Individual Risk Of Recurrence Research Articles

Abstract PO4-07-05: Clinical evaluation of image-based risk profiling in breast cancer histopathology and comparison to an established gene expression assay

Abstract Background: Among oestrogen receptor (ER)-positive and human epidermal growth factor receptor 2 (HER2)-negative early breast cancer, a significant proportion of patients are categorised as intermediate risk, based on classic clinico-pathological variables, thus providing limited information to guide adjuvant chemotherapy decisions. Prognostic risk profiling is an integrated part of modern breast cancer diagnostics to provide additional risk information for this patient group. Among the established prognostic assays based on gene expression, the Prosigna assay is widely used and provides an individual risk of recurrence (ROR) score and identifies intrinsic subtypes with associated survival outcomes. Pioneering artificial intelligence-based precision diagnostics, Stratipath Breast, is a deep learning-based image analysis tool that utilises digitised histopathological whole slide images to stratify intermediate risk patients in terms of risk of recurrence. Materials and methods: The study included 234 invasive breast tumours from patients with early ER-positive HER2-negative breast cancer, clinically assessed as intermediate risk tumours and eligible for chemotherapy. All tumours had therefore previously been analysed by the Prosigna assay in clinical routine at point of diagnosis between 2020 and 2022 at the Karolinska University Hospital and Södersjukhuset, Stockholm, Sweden. Clinicopathological data including Prosigna results (ROR score, risk group and intrinsic subtype) were extracted from medical records, along with the corresponding archived haematoxylin and eosin (HE)-stained formalin-fixed paraffin-embedded tissue slides. The HE slides were subsequently digitised and analysed by the Stratipath Breast tool. The agreement between the two tests for risk stratification was evaluated in this real-world breast cancer case series. Results: The Prosigna assay classified 76 (32.5%), 110 (47.0%) and 48 (20.5%) tumours as low, intermediate and high risk, respectively. The Stratipath Breast analysis identified 116 (49.6%) tumours as low risk and 118 (50.4%) as high risk. Among Prosigna intermediate risk tumours, 52 (47.3%) were stratified as low risk and 58 (52.7%) as high risk by Stratipath Breast. The overall agreement between the two tests for low risk and high risk groups was 71.0%, with a Cohen’s linear kappa of 0.42. Twelve of the 48 Prosigna high risk cases were classified as Stratipath low risk. ROR scores were higher in the Stratipath high risk group compared to the low risk group (p < 0.001), across all cases as well as in the Prosigna intermediate group. Among the 176 histological grade (NHG) 2 tumours, 97 (55.1%) and 79 (44.9%) were stratified as Stratipath low risk and high risk, respectively, whereas 66 (37.5%), 83 (47.2%) and 27 (15.3%) were stratified as Prosigna low, intermediate and high risk, respectively. The majority of NHG1 (10 of 12) and NHG3 (37 of 46) tumours were stratified as Stratipath low risk and high risk, respectively. For both risk profiling tests, NHG and Ki67 proliferation index differed between risk groups. Conclusions: In this study of clinically assessed intermediate risk ER-positive HER2-negative breast cancer, we observed a moderate agreement between Prosigna and Stratipath Breast for low risk and high risk groups. In addition, image-based risk profiling stratified more of the NHG2 tumours as high risk. Citation Format: Stephanie Robertson, Yinxi Wang, Wenwen Sun, Emelie Karlsson, Sandy Kang Lövgren, Mattias Rantalainen, Johan Hartman. Clinical evaluation of image-based risk profiling in breast cancer histopathology and comparison to an established gene expression assay [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO4-07-05.

Abstract PO4-17-01: Patient Perception and Decision-Making in HER2+ Early Breast Cancer Management: Insights from the ASKHER2 European Survey

