Identifying Medication-Related Intents From a Bidirectional Text Messaging Platform for Hypertension Management Using an Unsupervised Learning Approach: Retrospective Observational Pilot Study.

BACKGROUND: Free-text communication between patients and providers plays an increasing role in chronic disease management, through platforms varying from traditional health care portals to novel mobile messaging apps. These text data are rich resources for clinical purposes, but their sheer volume render them difficult to manage. Even automated approaches, such as natural language processing, require labor-intensive manual classification for developing training data sets. Automated approaches to organizing free-text data are necessary to facilitate use of free-text communication for clinical care. OBJECTIVE: The aim of this study was to apply unsupervised learning approaches to (1) understand the types of topics discussed and (2) learn medication-related intents from messages sent between patients and providers through a bidirectional text messaging system for managing participant blood pressure (BP). METHODS: This study was a secondary analysis of deidentified messages from a remote, mobile, text-based employee hypertension management program at an academic institution. We trained a latent Dirichlet allocation (LDA) model for each message type (ie, inbound patient messages and outbound provider messages) and identified the distribution of major topics and significant topics (probability >.20) across message types. Next, we annotated all medication-related messages with a single medication intent. Then, we trained a second medication-specific LDA (medLDA) model to assess how well the unsupervised method could identify more fine-grained medication intents. We encoded each medication message with n-grams (n=1-3 words) using spaCy, clinical named entities using Stanza, and medication categories using MedEx; we then applied chi-square feature selection to learn the most informative features associated with each medication intent. RESULTS: In total, 253 participants and 5 providers engaged in the program, generating 12,131 total messages: 46.90% (n=5689) patient messages and 53.10% (n=6442) provider messages. Most patient messages corresponded to BP reporting, BP encouragement, and appointment scheduling; most provider messages corresponded to BP reporting, medication adherence, and confirmatory statements. Most patient and provider messages contained 1 topic and few contained more than 3 topics identified using LDA. In total, 534 medication messages were annotated with a single medication intent. Of these, 282 (52.8%) were patient medication messages: most referred to the medication request intent (n=134, 47.5%). Most of the 252 (47.2%) provider medication messages referred to the medication question intent (n=173, 68.7%). Although the medLDA model could identify a majority intent within each topic, it could not distinguish medication intents with low prevalence within patient or provider messages. Richer feature engineering identified informative lexical-semantic patterns associated with each medication intent class. CONCLUSIONS: LDA can be an effective method for generating subgroups of messages with similar term usage and facilitating the review of topics to inform annotations. However, few training cases and shared vocabulary between intents precludes the use of LDA for fully automated, deep, medication intent classification. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR2-10.1101/2021.12.23.21268061.

Locally Informed Simulation to Predict Hospital Capacity Needs During the COVID-19 Pandemic.

BACKGROUND: The coronavirus disease 2019 (COVID-19) pandemic challenges hospital leaders to make time-sensitive, critical decisions about clinical operations and resource allocations. OBJECTIVE: To estimate the timing of surges in clinical demand and the best- and worst-case scenarios of local COVID-19-induced strain on hospital capacity, and thus inform clinical operations and staffing demands and identify when hospital capacity would be saturated. DESIGN: Monte Carlo simulation instantiation of a susceptible, infected, removed (SIR) model with a 1-day cycle. SETTING: 3 hospitals in an academic health system. PATIENTS: All people living in the greater Philadelphia region. MEASUREMENTS: The COVID-19 Hospital Impact Model (CHIME) (http://penn-chime.phl.io) SIR model was used to estimate the time from 23 March 2020 until hospital capacity would probably be exceeded, and the intensity of the surge, including for intensive care unit (ICU) beds and ventilators. RESULTS: Using patients with COVID-19 alone, CHIME estimated that it would be 31 to 53 days before demand exceeds existing hospital capacity. In best- and worst-case scenarios of surges in the number of patients with COVID-19, the needed total capacity for hospital beds would reach 3131 to 12 650 across the 3 hospitals, including 338 to 1608 ICU beds and 118 to 599 ventilators. LIMITATIONS: Model parameters were taken directly or derived from published data across heterogeneous populations and practice environments and from the health system's historical data. CHIME does not incorporate more transition states to model infection severity, social networks to model transmission dynamics, or geographic information to account for spatial patterns of human interaction. CONCLUSION: Publicly available and designed for hospital operations leaders, this modeling tool can inform preparations for capacity strain during the early days of a pandemic. PRIMARY FUNDING SOURCE: University of Pennsylvania Health System and the Palliative and Advanced Illness Research Center.

