstrated that women who experience a local recurrence within a 20-year period after diagnosis of low-risk breast cancer have a long-term risk of subsequent mortality of 15–30% or more. Preventing local recurrence with local therapies given at the time of diagnosis does not reduce mortality, however it is possible that systemic therapy given at the time of local recurrence might be beneficial.
  • #33 Prognostic models for breast cancer: a systematic review | BMC Cancer | Full Text
    https://bmccancer.biomedcentral.com/articles/10.1186/s12885-019-5442-6
    The most commonly used prognostic factors in the models were nodal status, tumour size, and tumour grade, followed by age at diagnosis and ER status, as reported in other reviews. […] The NPI was one of the simplest and oldest models, and included only nodal status, tumour size, and tumour grade. […] The performance of a particular model may vary across different populations. […] Most studies in our review showed that models were less accurate in patients aged under 40years or over 65years, although some studies showed opposite results. […] We reviewed the development and/or validation of 58 models predicting mortality and/or recurrence for female breast cancer. These models varied in terms of methods of development and/or validation, predictors, outcomes, and patients included. Most models have been developed in Europe, Asia, and North America. We found that models performed well in internal validation cohorts, but the results were unpredictable in external validation cohorts, especially in young and elderly patients, and in high risk patients. NPI is an exception, which performed well in most independent populations. Therefore, models should be validated before being applied in another population.
  • #34 Breast cancer recurrence rates: Types and outlook
    https://www.medicalnewstoday.com/articles/breast-cancer-types-recurrence-rates
    The risk of recurrence is higher for people with advanced breast cancer at the time of their initial diagnosis than those with early-stage breast cancer. […] The risk of recurrence is also higher for younger people or people with other health conditions, such as a heart attack, stroke, or diabetes. […] The average time for breast cancer recurrence varies depending on the breast cancer subtype. For example, most local breast cancer recurrence occurs within the first 5 years after diagnosis. […] However, people with TNBC have a higher risk of recurrence, and their cancer may return as early as 2.6 years after diagnosis. […] The outlook for recurrent breast cancer is generally better than it used to be. With advances in treatment, many people with recurrent breast cancer can live long and healthy lives. […] The relative 5-year survival rate for people with recurrent breast cancer is about 25%. […] The risk of recurrence is higher for those with IBC, TNBC, or other risk factors.