Abstract Background Breast cancer remains the most prevalent cancer in women globally, with Human Epidermal Growth Factor Receptor 2 positivity (HER2+) observed in 15-30% of initial breast cancer cases. Adjuvant treatment for HER2+ early breast cancer has notably reduced mortality and recurrence rates. However, the heterogeneity of the disease and in conveying risk information by healthcare providers (HCPs) leaves many women uncertain about their individual risk of recurrence and potential treatment (tx) options. Evidence shows that fear of recurrence, uncertainty about prognosis, and inadequate risk/benefit information can affect patients' decisions during their tx phase. Therefore, it is important to better understand the perceptions, attitudes, and behaviors regarding the risk of recurrence in women with HER2+ early breast cancer. Methods A protocol-driven, direct-to-patient online survey (30 questions total) was administered in France, Germany, Italy, Portugal, Spain, and Sweden via patient advocacy groups and panels. Women aged 18 years and above with either early-stage (eBC) (stages I-III) or metastatic (mBC) (stage IV) as the result of recurrence from an initial diagnosis of locally advanced HER2+ breast cancer were eligible to participate. The implementation of soft quotas ensured a representative sample size. This abstract presents the results of the survey. Results A total of 622 participants completed the survey between July 2022 and February 2023. Majority of participants (70%) were between 40 and 65 years of age. Almost 85% had eBC (N=527), 62% had been diagnosed with HER2+ eBC for ≥ 2 years, and 68% were undergoing breast cancer tx at the time of the survey. The main worries and concerns that were reported by participants when asked about their tx plan were risk of recurrence (27%), fear of dying (22%) and risk of tx failure (14%). Among eBC participants, 40% perceived their personal risk of recurrence to be moderate, 18% perceived it to be high, while 21% did not know their personal risk. Most eBC participants (72%) preferred short and simple explanations from the medical team about the risk of cancer recurrence, while 4% preferred not to receive this information. Overall, 30% of participants said they had fully discussed the risk of recurrence with their doctor, while 20% had no discussion. Almost all participants (97%) wanted to be involved in their tx decision, 49% completely and 48% partially. To reduce this risk of recurrence, participants with eBC were willing to change their diet habits (77%), exercise more frequently (74%), take additional tx (65%) or undergo surgery (60%). Most participants (69%) were willing to take additional tx even if it would reduce their risk of recurrence by less than 50%. Participants were most willing to tolerate fatigue (53%), followed by hot flashes (51%) and joint pain (44%), as the most acceptable side effects if they had to take additional treatments with the potential benefit of reducing risk of recurrence. Conclusion The multinational large direct-to-patient ASKHER2 survey reflects participants’ experience and highlights concerns of patients with HER2+ breast cancer, notably on their recurrence risk. To mitigate this risk, patients exhibited a willingness to modify lifestyle habits and consider additional tx. A fraction of participants considered they had thoroughly discussed these risks with their HCPs, while the vast majority desired active involvement in their treatment decisions. These results underscore the ongoing need for HCPs to discuss the risk of recurrence in a clear way, addressing the full potential of treatment options in eBC and mBC, to enable patients to participate in this patient-centered approach of the decision-making process. Citation Format: Matteo Lambertini, Christian Jackisch, Olivier Trédan, Maria Vidal, Mário Fontes-Sousa, Antonios Valachis, Rosanna D’Antona, Marcelo Ruz, Eugenia Krone, Miriam Brice, Erwan Berjonneau, Soraia Matos, Olivia Dialla, Laure Guéroult-Accolas. Patient Perception and Decision-Making in HER2+ Early Breast Cancer Management: Insights from the ASKHER2 European Survey [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO4-17-01.

PRERISK: A Personalized, Artificial Intelligence-Based and Statistically-Based Stroke Recurrence Predictor for Recurrent Stroke.

Predicting stroke recurrence for individual patients is difficult, but individualized prediction may improve stroke survivors' engagement in self-care. We developed PRERISK: a statistical and machine learning classifier to predict individual risk of stroke recurrence. We analyzed clinical and socioeconomic data from a prospectively collected public health care-based data set of 41 975 patients admitted with stroke diagnosis in 88 public health centers over 6 years (2014-2020) in Catalonia-Spain. A new stroke diagnosis at least 24 hours after the index event was considered as a recurrent stroke, which was considered as our outcome of interest. We trained several supervised machine learning models to provide individualized risk over time and compared them with a Cox regression model. Models were trained to predict early, late, and long-term recurrence risk, within 90, 91 to 365, and >365 days, respectively. C statistics and area under the receiver operating characteristic curve were used to assess the accuracy of the models. Overall, 16.21% (5932 of 36 114) of patients had stroke recurrence during a median follow-up of 2.69 years. The most powerful predictors of stroke recurrence were time from previous stroke, Barthel Index, atrial fibrillation, dyslipidemia, age, diabetes, and sex, which were used to create a simplified model with similar performance, together with modifiable vascular risk factors (glycemia, body mass index, high blood pressure, cholesterol, tobacco dependence, and alcohol abuse). The areas under the receiver operating characteristic curve were 0.76 (95% CI, 0.74-0.77), 0.60 (95% CI, 0.58-0.61), and 0.71 (95% CI, 0.69-0.72) for early, late, and long-term recurrence risk, respectively. The areas under the receiver operating characteristic curve of the Cox risk class probability were 0.73 (95% CI, 0.72-0.75), 0.59 (95% CI, 0.57-0.61), and 0.67 (95% CI, 0.66-0.70); machine learning approaches (random forest and AdaBoost) showed statistically significant improvement (P<0.05) over the Cox model for the 3 recurrence time periods. Stroke recurrence curves can be simulated for each patient under different degrees of control of modifiable factors. PRERISK is a novel approach that provides a personalized and fairly accurate risk prediction of stroke recurrence over time. The model has the potential to incorporate dynamic control of risk factors.

