A new methodology to predict the oncotype scores based on clinico-pathological data with similar tumor profiles.

PURPOSE: The Oncotype DX (ODX) test is a commercially available molecular test for breast cancer assay that provides prognostic and predictive breast cancer recurrence information for hormone positive, HER2-negative patients. The aim of this study is to propose a novel methodology to assist physicians in their decision-making. METHODS: A retrospective study between 2012 and 2020 with 333 cases that underwent an ODX assay from three hospitals in the Bourgogne Franche-Comté region (France) was conducted. Clinical and pathological reports were used to collect the data. A methodology based on distributional random forest was developed to predict the ODX score classes (ODX [Formula: see text] and ODX [Formula: see text]) using 9 clinico-pathological characteristics. This methodology can be used particularly to identify the patients of the training cohort that share similarities with the new patient and to predict an estimate of the distribution of the ODX score. RESULTS: The mean age of participants is 56.9 years old. We have correctly classified [Formula: see text] of patients in low risk and [Formula: see text] of patients in high risk. The overall accuracy is [Formula: see text]. The proportion of low risk correct predicted value (PPV) is [Formula: see text]. The percentage of high risk correct predicted value (NPV) is approximately [Formula: see text]. The F1-score and the Area Under Curve (AUC) are of 0.87 and 0.759, respectively. CONCLUSION: The proposed methodology makes it possible to predict the distribution of the ODX score for a patient. This prediction is reinforced by the determination of a family of known patients with follow-up of identical scores. The use of this methodology with the pathologist's expertise on the different histological and immunohistochemical characteristics has a clinical impact to help oncologist in decision-making regarding breast cancer therapy.

Confounding Effects on the Performance of Machine Learning Analysis of Static Functional Connectivity Computed from rs-fMRI Multi-site Data.

Resting-state functional magnetic resonance imaging (rs-fMRI) is a non-invasive imaging technique widely used in neuroscience to understand the functional connectivity of the human brain. While rs-fMRI multi-site data can help to understand the inner working of the brain, the data acquisition and processing of this data has many challenges. One of the challenges is the variability of the data associated with different acquisitions sites, and different MRI machines vendors. Other factors such as population heterogeneity among different sites, with variables such as age and gender of the subjects, must also be considered. Given that most of the machine-learning models are developed using these rs-fMRI multi-site data sets, the intrinsic confounding effects can adversely affect the generalizability and reliability of these computational methods, as well as the imposition of upper limits on the classification scores. This work aims to identify the phenotypic and imaging variables producing the confounding effects, as well as to control these effects. Our goal is to maximize the classification scores obtained from the machine learning analysis of the Autism Brain Imaging Data Exchange (ABIDE) rs-fMRI multi-site data. To achieve this goal, we propose novel methods of stratification to produce homogeneous sub-samples of the 17 ABIDE sites, as well as the generation of new features from the static functional connectivity values, using multiple linear regression models, ComBat harmonization models, and normalization methods. The main results obtained with our statistical models and methods are an accuracy of 76.4%, sensitivity of 82.9%, and specificity of 77.0%, which are 8.8%, 20.5%, and 7.5% above the baseline classification scores obtained from the machine learning analysis of the static functional connectivity computed from the ABIDE rs-fMRI multi-site data.

Metabolic syndrome screening in adolescents: New scores AI_METS based on artificial intelligence techniques.

BACKGROUND AND AIMS: Metabolic syndrome (MetS) definitions in adolescents based on the percentiles of its components are rather complicated to use in clinical practice. The aim of this study was to test the validity of artificial intelligence (AI)-based scores (AI_METS) that do not use these percentiles for MetS screening for adolescents. METHODS AND RESULTS: This study included 1086 adolescents aged 12 to 18. The cohort underwent anthropometric measurements and blood tests. Mean blood pressure (MBP), and triglyceride glucose index (TyG) were calculated. Explainable AI methods are used to extract the learned function. Gini importance techniques were tested and used to build new scores for the screening of MetS. IDF, Cook, De Ferranti, Viner, and Weiss definitions of MetS were used to test the validity of these scores. MetS prevalence was 0.4%-4.7% according to these definitions. AI_METS used age, waist circumference, MBP, and TyG index. They offer area under the curves (AUCs) 0.91, 0.93, 0.89, 0.93, and 0.98; specificity 81%, 75%, 72%, 80%, and 97%; and sensitivity 90%, 100%, 90%, 100%, and 100%, respectively, for the detection of MetS according to these definitions. Considering only MBP offers a better specificity and sensitivity to detect MetS than considering only TyG index. MBP offers slightly lower performance than AI_METS. CONCLUSION: AI techniques have proven their ability to extract knowledge from data. They allowed us to generate new scores for MetS detection in adolescents without using specific percentiles for each component. Although these scores are less intuitive than the percentile-based definition, their accuracy is rather effective for the detection of MetS.

