Explainable Machine Learning Model to Preoperatively Predict Postoperative Complications in Inpatients With Cancer Undergoing Major Operations.

PURPOSE: Preoperative prediction of postoperative complications (PCs) in inpatients with cancer is challenging. We developed an explainable machine learning (ML) model to predict PCs in a heterogenous population of inpatients with cancer undergoing same-hospitalization major operations. METHODS: Consecutive inpatients who underwent same-hospitalization operations from December 2017 to June 2021 at a single institution were retrospectively reviewed. The ML model was developed and tested using electronic health record (EHR) data to predict 30-day PCs for patients with Clavien-Dindo grade 3 or higher (CD 3+) per the CD classification system. Model performance was assessed using area under the receiver operating characteristic curve (AUROC), area under the precision recall curve (AUPRC), and calibration plots. Model explanation was performed using the Shapley additive explanations (SHAP) method at cohort and individual operation levels. RESULTS: A total of 988 operations in 827 inpatients were included. The ML model was trained using 788 operations and tested using a holdout set of 200 operations. The CD 3+ complication rates were 28.6% and 27.5% in the training and holdout test sets, respectively. Training and holdout test sets' model performance in predicting CD 3+ complications yielded an AUROC of 0.77 and 0.73 and an AUPRC of 0.56 and 0.52, respectively. Calibration plots demonstrated good reliability. The SHAP method identified features and the contributions of the features to the risk of PCs. CONCLUSION: We trained and tested an explainable ML model to predict the risk of developing PCs in patients with cancer. Using patient-specific EHR data, the ML model accurately discriminated the risk of developing CD 3+ complications and displayed top features at the individual operation and cohort level.

Predicting survival of NSCLC patients treated with immune checkpoint inhibitors: Impact and timing of immune-related adverse events and prior tyrosine kinase inhibitor therapy.

Introduction: Immune checkpoint inhibitors (ICIs) produce a broad spectrum of immune-related adverse events (irAEs) affecting various organ systems. While ICIs are established as a therapeutic option in non-small cell lung cancer (NSCLC) treatment, most patients receiving ICI relapse. Additionally, the role of ICIs on survival in patients receiving prior targeted tyrosine kinase inhibitor (TKI) therapy has not been well-defined. Objective: To investigate the impact of irAEs, the relative time of occurrence, and prior TKI therapy to predict clinical outcomes in NSCLC patients treated with ICIs. Methods: A single center retrospective cohort study identified 354 adult patients with NSCLC receiving ICI therapy between 2014 and 2018. Survival analysis utilized overall survival (OS) and real-world progression free survival (rwPFS) outcomes. Model performance matrices for predicting 1-year OS and 6-month rwPFS using linear regression baseline, optimal, and machine learning modeling approaches. Results: Patients experiencing an irAE were found to have a significantly longer OS and rwPFS compared to patients who did not (median OS 25.1 vs. 11.1 months; hazard ratio [HR] 0.51, confidence interval [CI] 0.39- 0.68, P-value <0.001, median rwPFS 5.7 months vs. 2.3; HR 0.52, CI 0.41- 0.66, P-value <0.001, respectively). Patients who received TKI therapy before initiation of ICI experienced significantly shorter OS than patients without prior TKI therapy (median OS 7.6 months vs. 18.5 months; P-value < 0.01). After adjusting for other variables, irAEs and prior TKI therapy significantly impacted OS and rwPFS. Lastly, the performances of models implementing logistic regression and machine learning approaches were comparable in predicting 1-year OS and 6-month rwPFS. Conclusion: The occurrence of irAEs, the timing of the events, and prior TKI therapy were significant predictors of survival in NSCLC patients on ICI therapy. Therefore, our study supports future prospective studies to investigate the impact of irAEs, and sequence of therapy on the survival of NSCLC patients taking ICIs.

Representation of Aging in Elementary School Textbooks in Iran.