Importance about use of high-throughput sequencing in pediatric: case report of a patient with Fanconi-Bickel syndrome

BackgroundFanconi-Bickel syndrome is characterized by hepatorenal disease caused by anomalous glycogen storage. It occurs due to variants in the SLC2A2 gene. We present a male patient of 2 years 7 months old, with failure to thrive, hepatomegaly, metabolic acidosis, hypophosphatemia, hypokalemia, hyperlactatemia.ResultsExome sequencing identified the homozygous pathogenic variant NM_000340.2(SLC2A2):c.1093 C > T (p.Arg365Ter), related with Fanconi-Bickel syndrome. He received treatment with bicarbonate, amlodipine, sodium citrate and citric acid solution, enalapril, alendronate and zolendronate, and nutritional management with uncooked cornstarch, resulting in an improvement of one standard deviation in weight and height.ConclusionsThe importance of knowing the etiology in rare genetic disease is essential, not only to determine individual and familial recurrence risk, but also to establish the treatment and prognosis; in this sense, access to a new genomic technology in low- and middle-income countries is essential to shorten the diagnostic odyssey.

Utilization of Patient-Specific Characteristics and Competing Risks to Tailor the Duration of Surveillance Imaging After Surgery for Renal Cell Carcinoma

Purpose: The appropriate duration of follow-up after surgical resection of renal cell carcinoma (RCC) remains incompletely defined. To better inform on this time line, we investigate when an individual's risk of RCC recurrence becomes less significant than their risk of non-RCC death. Materials and Methods: We identified 1672 patients who underwent surgery for M0 RCC between 1999 and 2018. Patients were stratified by pathologic stage, histology, age, and Eastern Cooperative Oncology Group (ECOG) performance status. Cumulative incidence functions were estimated for RCC recurrence and non-RCC death using Fine and Gray models. Follow-up durations were estimated as the time point at which the cumulative incidence of non-RCC death exceeded that of RCC recurrence. Results: At a median follow-up of 2.1 years (IQR 0.6-5.1 years), a total of 272 recurrences (16.3%) and 234 non-RCC deaths (14.0%) occurred. The fitted model showed significant associations of stage with RCC recurrence and of age and ECOG with non-RCC death. For 50-year-old patients with pT1aN0-x clear cell and ECOG 0, the incidence of non-RCC death exceeded that of recurrence after 4.4 years. However, if such patients had an ECOG status of 1 or 2 to 4, the incidence of non-RCC death exceeded that of recurrence at 30 days, suggesting that routine oncologic surveillance may not be necessary. Alternatively, regardless of ECOG status, the incidence of non-RCC death failed to exceed that of recurrence for &gt;13.9 years in all patients age 50 with &gt; pT3aN0-x clear cell thereby suggesting longer surveillance than currently recommended. Conclusion: Modeling competing risks of RCC recurrence and non-RCC death provide patient-specific estimates when follow-up may be reasonably discontinued.

ESR Essentials: Imaging in colorectal cancer-practice recommendations by ESGAR.

Colorectal cancer (CRC) is a significant global health concern. Diagnostic imaging, using different modalities, has a pivotal role in CRC, from early detection (i.e., screening) to follow-up. The role of imaging in CRC screening depends on each country's approach: if an organized screening program is in place, the role of CT colonography (CTC) is limited to the study of either individuals with a positive stool test unwilling/unable to undergo colonoscopy (CC) or in patients with incomplete CC. Although CC is the most common modality to diagnose CRC, CRC can be also incidentally detected during a routine abdominal imaging examination or at the emergency room in patients presenting with intestinal occlusion/subocclusion or perforation. Staging is a crucial aspect of CRC management, guiding treatment decisions and providing valuable prognostic information. An accurate local staging is mandatory in both rectal and colon cancer to drive the appropriate therapeutic workflow. Important limitations of US, CT, and MR in N-staging can be partially solved by FDG PET/CT. Distant staging is usually managed by CT, with MR and FDG PET/CT which can be used as problem-solving techniques. Follow-up is performed according to the general recommendations of the oncological societies. CLINICAL RELEVANCE STATEMENT: It is essential to summarize each phase of colorectal cancer workup, differentiating the management for colon and rectal cancer supported by the main international guidelines and literature data, with the aim to inform the community on the best practice imaging in colorectal cancer. KEY POINTS: • Colorectal cancer is a prevalent disease that lends itself to imaging at each stage of detection and management. • Various imaging modalities can be used as adjuncts to, or in place of, direct visualization methods of screening and are necessary for evaluating metastatic disease. • Reevaluation of follow-up strategies should be considered depending on patients' individual risk of recurrence.

A recurrence-predictive model based on eight genes and tumor mutational burden/microsatellite instability status in Stage II/III colorectal cancer.