Détection précoce du cancer du sein : étude de l'impact sociotechnique d'un soutien-gorge «â€ˆintelligent ¼.

INTRODUCTION: The SBra (Smart Bra) project aims to develop an intelligent bra, combining sensors for measuring skin temperature and the electrical impedance of breast tissue, which could be used for breast cancer screening. The objective of this study is to anticipate both the hindrances to usage and acceptability of SBra with respect to the breast cancer screening practices of healthcare professionals and patients, and then to propose ways to modify the shape and functions of the device to facilitate its potential insertion into the healthcare system. METHODS: A qualitative survey was conducted between September 2019 and December 2020, consisting of a series of interviews conducted with hospital and private healthcare professionals (N = 22) working in Burgundy-Franche-Comté and related to breast cancer, and with women aged 38 to 74 years old living in Burgundy-Franche-Comté and Auvergne-Rhône-Alpes (N = 21) who have or have not had breast cancer, and who either practice or refuse screening. RESULTS: If patients say they are ready to use such a device, at most once a year, and subject to its usability, the majority of them prefer an examination in the office, performed by a gynecologist or a general practitioner. Health professionals point out that this option generates institutional (remuneration and cost of the procedure) and organizational needs, which are both material and human. DISCUSSION: The study highlights the need to pluralize the system in order to respond to the multiplicity of local situations.

Robustness testing framework for RUL prediction Deep LSTM networks.

Efficiency and robustness in remaining useful life (RUL) prediction are crucial in system health monitoring. Thus, the internal logic computation of a Deep LSTM model for RUL prediction is mainly shaped and evaluated over a training data-set and its performance examined on a testing data-set. This paper proposes a framework for testing robustness of deep Long Short Term Memory (LSTM) architecture for remaining useful life prediction that enables to gain confidence in the trained LSTM model for RUL prediction and ensures better quality. The resiliency of proposed Deep LSTM networks for RUL estimation using stress functions is first checked then the effect of the stress on model performance is analyzed. A comparison between the performance of the constructed mutant fuzzed Deep LSTM networks and the original Deep LSTM model for RUL prediction is provided to determine the quality of the RUL prediction model. Furthermore, the main purpose of this paper is to determine to what extent Deep LSTM models in the neighborhood of the trained LSTM model still have high test accuracy and quality scoring. Thus, the use of φ-stress operators shows that we could build stable and data-independent Deep LSTM models for RUL prediction. Finally, the proposed framework is validated using the Commercial Modular Aero Propulsion System Simulation (C-MAPSS) data-set.

Prediction of Oncotype DX recurrence score using deep multi-layer perceptrons in estrogen receptor-positive, HER2-negative breast cancer.

Oncotype DX (ODX) is a multi-gene expression signature designed for estrogen receptor (ER)-positive and human epidermal growth factor receptor 2 (HER2)-negative breast cancer patients to predict the recurrence score (RS) and chemotherapy (CT) benefit. The aim of our study is to develop a prediction tool for the three RS's categories based on deep multi-layer perceptrons (DMLP) and using only the morphoimmunohistological variables. We performed a retrospective cohort of 320 patients who underwent ODX testing from three French hospitals. Clinico-pathological characteristics were recorded. We built a supervised machine learning classification model using Matlab software with 152 cases for the training and 168 cases for the testing. Three classifiers were used to learn the three risk categories of the ODX, namely the low, intermediate, and high risk. Experimental results provide the area under the curve (AUC), respectively, for the three risk categories: 0.63 [95% confidence interval: (0.5446, 0.7154), p < 0.001], 0.59 [95% confidence interval: (0.5031, 0.6769), p < 0.001], 0.75 [95% confidence interval: (0.6184, 0.8816), p < 0.001]. Concordance rate between actual RS and predicted RS ranged from 53 to 56% for each class between DMLP and ODX. The concordance rate of low and intermediate combined risk group was 85%.We developed a predictive machine learning model that could help to define patient's RS. Moreover, we integrated histopathological data and DMLP results to select tumor for ODX testing. Thus, this process allows more relevant use of histopathological data, and optimizes and enhances this information.