The attitude toward older adults is developed from childhood. School textbooks are one of the most important sources of shaping attitude in children. So, the present study aimed to analyze the visual and textual content of the aging concept in elementary school textbooks after the Irans's Islamic Revolution (1979). The method of the present study was content analysis, and 112 textbooks were reviewed. The analysis unit included 118 images and 91 subset of texts pertaining to aging concept. The results showed that aging concepts are classified into two positive and negative stereotypes categories. The positive stereotype included social interaction, authority and respect, wisdom, spirituality, positive traits, and independence. Social interaction was the most frequent of them. Negative stereotypes included abuse, negative personality traits, illness, and disability, of which the negative personality traits were the most frequent. In addition, the results suggested that 87.7% of the concepts of aging in the textbooks were positive. Although the positive stereotypes were more frequent in textbooks, the active older adults were presented in low-status jobs, and the ethnic minorities and older women were less considered. Accordingly, policymaking through the textbooks and from childhood is necessary for developing successful aging and decreasing ageism in society.

Development and Validation of an Explainable Machine Learning Model for Major Complications After Cytoreductive Surgery.

Importance: Cytoreductive surgery (CRS) is one of the most complex operations in surgical oncology with significant morbidity, and improved risk prediction tools are critically needed. Machine learning models can potentially overcome the limitations of traditional multiple logistic regression (MLR) models and provide accurate risk estimates. Objective: To develop and validate an explainable machine learning model for predicting major postoperative complications in patients undergoing CRS. Design, Setting, and Participants: This prognostic study used patient data from tertiary care hospitals with expertise in CRS included in the US Hyperthermic Intraperitoneal Chemotherapy Collaborative Database between 1998 and 2018. Information from 147 variables was extracted to predict the risk of a major complication. An ensemble-based machine learning (gradient-boosting) model was optimized on 80% of the sample with subsequent validation on a 20% holdout data set. The machine learning model was compared with traditional MLR models. The artificial intelligence SHAP (Shapley additive explanations) method was used for interpretation of patient- and cohort-level risk estimates and interactions to define novel surgical risk phenotypes. Data were analyzed between November 2019 and August 2021. Exposures: Cytoreductive surgery. Main Outcomes and Measures: Area under the receiver operating characteristics (AUROC); area under the precision recall curve (AUPRC). Results: Data from a total 2372 patients were included in model development (mean age, 55 years [range, 11-95 years]; 1366 [57.6%] women). The optimized machine learning model achieved high discrimination (AUROC: mean cross-validation, 0.75 [range, 0.73-0.81]; test, 0.74) and precision (AUPRC: mean cross-validation, 0.50 [range, 0.46-0.58]; test, 0.42). Compared with the optimized machine learning model, the published MLR model performed worse (test AUROC and AUPRC: 0.54 and 0.18, respectively). Higher volume of estimated blood loss, having pelvic peritonectomy, and longer operative time were the top 3 contributors to the high likelihood of major complications. SHAP dependence plots demonstrated insightful nonlinear interactive associations between predictors and major complications. For instance, high estimated blood loss (ie, above 500 mL) was only detrimental when operative time exceeded 9 hours. Unsupervised clustering of patients based on similarity of sources of risk allowed identification of 6 distinct surgical risk phenotypes. Conclusions and Relevance: In this prognostic study using data from patients undergoing CRS, an optimized machine learning model demonstrated a superior ability to predict individual- and cohort-level risk of major complications vs traditional methods. Using the SHAP method, 6 distinct surgical phenotypes were identified based on sources of risk of major complications.

Analysis of Gut Microbiome Using Explainable Machine Learning Predicts Risk of Diarrhea Associated With Tyrosine Kinase Inhibitor Neratinib: A Pilot Study.