Although adjuvant chemotherapy (ACT) is widely used to treat patients with Stage II/III colorectal cancer (CRC), administering ACT to specific patients remains a challenge. The decision to ACT requires an accurate assessment of recurrence risk and absolute treatment benefit. However, the traditional TNM staging system does not accurately assess a patient's individual risk of recurrence. To identify recurrence risk-related genetic factors for Stage II/III CRC patients after radical surgery, we conducted an analysis of whole-exome sequencing of 47 patients with Stage II/III CRC who underwent radical surgery at five institutions. Patients were grouped into non-recurrence group (NR, n = 24, recurrence-free survival [RFS] > 5 years) and recurrence group (R, n = 23, RFS <2 years). The TCGA-COAD/READ cohort was employed as the validation dataset. A recurrence-predictive model (G8plus score) based on eight gene (CUL9, PCDHA12, HECTD3, DCX, SMARCA2, FAM193A, AATK, and SORCS2) mutations and tumor mutation burden/microsatellite instability (TMB/MSI) status was constructed, with 97.87% accuracy in our data and 100% negative predictive value in the TCGA-COAD/READ cohort. For the TCGA-COAD/READ cohort, the G8plus-high group had better RFS (HR = 0.22, p = 0.024); the G8plus-high tumors had significantly more infiltrated immune cell types, higher tertiary lymphoid structure signature scores, and higher immunological signature scores. The G8plus score was also a predict biomarker for immunotherapeutic in advanced CRC in the PUCH cohort. In conclusion, the G8plus score is a powerful biomarker for predicting the risk of recurrence in patients with stage II/III CRC. It can be used to stratify patients who benefit from ACT and immunotherapy.

Personalized surveillance and aftercare for non-metastasized breast cancer: the NABOR study protocol of a multiple interrupted time series design

BackgroundFollow-up of curatively treated primary breast cancer patients consists of surveillance and aftercare and is currently mostly the same for all patients. A more personalized approach, based on patients’ individual risk of recurrence and personal needs and preferences, may reduce patient burden and reduce (healthcare) costs. The NABOR study will examine the (cost-)effectiveness of personalized surveillance (PSP) and personalized aftercare plans (PAP) on patient-reported cancer worry, self-rated and overall quality of life and (cost-)effectiveness.MethodsA prospective multicenter multiple interrupted time series (MITs) design is being used. In this design, 10 participating hospitals will be observed for a period of eighteen months, while they -stepwise- will transit from care as usual to PSPs and PAPs. The PSP contains decisions on the surveillance trajectory based on individual risks and needs, assessed with the ‘Breast Cancer Surveillance Decision Aid’ including the INFLUENCE prediction tool. The PAP contains decisions on the aftercare trajectory based on individual needs and preferences and available care resources, which decision-making is supported by a patient decision aid. Patients are non-metastasized female primary breast cancer patients (N = 1040) who are curatively treated and start follow-up care. Patient reported outcomes will be measured at five points in time during two years of follow-up care (starting about one year after treatment and every six months thereafter). In addition, data on diagnostics and hospital visits from patients’ Electronical Health Records (EHR) will be gathered. Primary outcomes are patient-reported cancer worry (Cancer Worry Scale) and overall quality of life (as assessed with EQ-VAS score). Secondary outcomes include health care costs and resource use, health-related quality of life (as measured with EQ5D-5L/SF-12/EORTC-QLQ-C30), risk perception, shared decision-making, patient satisfaction, societal participation, and cost-effectiveness. Next, the uptake and appreciation of personalized plans and patients’ experiences of their decision-making process will be evaluated.DiscussionThis study will contribute to insight in the (cost-)effectiveness of personalized follow-up care and contributes to development of uniform evidence-based guidelines, stimulating sustainable implementation of personalized surveillance and aftercare plans.Trial registrationStudy sponsor: ZonMw. Retrospectively registered at ClinicalTrials.gov (2023), ID: NCT05975437.

Machine learning radiomics of magnetic resonance imaging predicts recurrence-free survival after surgery and correlation of LncRNAs in patients with breast cancer: a multicenter cohort study

