UroPredict: Machine learning model on real-world data for prediction of kidney cancer recurrence (UroCCR-120).

Renal cell carcinoma (RCC) is most often diagnosed at a localized stage, where surgery is the standard of care. Existing prognostic scores provide moderate predictive performance, leading to challenges in establishing follow-up recommendations after surgery and in selecting patients who could benefit from adjuvant therapy. In this study, we developed a model for individual postoperative disease-free survival (DFS) prediction using machine learning (ML) on real-world prospective data. Using the French kidney cancer research network database, UroCCR, we analyzed a cohort of surgically treated RCC patients. Participating sites were randomly assigned to either the training or testing cohort, and several ML models were trained on the training dataset. The predictive performance of the best ML model was then evaluated on the test dataset and compared with the usual risk scores. In total, 3372 patients were included, with a median follow-up of 30 months. The best results in predicting DFS were achieved using Cox PH models that included 24 variables, resulting in an iAUC of 0.81 [IC95% 0.77-0.85]. The ML model surpassed the predictive performance of the most commonly used risk scores while handling incomplete data in predictors. Lastly, patients were stratified into four prognostic groups with good discrimination (iAUC = 0.79 [IC95% 0.74-0.83]). Our study suggests that applying ML to real-world prospective data from patients undergoing surgery for localized or locally advanced RCC can provide accurate individual DFS prediction, outperforming traditional prognostic scores.

GIInger predicts homologous recombination deficiency and patient response to PARPi treatment from shallow genomic profiles.

Homologous recombination deficiency (HRD) is a predictive biomarker for poly(ADP-ribose) polymerase 1 inhibitor (PARPi) sensitivity. Routine HRD testing relies on identifying BRCA mutations, but additional HRD-positive patients can be identified by measuring genomic instability (GI), a consequence of HRD. However, the cost and complexity of available solutions hamper GI testing. We introduce a deep learning framework, GIInger, that identifies GI from HRD-induced scarring observed in low-pass whole-genome sequencing data. GIInger seamlessly integrates into standard BRCA testing workflows and yields reproducible results concordant with a reference method in a multisite study of 327 ovarian cancer samples. Applied to a BRCA wild-type enriched subgroup of 195 PAOLA-1 clinical trial patients, GIInger identified HRD-positive patients who experienced significantly extended progression-free survival when treated with PARPi. GIInger is, therefore, a cost-effective and easy-to-implement method for accurately stratifying patients with ovarian cancer for first-line PARPi treatment.

A CT-Based Clinical, Radiological and Radiomic Machine Learning Model for Predicting Malignancy of Solid Renal Tumors (UroCCR-75).

BACKGROUND: Differentiating benign from malignant renal tumors is important for patient management, and it may be improved by quantitative CT features analysis including radiomic. PURPOSE: This study aimed to compare performances of machine learning models using bio-clinical, conventional radiologic and 3D-radiomic features for the differentiation of benign and malignant solid renal tumors using pre-operative multiphasic contrast-enhanced CT examinations. MATERIALS AND METHODS: A unicentric retrospective analysis of prospectively acquired data from a national kidney cancer database was conducted between January 2016 and December 2020. Histologic findings were obtained by robotic-assisted partial nephrectomy. Lesion images were semi-automatically segmented, allowing for a 3D-radiomic features extraction in the nephrographic phase. Conventional radiologic parameters such as shape, content and enhancement were combined in the analysis. Biological and clinical features were obtained from the national database. Eight machine learning (ML) models were trained and validated using a ten-fold cross-validation. Predictive performances were evaluated comparing sensitivity, specificity, accuracy and AUC. RESULTS: A total of 122 patients with 132 renal lesions, including 111 renal cell carcinomas (RCCs) (111/132, 84%) and 21 benign tumors (21/132, 16%), were evaluated (58 +/- 14 years, men 74%). Unilaterality (100/111, 90% vs. 13/21, 62%; p = 0.02), necrosis (81/111, 73% vs. 8/21, 38%; p = 0.02), lower values of tumor/cortex ratio at portal time (0.61 vs. 0.74, p = 0.01) and higher variation of tumor/cortex ratio between arterial and portal times (0.22 vs. 0.05, p = 0.008) were associated with malignancy. A total of 35 radiomics features were selected, and "intensity mean value" was associated with RCCs in multivariate analysis (OR = 0.99). After ten-fold cross-validation, a C5.0Tree model was retained for its predictive performances, yielding a sensitivity of 95%, specificity of 42%, accuracy of 87% and AUC of 0.74. CONCLUSION: Our machine learning-based model combining clinical, radiologic and radiomics features from multiphasic contrast-enhanced CT scans may help differentiate benign from malignant solid renal tumors.