Neratinib has great efficacy in treating HER2+ breast cancer but is associated with significant gastrointestinal toxicity. The objective of this pilot study was to understand the association of gut microbiome and neratinib-induced diarrhea. Twenty-five patients (age ≥ 60) were enrolled in a phase II trial evaluating safety and tolerability of neratinib in older adults with HER2+ breast cancer (NCT02673398). Fifty stool samples were collected from 11 patients at baseline and during treatment. 16S rRNA analysis was performed and relative abundance data were generated. Shannon's diversity was calculated to examine gut microbiome dysbiosis. An explainable tree-based approach was utilized to classify patients who might experience neratinib-related diarrhea (grade ≥ 1) based on pre-treatment baseline microbial relative abundance data. The hold-out Area Under Receiver Operating Characteristic and Area Under Precision-Recall Curves of the model were 0.88 and 0.95, respectively. Model explanations showed that patients with a larger relative abundance of Ruminiclostridium 9 and Bacteroides sp. HPS0048 may have reduced risk of neratinib-related diarrhea and was confirmed by Kruskal-Wallis test (p ≤ 0.05, uncorrected). Our machine learning model identified microbiota associated with reduced risk of neratinib-induced diarrhea and the result from this pilot study will be further verified in a larger study. CLINICAL TRIAL REGISTRATION: ClinicalTrials.gov, identifier NCT02673398.

Explainable Tree-Based Predictions for Unplanned 30-Day Readmission of Patients With Cancer Using Clinical Embeddings.

PURPOSE: Thirty-day unplanned readmission is one of the key components in measuring quality in patient care. Risk of readmission in oncology patients may be associated with a wide variety of specific factors including laboratory results and diagnoses, and it is hard to include all such features using traditional approaches such as one-hot encoding in predictive models. METHODS: We used clinical embeddings to represent complex medical concepts in lower dimensional spaces. For predictive modeling, we used gradient-boosted trees and adopted the shapley additive explanation framework to offer consistent individualized predictions. We used retrospective inpatient data between 2013 and 2018 with temporal split for training and testing. RESULTS: Our best performing model predicting readmission at discharge using clinical embeddings showed a testing area under receiver operating characteristic curve of 0.78 (95% CI, 0.77 to 0.80). Use of clinical embeddings led to up to 23.1% gain in area under precision-recall curve and 6% in area under receiver operating characteristic curve. Hematology models had more performance gain over surgery and medical oncology. Our study was the first to develop (1) explainable predictive models for the hematology population and (2) dynamic models to keep track of readmission risk throughout the duration of patient visit. CONCLUSION: To our knowledge, our study was the first to develop (1) explainable predictive models for the hematology population and (2) dynamic models to keep track of readmission risk throughout the duration of patient visit.

Molecular Profiling of Innate Immune Response Mechanisms in Ventilator-associated Pneumonia.

Ventilator-associated pneumonia (VAP) is a common hospital-acquired infection, leading to high morbidity and mortality. Currently, bronchoalveolar lavage (BAL) is used in hospitals for VAP diagnosis and guiding treatment options. Although BAL collection procedures are invasive, alternatives such as endotracheal aspirates (ETA) may be of diagnostic value, however, their use has not been thoroughly explored. Longitudinal ETA and BAL were collected from 16 intubated patients up to 15 days, of which 11 developed VAP. We conducted a comprehensive LC-MS/MS based proteome and metabolome characterization of longitudinal ETA and BAL to detect host and pathogen responses to VAP infection. We discovered a diverse ETA proteome of the upper airways reflective of a rich and dynamic host-microbe interface. Prior to VAP diagnosis by microbial cultures from BAL, patient ETA presented characteristic signatures of reactive oxygen species and neutrophil degranulation, indicative of neutrophil mediated pathogen processing as a key host response to the VAP infection. Along with an increase in amino acids, this is suggestive of extracellular membrane degradation resulting from proteolytic activity of neutrophil proteases. The metaproteome approach successfully allowed simultaneous detection of pathogen peptides in patients' ETA, which may have potential use in diagnosis. Our findings suggest that ETA may facilitate early mechanistic insights into host-pathogen interactions associated with VAP infection and therefore provide its diagnosis and treatment.