DummyNeratinib 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 RegistrationClinicalTrials.gov, identifier NCT02673398.

Key Points Question Can machine learning provide superior risk prediction compared with the current statistical methods for patients undergoing cytoreductive surgery? Findings In this prognostic study, an optimized machine learning model demonstrated superior capability of predicting individual-level risk of major complications after cytoreductive surgery than traditional methods. Cohort-level risk prediction allowed unbiased categorization of patients into 6 distinct surgical risk groups. Meaning These results suggest that explainable machine learning methods cannot only provide accurate risk prediction but can also allow identification of potentially modifiable sources of risk on patient and cohort levels.

Ventilator-associated pneumonia (VAP) is a common hospital-acquired infection, leading to high morbidity and mortality. Currently, bronchoalveolar lavage (BAL) is utilized in hospitals for VAP diagnosis and guiding treatment options. While BAL collection procedures are invasive, alternatives such as endotracheal aspirates (ETA) may be of diagnostic value, however, their utility 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 utility 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.

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.

Sepsis and severe sepsis contribute significantly to early treatment-related mortality after hematopoietic cell transplantation (HCT), with reported mortality rates of 30 and 55% due to severe sepsis, during engraftment admission, for autologous and allogeneic HCT, respectively. Since the clinical presentation and characteristics of sepsis immediately after HCT can be different from that seen in general population or those who are receiving non-HCT chemotherapy, detecting early signs of sepsis in HCT recipients becomes critical. Herein, we developed and validated a machine-learning based sepsis prediction model for patients who underwent HCT at City of Hope, using variables within the Electronic Health Record (EHR) data. We evaluated a consecutive case series of 1046 HCTs (autologous: n=491, allogeneic: n=555) at our center between 2014 and 2017. The median age at the time of HCT was 56 years (range: 18-78). For this analysis, the primary clinical event was sepsis diagnosis within 100 days post-HCT, identified based on - use of the institutional sepsis management order set and mention of "sepsis" in the progress notes. The time of sepsis order set was considered as time of sepsis for analyses. To train the model, 829 visits (104 septic and 725 non-septic) and their data were used, while 217 visits (31 septic and 186 non-septic) were used as a validation cohort. At each hour after HCT, when a new data point was available, 47 variables were calculated from each patient's data and a risk score was assigned to each time point. These variables consisted of patient demographics, transplant type, regimen intensity, disease status, Hematopoietic cell transplantation - specific comorbidity index, lab values, vital signs, medication orders, and comorbidities. For the 829 visits in the training dataset, the 47 variables were calculated at 220,889 different time points, resulting in a total of 10,381,783 data points. Lab values and vital signs were considered as changes from individual patient's baselines at each time point. The baseline for each lab value and vital sign were the last measured values before HCT. An ensemble of 20 random forest binary classification models were trained to identify and learn patterns of data for HCT patients at high risk for sepsis and differentiate them from patients at lower sepsis risk. To help the model learning patterns of data prior to sepsis, available data from septic patients' within 24 hours preceding diagnosis of sepsis was used. For 829 septic visits in the training data set, there were 5048 time points, each having 47 variables. Variable importance for the 20 models was assessed using Gini mean decrease accuracy method. The sum of importance values from each model was calculated for each variable as the final importance value. Figure 1a shows the importance of variables using this method. Testing the model on the validation cohort results in an AUC of 0.85 on the test dataset (Figure 1b). At a threshold of 0.6, our model was 0.32 sensitive and 0.96 specific. At this threshold, this model identified 10 out of 31 patients with a median lead time of 119.5 hours, of which 2 patients were flagged as high risk at the time of transplant and developed sepsis at 17 and 60 days post-HCT. The lead time is what truly sets this predictive model apart from detective models with organ failure or dysfunction or other deterioration metrics as their detection criteria. At a threshold of 0.4, our model has 0.9 sensitivity and 0.65 specificity. In summary, a machine-learning sepsis prediction model can be tailored towards HCT recipients to improve the quality of care, prevent sepsis associated-organ damage and decrease mortality post-HCT. Our model significantly outperforms widely used Modified Early Warning Score (MEWS), with AUC of 0.73 in general population. Possible application of our model include showing a "red flag" at a threshold of 0.6 (0.32 true positive rate and 0.04 false positive rate) for antibiotic initiation/modification, and a "yellow flag" at a threshold of 0.4 (0.9 true positive rate and 0.35 false positive rate) suggesting closer monitoring or less aggressive treatments for the patient. Figure 1. Figure 1. Disclosures Dadwal: MERK: Consultancy, Membership on an entity's Board of Directors or advisory committees, Research Funding, Speakers Bureau; Gilead: Research Funding; AiCuris: Research Funding; Shire: Research Funding.