The prognostic value of radiomic features in liver-limited metastatic colorectal cancer patients from the TRIBE2 study.

Aims: Evaluating the prognostic role of radiomic features in liver-limited metastatic colorectal cancer treated with first-line therapy at baseline and best response among patients undergoing resection. Patients & methods: Among patients enrolled in TRIBE2 (NCT02339116), the association of clinical and radiomic data, extracted by SOPHiA-DDM™ with progression-free and overall survival (OS) in the overall population and with disease-free survival/postresection OS in those undergoing resection was investigated. Results: Among 98 patients, radiomic parameters improved the prediction accuracy of our model for OS (area under the curve: 0.83; sensitivity: 0.85; specificity: 0.73; accuracy: 0.78), but not progression-free survival. Of 46 resected patients, small-distance high gray-level emphasis was associated with shorter disease-free survival and high gray-level zone emphasis/higher kurtosis with shorter postresection OS. Conclusion: Radiomic features should be implemented as tools of outcome prediction for liver-limited metastatic colorectal cancer.

Machine-learning approach for prediction of pT3a upstaging and outcomes of localized renal cell carcinoma (UroCCR-15).

OBJECTIVES: To assess the impact of pathological upstaging from clinically localized to locally advanced pT3a on survival in patients with renal cell carcinoma (RCC), as well as the oncological safety of various surgical approaches in this setting, and to develop a machine-learning-based, contemporary, clinically relevant model for individual preoperative prediction of pT3a upstaging. MATERIALS AND METHODS: Clinical data from patients treated with either partial nephrectomy (PN) or radical nephrectomy (RN) for cT1/cT2a RCC from 2000 to 2019, included in the French multi-institutional kidney cancer database UroCCR, were retrospectively analysed. Seven machine-learning algorithms were applied to the cohort after a training/testing split to develop a predictive model for upstaging to pT3a. Survival curves for disease-free survival (DFS) and overall survival (OS) rates were compared between PN and RN after G-computation for pT3a tumours. RESULTS: A total of 4395 patients were included, among whom 667 patients (15%, 337 PN and 330 RN) had a pT3a-upstaged RCC. The UroCCR-15 predictive model presented an area under the receiver-operating characteristic curve of 0.77. Survival analysis after adjustment for confounders showed no difference in DFS or OS for PN vs RN in pT3a tumours (DFS: hazard ratio [HR] 1.08, P = 0.7; OS: HR 1.03, P > 0.9). CONCLUSIONS: Our study shows that machine-learning technology can play a useful role in the evaluation and prognosis of upstaged RCC. In the context of incidental upstaging, PN does not compromise oncological outcomes, even for large tumour sizes.

Impact of Model Choice When Studying the Relationship Between Blood Pressure Variability and Risk of Stroke Recurrence.

[Figure: see text].

Cardio-pulmonary-renal interactions in ICU patients. Role of mechanical ventilation, venous congestion and perfusion deficit on worsening of renal function: Insights from the MIMIC-III database.