Improving Identification of Patients at Low Risk for Major Cardiac Events After Noncardiac Surgery Using Intraoperative Data.

BACKGROUND/OBJECTIVE: Risk-stratification tools for cardiac complications after noncardiac surgery based on preoperative risk factors are used to inform postoperative management. However, there is limited evidence on whether risk stratification can be improved by incorporating data collected intraoperatively, particularly for low-risk patients. METHODS: We conducted a retrospective cohort study of adults who underwent noncardiac surgery between 2014 and 2018 at four hospitals in the United States. Logistic regression with elastic net selection was used to classify in-hospital major adverse cardiovascular events (MACE) using preoperative and intraoperative data ("perioperative model"). We compared model performance to standard risk stratification tools and professional society guidelines that do not use intraoperative data. RESULTS: Of 72,909 patients, 558 (0.77%) experienced MACE. Those with MACE were older and less likely to be female. The perioperative model demonstrated an area under the receiver operating characteristic curve (AUC) of 0.88 (95% CI, 0.85-0.92). This was higher than the Lee Revised Cardiac Risk Index (RCRI) AUC of 0.79 (95% CI, 0.74-0.84; P < .001 for AUC comparison). There were more MACE complications in the top decile (n = 1,465) of the perioperative model's predicted risk compared with that of the RCRI model (n = 58 vs 43). Additionally, the perioperative model identified 2,341 of 7,597 (31%) patients as low risk who did not experience MACE but were recommended to receive postoperative biomarker testing by a risk factor-based guideline algorithm. CONCLUSIONS: Addition of intraoperative data to preoperative data improved prediction of cardiovascular complication outcomes after noncardiac surgery and could potentially help reduce unnecessary postoperative testing.

Risk Stratification for Postoperative Acute Kidney Injury in Major Noncardiac Surgery Using Preoperative and Intraoperative Data.

Importance: Acute kidney injury (AKI) is one of the most common complications after noncardiac surgery. Yet current postoperative AKI risk stratification models have substantial limitations, such as limited use of perioperative data. Objective: To examine whether adding preoperative and intraoperative data is associated with improved prediction of noncardiac postoperative AKI. Design, Setting, and Participants: A prognostic study using logistic regression with elastic net selection, gradient boosting machine (GBM), and random forest approaches was conducted at 4 tertiary academic hospitals in the United States. A total of 42 615 hospitalized adults with serum creatinine measurements who underwent major noncardiac surgery between January 1, 2014, and April 30, 2018, were included in the study. Serum creatinine measurements from 365 days before and 7 days after surgery were used in this study. Main Outcomes and Measures: Postoperative AKI (defined by the Kidney Disease Improving Global Outcomes within 7 days after surgery) was the primary outcome. The area under the receiver operating characteristic curve (AUC) was used to assess discrimination. Results: Among 42 615 patients who underwent noncardiac surgery, the mean (SD) age was 57.9 (15.7) years, 23 943 (56.2%) were women, 27 857 (65.4%) were white, and the most frequent surgery types were orthopedic (15 718 [36.9%]), general (8808 [20.7%]), and neurologic (6564 [15.4%]). The rate of postoperative AKI was 10.1% (n = 4318). The progressive addition of clinical data improved model performance across all modeling approaches, with GBM providing the highest discrimination by AUC. In GBM models, the AUC increased from 0.712 (95% CI, 0.694-0.731) using prehospitalization variables to 0.804 (95% CI, 0.788-0.819) using preoperative variables (inclusive of prehospitalization variables) (P < .001 for AUC comparison). The AUC further increased to 0.817 (95% CI, 0.802-0.832) when adding intraoperative variables (P < .001 for comparison vs model using preoperative variables). However, the statistically significant improvements in discrimination did not appear to be clinically significant. In particular, the AKI rate among patients classified as high risk improved from 29.1% to 30.0%, a net of 15 patients were appropriately reclassified as high risk, and an additional 15 patients were appropriately reclassified as low risk. Conclusions and Relevance: The findings of the study suggest that electronic health record data may be used to accurately stratify patients at risk of perioperative AKI, but the modest improvements from adding intraoperative data should be weighed against challenges in using intraoperative data.

