• Assessment of Machine Learning vs Standard Prediction Rules for Predicting Hospital Readmissions

      Morgan, D.J.; Bame, B.; Zimand, P. (American Medical Association, 2019)
      Importance: Hospital readmissions are associated with patient harm and expense. Ways to prevent hospital readmissions have focused on identifying patients at greatest risk using prediction scores. Objective: To identify the type of score that best predicts hospital readmissions. Design, Setting, and Participants: This prognostic study included 14 062 consecutive adult hospital patients with 16 649 discharges from a tertiary care center, suburban community hospital, and urban critical access hospital in Maryland from September 1, 2016, through December 31, 2016. Patients not included as eligible discharges by the Centers for Medicare & Medicaid Services or the Chesapeake Regional Information System for Our Patients were excluded. A machine learning rank score, the Baltimore score (B score) developed using a machine learning technique, for each individual hospital using data from the 2 years before September 1, 2016, was compared with standard readmission risk assessment scores to predict 30-day unplanned readmissions. Main Outcomes and Measures: The 30-day readmission rate evaluated using various readmission scores: B score, HOSPITAL score, modified LACE score, and Maxim/RightCare score. Results: Of the 10 732 patients (5605 [52.2%] male; mean [SD] age, 54.56 [22.42] years) deemed to be eligible for the study, 1422 were readmitted. The area under the receiver operating characteristic curve (AUROC) for individual rules was 0.63 (95% CI, 0.61-0.65) for the HOSPITAL score, which was significantly lower than the 0.66 for modified LACE score (95% CI, 0.64-0.68; P < .001). The B score machine learning score was significantly better than all other scores; 48 hours after admission, the AUROC of the B score was 0.72 (95% CI, 0.70-0.73), which increased to 0.78 (95% CI, 0.77-0.79) at discharge (all P < .001). At the hospital using Maxim/RightCare score, the AUROC was 0.63 (95% CI, 0.59-0.69) for HOSPITAL, 0.64 (95% CI, 0.61-0.68) for Maxim/RightCare, and 0.66 (95% CI, 0.62-0.69) for modified LACE score. The B score was 0.72 (95% CI, 0.69-0.75) 48 hours after admission and 0.81 (95% CI, 0.79-0.84) at discharge. In directly comparing the B score with the sensitivity at cutoff values for modified LACE, HOSPITAL, and Maxim/RightCare scores, the B score was able to identify the same number of readmitted patients while flagging 25.5% to 54.9% fewer patients. Conclusions and Relevance: Among 3 hospitals in different settings, an automated machine learning score better predicted readmissions than commonly used readmission scores. More efficiently targeting patients at higher risk of readmission may be the first step toward potentially preventing readmissions.
    • A Data-Driven Framework for Identifying Intensive Care Unit Admissions Colonized With Multidrug-Resistant Organisms

      Çaǧlayan, Çaǧlar; Barnes, Sean L; Pineles, Lisa L; Harris, Anthony D; Klein, Eili Y (2022-03-17)
      The rising prevalence of multi-drug resistant organisms (MDROs), such as Methicillin-resistant Staphylococcus aureus (MRSA), Vancomycin-resistant Enterococci (VRE), and Carbapenem-resistant Enterobacteriaceae (CRE), is an increasing concern in healthcare settings.
    • Generative Self-training for Cross-Domain Unsupervised Tagged-to-Cine MRI Synthesis

      Liu, Xiaofeng; Xing, Fangxu; Stone, Maureen; Zhuo, Jiachen; Reese, Timothy; Prince, Jerry L.; El Fakhri, Georges; Woo, Jonghye (Springer Nature, 2021-09-21)
      Self-training based unsupervised domain adaptation (UDA) has shown great potential to address the problem of domain shift, when applying a trained deep learning model in a source domain to unlabeled target domains. However, while the self-training UDA has demonstrated its effectiveness on discriminative tasks, such as classification and segmentation, via the reliable pseudo-label selection based on the softmax discrete histogram, the self-training UDA for generative tasks, such as image synthesis, is not fully investigated. In this work, we propose a novel generative self-training (GST) UDA framework with continuous value prediction and regression objective for cross-domain image synthesis. Specifically, we propose to filter the pseudo-label with an uncertainty mask, and quantify the predictive confidence of generated images with practical variational Bayes learning. The fast test-time adaptation is achieved by a round-based alternative optimization scheme. We validated our framework on the tagged-to-cine magnetic resonance imaging (MRI) synthesis problem, where datasets in the source and target domains were acquired from different scanners or centers. Extensive validations were carried out to verify our framework against popular adversarial training UDA methods. Results show that our GST, with tagged MRI of test subjects in new target domains, improved the synthesis quality by a large margin, compared with the adversarial training UDA methods.
    • Law and technology when machine learning is facially invalid

      Pasquale, F. (Association for Computing Machinery, 2018)
    • Pathogen Identification Direct From Polymicrobial Specimens Using Membrane Glycolipids

      Fondrie, W.E.; Liang, T.; Oyler, B.L. (Nature Publishing Group, 2018)
      With the increased prevalence of multidrug-resistant Gram-negative bacteria, the use of colistin and other last-line antimicrobials is being revisited clinically. As a result, there has been an emergence of colistin-resistant bacterial species, including Acinetobacter baumannii and Klebsiella pneumoniae. The rapid identification of such pathogens is vitally important for the effective treatment of patients. We previously demonstrated that mass spectrometry of bacterial glycolipids has the capacity to identify and detect colistin resistance in a variety of bacterial species. In this study, we present a machine learning paradigm that is capable of identifying A. baumannii, K. pneumoniae and their colistin-resistant forms using a manually curated dataset of lipid mass spectra from 48 additional Gram-positive and -negative organisms. We demonstrate that these classifiers detect A. baumannii and K. pneumoniae in isolate and polymicrobial specimens, establishing a framework to translate glycolipid mass spectra into pathogen identifications. Copyright 2018, The Author(s).