Background Mechanical ventilation (MV) in ICU patients may impact hemodynamics and renal function. We aimed to describe the interactions of MV settings, hemodynamic parameters and worsening of renal function (WRF). Methods We included adult patients admitted for the first time in the ICU from the MIMIC-III database. Mean arterial blood pressure (mABP), central venous pressure (CVP) and positive end-expiratory pressure (PEEP) were collected and summarized as a time-weighted mean. The main outcome was WRF defined as acute kidney injury (AKI) occurrence or one-KDIGO stage worsening compared to the KDIGO stage the day before. We used a multinomial logistic regression at day 1 (ldmk-1) and day 2 (ldmk-2) according to a landmark-approach, with a two-days sliding perspective. Results 27,248/61,051 patients met the inclusion criteria (15,258 male (56.0%); 60.1% over 60 y). ICU and hospital mortality were 7.4 and 10.7%, respectively. MV was independently associated with WRF in the ldmrk-1 and -2 models (relative risk ratio [RRR] 8.15 [6.58;10.11] and 7.08 [3.97;12.61] at day-3 and 4, respectively). In MV patients, PEEP was associated with WRF in the ldmrk-1 and -2 models (RRR 1.36 [1.16, 1.6] and 1.17 [0.88, 1.56] by 1 cmH2O increase at day-3 and 4, respectively). Mean perfusion pressure decreased while central venous pressure increased over PEEP categories. In multivariable analysis, mABP, CVP and PEEP were independently associated with WRF. Conclusion In this large cohort of ICU patients, we observed a strong relationship between MV and WRF. PEEP was associated with WRF in MV patients. This association relied at least partly on renal venous congestion.

Role of 3D volume growth rate for drug activity evaluation in meningioma clinical trials: the example of the CEVOREM study.

BACKGROUND: We aimed to improve the assessment of the drug activity in meningioma clinical trials based on the study of the 3D volume growth rate (3DVGR) in a series of aggressive meningiomas. We secondarily aimed to correlate 3DVGR study with patient outcome. METHODS: We performed a post hoc analysis based on volume data and 3DVGR extracted from CEVOREM study including 18 patients with 32 recurrent high-grade meningiomas and treated with everolimus and octreotide. The joint latent class model was used to classify tumor 3DVGR undertreatment. RESULTS: Class 1 includes lesions responding to treatment with decrease in volume in the first 3 months, and then a stabilization thereafter (9.5% of tumors) (mean pretreatment 3DVGR = 6.13%/month; mean undertreatment 3DVGR = -18.7%/month within 3 first months and -0.14%/month after the 3 first months). Class 2 includes lesions considered as stable or with a slight increase in volume undertreatment (65.5%) (mean pretreatment 3DVGR = 6.09%/month; undertreatment 3DVGR = -0.09% within the first 3 months). Class 3 includes lesions without 3DVGR decrease (25%) (mean pretreatment 3DVGR = 46.9%/month; mean undertreatment 3DVGR = 19.2%/month within the first 3 months). Patients with class 3 lesions had a significantly worse progression-free survival (PFS) rate than class 1 and 2 ones. CONCLUSIONS: Tumor 3DVGR could be helpful to detect early signal of drugs antitumoral activity or nonactivity. This volume response classification could help in the assessment of drug activity in tumors with mostly volume stabilization and rare response as aggressive meningiomas even with a low number of patients in complement to 6 months PFS.

Dynamic prediction models for graft failure in paediatric kidney transplantation.

BACKGROUND: Several models have been proposed to predict kidney graft failure in adult recipients but none in younger recipients. Our objective was to propose a dynamic prediction model for graft failure in young kidney transplant recipients. METHODS: We included 793 kidney transplant recipients waitlisted before the age of 18 years who received a first kidney transplantation before the age of 21 years in France in 2002-13 and survived >90 days with a functioning graft. We used a Cox model including baseline predictors only (sex, age at transplant, primary kidney disease, dialysis duration, donor type and age, human leucocyte antigen matching, cytomegalovirus serostatus, cold ischaemia time and delayed graft function) and two joint models also accounting for post-transplant estimated glomerular filtration rate (eGFR) trajectory. Predictive performances were evaluated using a cross-validated area under the curve (AUC) and R2 curves. RESULTS: When predicting the risk of graft failure from any time within the first 7 years after paediatric kidney transplantation, the predictions for the following 3 or 5 years were accurate and much better with the joint models than with the Cox model (AUC ranged from 0.83 to 0.91 for the joint models versus 0.56 to 0.64 for the Cox model). CONCLUSION: Accounting for post-transplant eGFR trajectory strongly increased the accuracy of graft failure prediction in young kidney transplant recipients.