Model Performance Metrics in Assessing the Value of Adding Intraoperative Data for Death Prediction: Applications to Noncardiac Surgery.

We tested the value of adding data from the operating room to models predicting in-hospital death. We assessed model performance using two metrics, the area under the receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (AUPRC), to illustrate the differences in information they convey in the setting of class imbalance. Data was collected on 74,147 patients who underwent major noncardiac surgery and 112 unique features were extracted from electronic health records. Sets of features were incrementally added to models using logistic regression, naïve Bayes, random forest, and gradient boosted machine methods. AUROC increased as more features were added, but changes were small for some modeling approaches. In contrast, AUPRC, which reflects positive predicted value, exhibited improvements across all models. Using AUPRC highlighted the added value of intraoperative data, not seen consistently with AUROC, and that with class imbalance AUPRC may serve as the more clinically relevant criterion.

Mining images in biomedical publications: Detection and analysis of gel diagrams.

Authors of biomedical publications use gel images to report experimental results such as protein-protein interactions or protein expressions under different conditions. Gel images offer a concise way to communicate such findings, not all of which need to be explicitly discussed in the article text. This fact together with the abundance of gel images and their shared common patterns makes them prime candidates for automated image mining and parsing. We introduce an approach for the detection of gel images, and present a workflow to analyze them. We are able to detect gel segments and panels at high accuracy, and present preliminary results for the identification of gene names in these images. While we cannot provide a complete solution at this point, we present evidence that this kind of image mining is feasible.

Finding and accessing diagrams in biomedical publications.

Complex relationships in biomedical publications are often communicated by diagrams such as bar and line charts, which are a very effective way of summarizing and communicating multi-faceted data sets. Given the ever-increasing amount of published data, we argue that the precise retrieval of such diagrams is of great value for answering specific and otherwise hard-to-meet information needs. To this end, we demonstrate the use of advanced image processing and classification for identifying bar and line charts by the shape and relative location of the different image elements that make up the charts. With recall and precisions of close to 90% for the detection of relevant figures, we discuss the use of this technology in an existing biomedical image search engine, and outline how it enables new forms of literature queries over biomedical relationships that are represented in these charts.

Introducing meta-services for biomedical information extraction.

We introduce the first meta-service for information extraction in molecular biology, the BioCreative MetaServer (BCMS; http://bcms.bioinfo.cnio.es/). This prototype platform is a joint effort of 13 research groups and provides automatically generated annotations for PubMed/Medline abstracts. Annotation types cover gene names, gene IDs, species, and protein-protein interactions. The annotations are distributed by the meta-server in both human and machine readable formats (HTML/XML). This service is intended to be used by biomedical researchers and database annotators, and in biomedical language processing. The platform allows direct comparison, unified access, and result aggregation of the annotations.

Mapping terms to UMLS concepts of the same semantic type.

We are interested in mapping terms from the biomedical literature to controlled terminologies. For clinical and related terms, we rely on the MetaMap program for mapping terms to the UMLS Metathesaurus, accepting term assignments that have a reasonable match score. In a sizable number of cases, terms are ambiguous, and MetaMap proposes several mapping candidates. To address these cases prior studies investigated Word Sense Disambiguation (WSD) strategies for selecting between concepts of different semantic types. Here, we investigated the situation where MetaMap proposes concepts that share the same semantic type. We present an ontology-based strategy for selecting between these concepts.

Minimotif Miner: a tool for investigating protein function.

In addition to large domains, many short motifs mediate functional post-translational modification of proteins as well as protein-protein interactions and protein trafficking functions. We have constructed a motif database comprising 312 unique motifs and a web-based tool for identifying motifs in proteins. Functional motifs predicted by MnM can be ranked by several approaches, and we validated these scores by analyzing thousands of confirmed examples and by confirming prediction of previously unidentified 14-3-3 motifs in EFF-1.