Natural language processing system for rapid detection and intervention of mental health crisis chat messages.

Patients experiencing mental health crises often seek help through messaging-based platforms, but may face long wait times due to limited message triage capacity. Here we build and deploy a machine-learning-enabled system to improve response times to crisis messages in a large, national telehealth provider network. We train a two-stage natural language processing (NLP) system with key word filtering followed by logistic regression on 721 electronic medical record chat messages, of which 32% are potential crises (suicidal/homicidal ideation, domestic violence, or non-suicidal self-injury). Model performance is evaluated on a retrospective test set (4/1/21-4/1/22, N = 481) and a prospective test set (10/1/22-10/31/22, N = 102,471). In the retrospective test set, the model has an AUC of 0.82 (95% CI: 0.78-0.86), sensitivity of 0.99 (95% CI: 0.96-1.00), and PPV of 0.35 (95% CI: 0.309-0.4). In the prospective test set, the model has an AUC of 0.98 (95% CI: 0.966-0.984), sensitivity of 0.98 (95% CI: 0.96-0.99), and PPV of 0.66 (95% CI: 0.626-0.692). The daily median time from message receipt to crisis specialist triage ranges from 8 to 13 min, compared to 9 h before the deployment of the system. We demonstrate that a NLP-based machine learning model can reliably identify potential crisis chat messages in a telehealth setting. Our system integrates into existing clinical workflows, suggesting that with appropriate training, humans can successfully leverage ML systems to facilitate triage of crisis messages.

Selective prediction for extracting unstructured clinical data.

OBJECTIVE: While there are currently approaches to handle unstructured clinical data, such as manual abstraction and structured proxy variables, these methods may be time-consuming, not scalable, and imprecise. This article aims to determine whether selective prediction, which gives a model the option to abstain from generating a prediction, can improve the accuracy and efficiency of unstructured clinical data abstraction. MATERIALS AND METHODS: We trained selective classifiers (logistic regression, random forest, support vector machine) to extract 5 variables from clinical notes: depression (n = 1563), glioblastoma (GBM, n = 659), rectal adenocarcinoma (DRA, n = 601), and abdominoperineal resection (APR, n = 601) and low anterior resection (LAR, n = 601) of adenocarcinoma. We varied the cost of false positives (FP), false negatives (FN), and abstained notes and measured total misclassification cost. RESULTS: The depression selective classifiers abstained on anywhere from 0% to 97% of notes, and the change in total misclassification cost ranged from -58% to 9%. Selective classifiers abstained on 5%-43% of notes across the GBM and colorectal cancer models. The GBM selective classifier abstained on 43% of notes, which led to improvements in sensitivity (0.94 to 0.96), specificity (0.79 to 0.96), PPV (0.89 to 0.98), and NPV (0.88 to 0.91) when compared to a non-selective classifier and when compared to structured proxy variables. DISCUSSION: We showed that selective classifiers outperformed both non-selective classifiers and structured proxy variables for extracting data from unstructured clinical notes. CONCLUSION: Selective prediction should be considered when abstaining is preferable to making an incorrect prediction.

Sp3 is essential for normal lung morphogenesis and cell cycle progression during mouse embryonic development.

Members of the Sp family of transcription factors regulate gene expression via binding GC boxes within promoter regions. Unlike Sp1, which stimulates transcription, the closely related Sp3 can either repress or activate gene expression and is required for perinatal survival in mice. Here, we use RNA-seq and cellular phenotyping to show how Sp3 regulates murine fetal cell differentiation and proliferation. Homozygous Sp3-/- mice were smaller than wild-type and Sp+/- littermates, died soon after birth and had abnormal lung morphogenesis. RNA-seq of Sp3-/- fetal lung mesenchymal cells identified alterations in extracellular matrix production, developmental signaling pathways and myofibroblast/lipofibroblast differentiation. The lungs of Sp3-/- mice contained multiple structural defects, with abnormal endothelial cell morphology, lack of elastic fiber formation, and accumulation of lipid droplets within mesenchymal lipofibroblasts. Sp3-/- cells and mice also displayed cell cycle arrest, with accumulation in G0/G1 and reduced expression of numerous cell cycle regulators including Ccne1. These data detail the global impact of Sp3 on in vivo mouse gene expression and development.

The Novel Omega-6 Fatty Acid Docosapentaenoic Acid Positively Modulates Brain Innate Immune Response for Resolving Neuroinflammation at Early and Late Stages of Humanized APOE-Based Alzheimer's Disease Models.

Neuroinflammation plays a crucial role in the development and progression of Alzheimer's disease (AD), in which activated microglia are found to be associated with neurodegeneration. However, there is limited evidence showing how neuroinflammation and activated microglia are directly linked to neurodegeneration in vivo. Besides, there are currently no effective anti-inflammatory drugs for AD. In this study, we report on an effective anti-inflammatory lipid, linoleic acid (LA) metabolite docosapentaenoic acid (DPAn-6) treatment of aged humanized EFAD mice with advanced AD pathology. We also report the associations of neuroinflammatory and/or activated microglial markers with neurodegeneration in vivo. First, we found that dietary LA reduced proinflammatory cytokines of IL1-ß, IL-6, as well as mRNA expression of COX2 toward resolving neuroinflammation with an increase of IL-10 in adult AD models E3FAD and E4FAD mice. Brain fatty acid assays showed a five to six-fold increase in DPAn-6 by dietary LA, especially more in E4FAD mice, when compared to standard diet. Thus, we tested DPAn-6 in aged E4FAD mice. After DPAn-6 was administered to the E4FAD mice by oral gavage for three weeks, we found that DPAn-6 reduced microgliosis and mRNA expressions of inflammatory, microglial, and caspase markers. Further, DPAn-6 increased mRNA expressions of ADCYAP1, VGF, and neuronal pentraxin 2 in parallel, all of which were inversely correlated with inflammatory and microglial markers. Finally, both LA and DPAn-6 directly reduced mRNA expression of COX2 in amyloid-beta42 oligomer-challenged BV2 microglial cells. Together, these data indicated that DPAn-6 modulated neuroinflammatory responses toward resolution and improvement of neurodegeneration in the late stages of AD models.