BackgroundSeveral studies have indicated that magnetic resonance imaging radiomics can predict survival in patients with breast cancer, but the potential biological underpinning remains indistinct. Herein, we aim to develop an interpretable deep-learning-based network for classifying recurrence risk and revealing the potential biological mechanisms.MethodsIn this multicenter study, 1113 nonmetastatic invasive breast cancer patients were included, and were divided into the training cohort (n = 698), the validation cohort (n = 171), and the testing cohort (n = 244). The Radiomic DeepSurv Net (RDeepNet) model was constructed using the Cox proportional hazards deep neural network DeepSurv for predicting individual recurrence risk. RNA-sequencing was performed to explore the association between radiomics and tumor microenvironment. Correlation and variance analyses were conducted to examine changes of radiomics among patients with different therapeutic responses and after neoadjuvant chemotherapy. The association and quantitative relation of radiomics and epigenetic molecular characteristics were further analyzed to reveal the mechanisms of radiomics.ResultsThe RDeepNet model showed a significant association with recurrence-free survival (RFS) (HR 0.03, 95% CI 0.02–0.06, P < 0.001) and achieved AUCs of 0.98, 0.94, and 0.92 for 1-, 2-, and 3-year RFS, respectively. In the validation and testing cohorts, the RDeepNet model could also clarify patients into high- and low-risk groups, and demonstrated AUCs of 0.91 and 0.94 for 3-year RFS, respectively. Radiomic features displayed differential expression between the two risk groups. Furthermore, the generalizability of RDeepNet model was confirmed across different molecular subtypes and patient populations with different therapy regimens (All P < 0.001). The study also identified variations in radiomic features among patients with diverse therapeutic responses and after neoadjuvant chemotherapy. Importantly, a significant correlation between radiomics and long non-coding RNAs (lncRNAs) was discovered. A key lncRNA was found to be noninvasively quantified by a deep learning-based radiomics prediction model with AUCs of 0.79 in the training cohort and 0.77 in the testing cohort.ConclusionsThis study demonstrates that machine learning radiomics of MRI can effectively predict RFS after surgery in patients with breast cancer, and highlights the feasibility of non-invasive quantification of lncRNAs using radiomics, which indicates the potential of radiomics in guiding treatment decisions.

Differentiated thyroid cancer: a focus on post-operative thyroid hormone replacement and thyrotropin suppression therapy.

This review focuses on post-operative thyroid hormone replacement and thyrotropin suppression therapy in patients with differentiated thyroid cancer. A clinical review. Differentiated thyroid cancers (DTC), including papillary and follicular thyroid cancers, have an excellent prognosis and their management leverages a unique set of clinical tools arising from homology to the normal thyroid follicular cell. Surgery is the cornerstone of initial management, and post-operative care often requires thyroid hormone replacement therapy, which may be approached with the intent of physiologic normalization or used pharmacologically to suppress TSH as part of a DTC treatment. Management of DTC and approaches to TSH suppression are tailored to an individual's risk of DTC recurrence and are adjusted to a patient's clinical status and comorbidities over time with the goal of mitigating risk and maximizing benefit.

Recurrence Risk Stratification for Women With FIGO Stage I Uterine Endometrioid Carcinoma Who Underwent Surgical Lymph Node Evaluation.

The aim of this study was to estimate the recurrence risk based on the number of prognostic factors for patients with stage I uterine endometrioid carcinoma (EC) who underwent surgical lymph node evaluation (SLNE) and were managed with observation. We queried our database for women with FIGO-2009 stage I EC who underwent surgical staging including SLNE. Multivariate analysis with stepwise model selection was used to determine independent risk factors for 5-year recurrence-free survival (RFS). Study groups based on risk factors were compared for RFS, disease-specific survival, and overall survival. A total of 706 patients were identified: median age was 60 years (range, 30 to 93y) and median follow-up was 120 months. Median number of examined lymph nodes was 8 (range, 1 to 66). 91% were stage IA, 75% had grade 1 and lymphovascular space invasion was detected in 6%. Independent predictors of 5-year RFS included age 60 years and above ( P =0.038), grade 2 ( P =0.003), and grade 3 ( P <0.001) versus grade 1. Five-year RFS for group 0 (age less than 60y and grade 1) was 98% versus 92% for group 1 (either: age 60y and older or grade 2/3) versus 84% for group 2 (both: age 60y and above and grade 2/3), respectively ( P <0.001). Five-year disease-specific survival was 100% versus 98% versus 95%, ( P =0.012) and 5-year overall survival was 98% versus 90% versus 81%, for groups 0, 1, and 2, respectively ( P <0.001). In patients with stage I EC who received SLNE and no adjuvant therapy, only age 60 years and above and high tumor grade were independent predictors of recurrence and can be used to quantify individualized recurrence risk, whereas lymphovascular space invasion was not an independent prognostic factor in this cohort.

Association of serum cortisol and cortisone levels and risk of recurrence after endocrine treatment in breast cancer