Text Mining in Electronic Medical Records Enables Quick and Efficient Identification of Pregnancy Cases Occurring After Breast Cancer.

PURPOSE: To apply text mining (TM) technology on electronic medical records (EMRs) of patients with breast cancer (BC) to retrieve the occurrence of a pregnancy after BC diagnosis and compare its performance to manual curation. MATERIALS AND METHODS: The training cohort (Cohort A) comprised 344 patients with BC age ≤ 40 years old treated at Institut Curie between 2005 and 2007. Manual curation consisted in manually reviewing each EMR to retrieve pregnancies. TM consisted of first applying a keyword filter ("accouch*" or "enceinte," French terms for "deliver*" and "pregnant," respectively) to select a subset of EMRs, and, second, checking manually EMRs to confirm the pregnancy. Then, we applied our TM algorithm on an independent cohort of patients with BC treated between 2008 and 2012 (Cohort B). RESULTS: In Cohort A, 36 pregnancies were identified among 344 patients (10.5%; 2,829 person-years of EMR). Thirty were identified by manual review versus 35 by TM. TM resulted in a lower percentage of manual checking (26.7% v 100%, respectively) and substantial time gains (time to identify a pregnancy: 13 minutes for TM v 244 minutes for manual curation, respectively). Presence of any of the two TM filters showed excellent sensitivity (97%) and negative predictive value (100%). In Cohort B, 67 pregnancies were identified among 1,226 patients (5.5%; 7,349 person-years of EMR). Similarly, for Cohort B, TM spared 904 (73.7%) EMRs from manual review and quickly generated a cohort of 67 pregnancies after BC. Incidence rate of pregnancy after BC was 0.01 pregnancy per person-year of EMR in both cohorts. CONCLUSION: TM is highly efficient to quickly identify rare events and is a promising tool to improve rapidity, efficiency, and costs of medical research.

Evaluation of least significant changes of pulse contour analysis-derived parameters.

BACKGROUND: Many maneuvers assessing fluid responsiveness (minifluid challenge, lung recruitment maneuver, end-expiratory occlusion test, passive leg raising) are considered as positive when small variations in cardiac index, stroke volume index, stroke volume variation or pulse pressure variation occur. Pulse contour analysis allows continuous and real-time cardiac index, stroke volume, stroke volume variation and pulse pressure variation estimations. To use these maneuvers with pulse contour analysis, the knowledge of the minimal change that needs to be measured by a device to recognize a real change (least significant change) has to be studied. The aim of this study was to evaluate the least significant change of cardiac index, stroke volume index, stroke volume variation and pulse pressure variation obtained using pulse contour analysis (ProAQT®, Pulsion Medical System, Germany). METHODS: In this observational study, we included 50 mechanically ventilated patients undergoing neurosurgery in the operating room. Cardiac index, stroke volume index, pulse pressure variation and stroke volume variation obtained using ProAQT® (Pulsion Medical System, Germany) were recorded every 12 s during 15-min steady-state periods. Least significant changes were calculated every minute. RESULTS: Least significant changes statistically differed over time for cardiac index, stroke volume index, pulse pressure variation and stroke volume variation (p < 0.001). Least significant changes ranged from 1.3 to 0.7% for cardiac index, from 1.3 to 0.8% for stroke volume index, from 10 to 4.9% for pulse pressure variation and from 10.8 to 4.3% for stroke volume variation. CONCLUSION: To conclude, the present study suggests that pulse contour analysis is able to detect rapid and small changes in cardiac index and stroke volume index, but the interpretation of rapid and small changes of pulse pressure variation and stroke volume variation must be done with caution.

