Machine Learning Models for the Prediction of Breast Cancer Prognostic: Application and Comparison Based on a Retrospective Cohort Study (Preprint)

Abstract STUDY QUESTION Can a machine-learning-based model trained in clinical and biological variables support the prediction of the presence or absence of sperm in testicular biopsy in non-obstructive azoospermia (NOA) patients? SUMMARY ANSWER Our machine-learning model was able to accurately predict (AUC of 0.8) the presence or absence of spermatozoa in patients with NOA. WHAT IS KNOWN ALREADY Patients with NOA can conceive with their own biological gametes using ICSI in combination with successful testicular sperm extraction (TESE). Testicular sperm retrieval is successful in up to 50% of men with NOA. However, to the best of our knowledge, there is no existing model that can accurately predict the success of sperm retrieval in TESE. Moreover, machine-learning has never been used for this purpose. STUDY DESIGN, SIZE, DURATION A retrospective cohort study of 119 patients who underwent TESE in a single IVF unit between 1995 and 2017 was conducted. All patients with NOA who underwent TESE during their fertility treatments were included. The development of gradient-boosted trees (GBTs) aimed to predict the presence or absence of spermatozoa in patients with NOA. The accuracy of these GBTs was then compared to a similar multivariate logistic regression model (MvLRM). PARTICIPANTS/MATERIALS, SETTING, METHODS We employed univariate and multivariate binary logistic regression models to predict the probability of successful TESE using a dataset from a retrospective cohort. In addition, we examined various ensemble machine-learning models (GBT and random forest) and evaluated their predictive performance using the leave-one-out cross-validation procedure. A cutoff value for successful/unsuccessful TESE was calculated with receiver operating characteristic (ROC) curve analysis. MAIN RESULTS AND THE ROLE OF CHANCE ROC analysis resulted in an AUC of 0.807 ± 0.032 (95% CI 0.743–0.871) for the proposed GBTs and 0.75 ± 0.052 (95% CI 0.65–0.85) for the MvLRM for the prediction of presence or absence of spermatozoa in patients with NOA. The GBT approach and the MvLRM yielded a sensitivity of 91% vs. 97%, respectively, but the GBT approach has a specificity of 51% compared with 25% for the MvLRM. A total of 78 (65.3%) men with NOA experienced successful TESE. FSH, LH, testosterone, semen volume, age, BMI, ethnicity and testicular size on clinical evaluation were included in these models. LIMITATIONS, REASONS FOR CAUTION This study is a retrospective cohort study, with all the associated inherent biases of such studies. This model was used only for TESE, since micro-TESE is not performed at our center. WIDER IMPLICATIONS OF THE FINDINGS Machine-learning models may lay the foundation for a decision support system for clinicians together with their NOA patients concerning TESE. The findings of this study should be confirmed with further larger and prospective studies. STUDY FUNDING/COMPETING INTEREST(S) The study was funded by the Division of Obstetrics and Gynecology, Soroka University Medical Center, there are no potential conflicts of interest for all authors.

Download Full-text

Can machine learning be used to reduce overtreatment of the axilla in breast cancer? Results from a retrospective cohort study

European Journal of Surgical Oncology ◽

10.1016/j.ejso.2020.11.195 ◽

2021 ◽

Vol 47 (2) ◽

pp. e19

Author(s):

Felix Jozsa ◽

Muneer Ahmed ◽

Rose Baker ◽

Michael Douek

Keyword(s):

Breast Cancer ◽

Machine Learning ◽

Cohort Study ◽

Retrospective Cohort Study ◽

Retrospective Cohort

Download Full-text

ACEI/ARB Medication During ICU Stay Decrease All-Cause In-hospital Mortality in Critically Ill Patients With Hypertension: A Retrospective Cohort Study Based on Machine Learning

Frontiers in Cardiovascular Medicine ◽

10.3389/fcvm.2021.787740 ◽

2022 ◽

Vol 8 ◽

Author(s):

Boshen Yang ◽

Sixuan Xu ◽

Di Wang ◽

Yu Chen ◽

Zhenfa Zhou ◽

...

Keyword(s):

Machine Learning ◽

Cohort Study ◽

Hospital Mortality ◽

Critically Ill ◽

Critically Ill Patients ◽

Retrospective Cohort ◽

Learning Models ◽

Hyperparameter Optimization ◽

Icu Stay ◽

Machine Learning Models

Background: Hypertension is a rather common comorbidity among critically ill patients and hospital mortality might be higher among critically ill patients with hypertension (SBP ≥ 140 mmHg and/or DBP ≥ 90 mmHg). This study aimed to explore the association between ACEI/ARB medication during ICU stay and all-cause in-hospital mortality in these patients.Methods: A retrospective cohort study was conducted based on data from Medical Information Mart for Intensive Care IV (MIMIC-IV) database, which consisted of more than 40,000 patients in ICU between 2008 and 2019 at Beth Israel Deaconess Medical Center. Adults diagnosed with hypertension on admission and those had high blood pressure (SBP ≥ 140 mmHg and/or DBP ≥ 90 mmHg) during ICU stay were included. The primary outcome was all-cause in-hospital mortality. Patients were divided into ACEI/ARB treated and non-treated group during ICU stay. Propensity score matching (PSM) was used to adjust potential confounders. Nine machine learning models were developed and validated based on 37 clinical and laboratory features of all patients. The model with the best performance was selected based on area under the receiver operating characteristic curve (AUC) followed by 5-fold cross-validation. After hyperparameter optimization using Grid and random hyperparameter search, a final LightGBM model was developed, and Shapley Additive exPlanations (SHAP) values were calculated to evaluate feature importance of each feature. The features closely associated with hospital mortality were presented as significant features.Results: A total of 15,352 patients were enrolled in this study, among whom 5,193 (33.8%) patients were treated with ACEI/ARB. A significantly lower all-cause in-hospital mortality was observed among patients treated with ACEI/ARB (3.9 vs. 12.7%) as well as a lower 28-day mortality (3.6 vs. 12.2%). The outcome remained consistent after propensity score matching. Among nine machine learning models, the LightGBM model had the highest AUC = 0.9935. The SHAP plot was employed to make the model interpretable based on LightGBM model after hyperparameter optimization, showing that ACEI/ARB use was among the top five significant features, which were associated with hospital mortality.Conclusions: The use of ACEI/ARB in critically ill patients with hypertension during ICU stay is related to lower all-cause in-hospital mortality, which was independently associated with increased survival in a large and heterogeneous cohort of critically ill hypertensive patients with or without kidney dysfunction.

Download Full-text