Metabolic reprogramming in breast cancer involves changes in steroid hormone synthesis and metabolism. Alterations in estrogen levels in both breast tissue and blood may influence carcinogenesis, breast cancer growth, and response to therapy. Our aim was to examine whether serum steroid hormone concentrations could predict the risk of recurrence and treatment-related fatigue in patients with breast cancer. This study included 66 postmenopausal patients with estrogen receptor-positive breast cancer who underwent surgery, radiotherapy, and adjuvant endocrine treatment. Serum samples were collected at six different time points [before the start of radiotherapy (as baseline), immediately after radiotherapy, and then 3, 6, 12 months, and 7–12 years after radiotherapy]. Serum concentrations of eight steroid hormones (cortisol, cortisone, 17α-hydroxyprogesterone, 17β-estradiol, estrone, androstenedione, testosterone, and progesterone) were measured using a liquid chromatography–tandem mass spectrometry-based method. Breast cancer recurrence was defined as clinically proven relapse/metastatic breast cancer or breast cancer-related death. Fatigue was assessed with the QLQ-C30 questionnaire. Serum steroid hormone concentrations measured before and immediately after radiotherapy differed between relapse and relapse-free patients [(accuracy 68.1%, p  = 0.02, and 63.2%, p  = 0.03, respectively, partial least squares discriminant analysis (PLS-DA)]. Baseline cortisol levels were lower in patients who relapsed than in those who did not (p < 0.05). The Kaplan–Meier analysis showed that patients with high baseline concentrations of cortisol (≥ median) had a significantly lower risk of breast cancer recurrence than patients with low cortisol levels (<median) (p  = 0.02). During follow-up, there was a decrease in cortisol and cortisone concentrations in relapse-free patients, whereas these steroid hormones increased in patients who relapsed. In addition, steroid hormone concentrations immediately after radiotherapy were associated with treatment-related fatigue (accuracy of 62.7%, p  = 0.03, PLS-DA). However, baseline steroid hormone levels did not predict fatigue at 1 year or at 7–12 years. In conclusion, breast cancer patients with low baseline cortisol levels were more likely to experience recurrence. During follow-up, cortisol and cortisone levels decreased in relapse-free patients but increased in patients with recurrence. Thus, cortisol and cortisone may act as potential biomarkers indicating individual risk of recurrence.

Disease-free survival in operated patients with nmRCC using machine learning.

4539 Background: In patients operated for a non-metastatic renal cell carcinoma (nmRCC), risk evaluation of disease recurrence enables the therapeutic strategy to be adapted after surgery. Usual risk group stratification does not fully exploit the power of machine learning (ML) applied to multimodal data. We developed a ML model capable of calculating the risk of recurrence after surgery for nmRCC patients. Methods: A multicentric cohort of patients undergoing surgery between May 2000 and January 2020 for a nmRCC (pT any, N any, M0) was analyzed from data collected prospectively in the French research network on kidney cancer UroCCR (ClinicalTrials.gov: NCT03293563). Using clinical, biological, histological and radiological features, we developed a signature of patient-specific DFS. Participating medical centers were randomly assigned to training or validation cohorts with a 2:1 ratio of patients. The ML signature managed missing data using multiple imputation based on gradient boosted trees and chained equations. Several ML models were trained in a repeated 5x10-fold cross-validation procedure to optimize the integrated Area Under the ROC Curve (iAUC) between 0.5- and 5-years following surgery. The performance of the selected ML signature was then evaluated on the validation cohort and compared with usual risk scores. Results: 3354 patients were randomly assigned to a training cohort (n=2239 from 10 centers) and a validation cohort (n=1115 from 13 centers). Our risk score achieved an iAUC of 0.81 (0.76, 0.85) on the validation cohort and significantly outperformed the GRANT ( p &lt;0.001), SSIGN ( p =0.03), and UISS ( p &lt;0.001) risk scores. The Leibovich-2018 score was only defined in 51% of the patients, due to incomplete data. Permutation-based feature importance and Shapley values were used to estimate the contribution of each feature. The stratification of patients into four risk groups achieved an iAUC of 0.78 (0.74, 0.83) on the validation cohort. 190 (17%) patients were stratified in the low-risk group, with an actual 5-year DFS higher than 98% and no death observed within this horizon window. 188 (17%) patients were stratified in the high-risk group, with an actual 5-year DFS of 48%. Conclusions: The machine learning model estimating individual disease recurrence risk outperformed the predictive performances of usual risk scores while handling incomplete data in predictors. This could help in identifying patients for whom surveillance could be reduced and those who could be candidates for adjuvant therapies. [Table: see text]

Molecular classification of endometrial carcinoma: Analysis of a multicentre Portuguese cohort.