Individual dynamic predictions using landmarking and joint modelling: Validation of estimators and robustness assessment.

After the diagnosis of a disease, one major objective is to predict cumulative probabilities of events such as clinical relapse or death from the individual information collected up to a prediction time, usually including biomarker repeated measurements. Several competing estimators have been proposed, mainly from two approaches: joint modelling and landmarking. These approaches differ by the information used, the model assumptions and the complexity of the computational procedures. This paper aims to review the two approaches, precisely define the derived estimators of dynamic predictions and compare their performances notably in case of misspecification. The ultimate goal is to provide key elements for the use of individual dynamic predictions in clinical practice. Prediction of two competing causes of prostate cancer progression from the history of prostate-specific antigen is used as a motivated example. We formally define the quantity to estimate and its estimators, propose techniques to assess the uncertainty around predictions and validate them. We then conduct an in-depth simulation study compare the estimators in terms of prediction error, discriminatory power, efficiency and robustness to model assumptions. We show that prediction tools should be handled with care, in particular by properly specifying models and estimators.

Joint modelling of longitudinal and multi-state processes: application to clinical progressions in prostate cancer.

Joint modelling of longitudinal and survival data is increasingly used in clinical trials on cancer. In prostate cancer for example, these models permit to account for the link between longitudinal measures of prostate-specific antigen (PSA) and time of clinical recurrence when studying the risk of relapse. In practice, multiple types of relapse may occur successively. Distinguishing these transitions between health states would allow to evaluate, for example, how PSA trajectory and classical covariates impact the risk of dying after a distant recurrence post-radiotherapy, or to predict the risk of one specific type of clinical recurrence post-radiotherapy, from the PSA history. In this context, we present a joint model for a longitudinal process and a multi-state process, which is divided into two sub-models: a linear mixed sub-model for longitudinal data and a multi-state sub-model with proportional hazards for transition times, both linked by a function of shared random effects. Parameters of this joint multi-state model are estimated within the maximum likelihood framework using an EM algorithm coupled with a quasi-Newton algorithm in case of slow convergence. It is implemented under R, by combining and extending mstate and JM packages. The estimation program is validated by simulations and applied on pooled data from two cohorts of men with localized prostate cancer. Thanks to the classical covariates available at baseline and the repeated PSA measurements, we are able to assess the biomarker's trajectory, define the risks of transitions between health states and quantify the impact of the PSA dynamics on each transition intensity. Copyright © 2016 John Wiley & Sons, Ltd.

Joint model for left-censored longitudinal data, recurrent events and terminal event: Predictive abilities of tumor burden for cancer evolution with application to the FFCD 2000-05 trial.

In oncology, the international WHO and RECIST criteria have allowed the standardization of tumor response evaluation in order to identify the time of disease progression. These semi-quantitative measurements are often used as endpoints in phase II and phase III trials to study the efficacy of new therapies. However, through categorization of the continuous tumor size, information can be lost and they can be challenged by recently developed methods of modeling biomarkers in a longitudinal way. Thus, it is of interest to compare the predictive ability of cancer progressions based on categorical criteria and quantitative measures of tumor size (left-censored due to detection limit problems) and/or appearance of new lesions on overall survival. We propose a joint model for a simultaneous analysis of three types of data: a longitudinal marker, recurrent events, and a terminal event. The model allows to determine in a randomized clinical trial on which particular component treatment acts mostly. A simulation study is performed and shows that the proposed trivariate model is appropriate for practical use. We propose statistical tools that evaluate predictive accuracy for joint models to compare our model to models based on categorical criteria and their components. We apply the model to a randomized phase III clinical trial of metastatic colorectal cancer, conducted by the Fédération Francophone de Cancérologie Digestive (FFCD 2000-05 trial), which assigned 410 patients to two therapeutic strategies with multiple successive chemotherapy regimens.