e17615 Background: Management of endometrial carcinoma (EC) relies on prognostic risk group classification to help to determine the individual risk of recurrence and the need for adjuvant treatment after surgery. A molecular classification with four distinct prognostic EC subtypes based on genomic abnormalities - DNA polymerase epsilon ( POLE) mutated ( POLEmut), mismatch repair deficient (MMRd), p53 abnormal (p53abn) and no specific molecular profile (NSMP) - has emerged, that raises the possibility of a more precise tailoring of adjuvant therapy. This study aimed to describe the clinicopathological and molecular characteristics of an EC Portuguese cohort, assess its potential impact in patient management and evaluate its prognostic value. Methods: Multicentre, retrospective cohort study of 230 patients with EC diagnosed between 2019 and 2022. Sample processing, clinicopathological, treatment and follow-up data was collected. Molecular classification was obtained by p53 and mismatch repair proteins immunohistochemistry, and POLE next-generation sequencing. Results: Overall, 230 patients from two institutions were included. Median age at diagnosis was 68 years. The most frequent histology was endometrioid (n=163; 70.9%) and most were low-grade (n=129, 56.1%).At diagnosis, disease was confined to the uterus in the majority of patients (FIGO stage I/II, n=153, 66.5%). Most had surgery upfront (n=196, 85.2%) and, of those, 120 (52.2%) received adjuvant treatment. 26 (11.3%) had metastatic disease. Median follow-up time was 15.4 months. Regarding molecular subgroups, the majority were classified as NSMP (n=87, 37.8%), followed by p53abn (n=73, 31.7%), MMRd (n=56, 24.3%), and POLEmut (n=14, 6.1%); 11 (4.8%) were multiple-classifier. Integration of these results led to a change in adjuvant treatment in 3 patients. Median disease-specific survival (DSS) was 108 months. Factors that significantly influenced survival included age (p=0.030), histological type (p&lt;0.001), grade (p&lt;0.001) and FIGO stage (p=0.006). Overall, 35 (15.2%) patients developed recurrences. Median recurrence-free survival (RFS) was 46.7 months. Kaplan-Meier survival analysis showed that molecular alterations were significantly associated both with DSS and RFS (p=0.0092 and p=0.0139, respectively). Tumours with p53abn had the worst prognosis, and patients with POLEmut tumours experienced an excellent prognosis. Comparative measures (BIC, C-index, log-likelihood) showed that considering the molecular classification in establishing risk groups for adjuvant treatment had prognostic significance. Conclusions: The molecular classification has prognostic value and should be considered in adjuvant treatment decisions. It allows for a more personalised approach, helps to reduce under and overtreatment, and therefore reduce patient morbidity associated with treatment toxicities, and healthcare related costs.

Use of antiseizure medications after traumatic brain injury

Background: Post-traumatic seizures and epilepsy are major complications that increase the mortality rate among patients with traumatic brain injury (TBI) and hinder functional recovery. It is important to establish prophylaxis and treatment strategies for high-risk patients. The use of antiseizure medications may not only adversely affect the cognitive function following TBI but also may be associated with a worse rehabilitation outcome.Current Concepts: The level of evidence in the current international guidelines related to the prophylaxis and management of post-traumatic seizure is not robust. Furthermore, the use of antiseizure medications after TBI remains unclear, indicating substantial variations in clinical practice.Discussion and Conclusion: Prophylactic antiseizure medications can reduce the risk of early seizures and partially prevent the secondary injury process of TBI; however, they do not seem to inhibit epileptogenesis. Therefore, if the benefits of preventing early seizures outweigh the potential risks associated with antiseizure medication, it is recommended to use them for a short period of about one week after the injury. Then, it is not recommended to continue using them routinely without considering the individual risk of seizure recurrence and potential adverse effects of long-term use. The treatment duration of anticonvulsant in patients with post-traumatic epilepsy should also be determined based on the individual risk of seizure recurrence, and the decision should take into account the opinions of both the patient and the caregiver, while considering not only the potential benefits but also the risks associated with long-term use.

The Future of Breast Cancer Research in the Survivorship Field.

Prevalence of survivors of breast cancer has been steadily increasing in the last 20years. Currently, more than 90% of women diagnosed with early-stage breast cancer are expected to be alive at 5years from diagnosis thanks to early detection and breakthrough innovations in multimodal treatment strategies. Alongside this advancement in clinical outcomes, survivors of breast cancer might experience several specific challenges and present with unique needs. Survivorship trajectories after diagnosis and treatment of breast cancer can be significantly impacted by long-lasting and severe treatment-related side effects, including physical problems, psychological distress, fertility issuesin young women, and impaired social and work reintegration, which add up to patients' individual risk of cancer recurrence and second primary malignancies. Alongside cancer-specific sequelae, survivors still present with general health needs, including management of chronic preexisting or ensuing conditions. Survivorship care should implement high-quality, evidence-based strategies to promptly screen, identify, and address survivors' needs in a comprehensive way and minimize the impact of severe treatment sequelae, preexisting comorbidities, unhealthy lifestyles, and risk of recurrence on quality of life. This narrative review focuses on core areas of survivorship care and discuss the state of the art and future research perspectives in key domains including selected long-term side effects, surveillance for recurrences and second cancers, well-being promotion, and specific survivors' needs.

Prioritizing prognostic-associated subpopulations and individualized recurrence risk signatures from single-cell transcriptomes of colorectal cancer.

Colorectal cancer (CRC) is one of the most common gastrointestinal malignancies. There are few recurrence risk signatures for CRC patients. Single-cell RNA-sequencing (scRNA-seq) provides a high-resolution platform for prognostic signature detection. However, scRNA-seq is not practical in large cohorts due to its high cost and most single-cell experiments lack clinical phenotype information. Few studies have been reported to use external bulk transcriptome with survival time to guide the detection of key cell subtypes in scRNA-seq data. We proposed scRankXMBD, a computational framework to prioritize prognostic-associated cell subpopulations based on within-cell relative expression orderings of gene pairs from single-cell transcriptomes. scRankXMBD achieves higher precision and concordance compared with five existing methods. Moreover, we developed single-cell gene pair signatures to predict recurrence risk for patients individually. Our work facilitates the application of the rank-based method in scRNA-seq data for prognostic biomarker discovery and precision oncology. scRankXMBD is available at https://github.com/xmuyulab/scRank-XMBD. (XMBD:Xiamen Big Data, a biomedical open software initiative in the National Institute for Data Science in Health and Medicine, Xiamen University, China.).

Recurrence of low back pain: A difficult outcome to predict. Development and validation of a multivariable prediction model for recurrence in patients recently recovered from an episode of non-specific low back pain

BackgroundRecurrence of low back pain (LBP) is common. If clinicians could identify an individual's risk of recurrence, this would enhance clinical decision-making and tailored patient care. Objective/designTo develop and validate a simple tool to predict the probability of a recurrence of LBP by 3- or 12-months following recovery. MethodsData utilised for the prediction model development came from a prospective inception cohort study of participants (n = 250) recently recovered from LBP, who had sought care from chiropractic or physiotherapy services. The outcome measure was a recurrence of activity-limiting LBP. Candidate predictor variables (e.g., basic demographics, LBP history, levels of physical activity, etc) collected at baseline were considered for inclusion in a multivariable Cox model. The model's performance was tested in a separate validation dataset of participants (n = 261) involved in a randomised controlled trial investigating exercise for the prevention of LBP recurrences. ResultsThe final model included the number of previous episodes, total sitting time, and level of education. In the development sample, discrimination was acceptable (Harrell's C-statistic = 0.61, 95% CI, 0.59–0.62), but in the validation sample, discrimination was poor (0.56, 95% CI, 0.54–0.58). Calibration of the model in the validation dataset was acceptable at 3 months but was less precise at 12 months. ConclusionThe developed prediction model, which included number of previous episodes, total sitting time, and level of education, did not perform adequately in the validation sample to recommend its use in clinical practice. Predicting recurrence of LBP in clinical practice remains challenging.

Deep Learning Provides a New Magnetic Resonance Imaging-Based Prognostic Biomarker for Recurrence Prediction in High-Grade Serous Ovarian Cancer

This study aims to use a deep learning method to develop a signature extract from preoperative magnetic resonance imaging (MRI) and to evaluate its ability as a non-invasive recurrence risk prognostic marker in patients with advanced high-grade serous ovarian cancer (HGSOC). Our study comprises a total of 185 patients with pathologically confirmed HGSOC. A total of 185 patients were randomly assigned in a 5:3:2 ratio to a training cohort (n = 92), validation cohort 1 (n = 56), and validation cohort 2 (n = 37). We built a new deep learning network from 3839 preoperative MRI images (T2-weighted images and diffusion-weighted images) to extract HGSOC prognostic indicators. Following that, a fusion model including clinical and deep learning features is developed to predict patients' individual recurrence risk and 3-year recurrence likelihood. In the two validation cohorts, the consistency index of the fusion model was higher than both the deep learning model and the clinical feature model (0.752, 0.813 vs. 0.625, 0.600 vs. 0.505, 0.501). Among the three models, the fusion model had a higher AUC than either the deep learning model or the clinical model in validation cohorts 1 or 2 (AUC = was 0.986, 0.961 vs. 0.706, 0.676/0.506, 0.506). Using the DeLong method, the difference between them was statistically significant (p < 0.05). The Kaplan-Meier analysis distinguished two patient groups with high and low recurrence risk (p = 0.0008 and 0.0035, respectively). Deep learning may be a low-cost, non-invasive method for predicting risk for advanced HGSOC recurrence. Deep learning based on multi-sequence MRI serves as a prognostic biomarker for advanced HGSOC, which provides a preoperative model for predicting recurrence in HGSOC. Additionally, using the fusion model as a new prognostic analysis means that can use MRI data can be used without the need to follow-up the prognostic biomarker.

Personalized recurrence risk assessment following the birth of a child with a pathogenic de novo mutation

Following the diagnosis of a paediatric disorder caused by an apparently de novo mutation, a recurrence risk of 1–2% is frequently quoted due to the possibility of parental germline mosaicism; but for any specific couple, this figure is usually incorrect. We present a systematic approach to providing individualized recurrence risk. By combining locus-specific sequencing of multiple tissues to detect occult mosaicism with long-read sequencing to determine the parent-of-origin of the mutation, we show that we can stratify the majority of couples into one of seven discrete categories associated with substantially different risks to future offspring. Among 58 families with a single affected offspring (representing 59 de novo mutations in 49 genes), the recurrence risk for 35 (59%) was decreased below 0.1%, but increased owing to parental mixed mosaicism for 5 (9%)—that could be quantified in semen for paternal cases (recurrence risks of 5.6–12.1%). Implementation of this strategy offers the prospect of driving a major transformation in the practice of genetic counselling.