Classifying Social Determinants of Health from Unstructured Electronic Health Records Using Deep Learning-based Natural Language Processing

Extracting Housing and Food Insecurity Information From Clinical Notes Using cTAKES

OBJECTIVE

To assess the utility and challenges of using natural language processing (NLP) in electronic health records (EHRs) to ascertain health-related social needs (HRSNs) among older adults.

STUDY SETTING AND DESIGN

We extracted HRSN information using the NLP system Clinical Text Analysis and Knowledge Extraction System (cTAKES), combined with Concept Unique Identifiers and Systematized Nomenclature for Medicine codes. We validated cTAKES performance, via manual chart review, on two HRSNs: food insecurity, which was included in the healthcare system's HRSN screening tool, and housing insecurity, which was not.

DATA SOURCES AND ANALYTIC SAMPLE

De-identified EHRs in a large California healthcare system (January 2013 through October 2022) from 119,127 patients aged 55+ in primary and emergency care settings (n = 1,385,259 clinical notes).

PRINCIPAL FINDINGS

Although cTAKES had a moderate positive predictive value (77.5%) for housing insecurity, housing challenges among older adults frequently did not align with the concepts the algorithm recognized. cTAKES performed poorly for food insecurity (positive predictive value: 18.5%) because this NLP system incorrectly flagged structured fields from the screening tool.

CONCLUSION

Unstandardized terminology and poor integration of HRSN screeners in EHR remain important barriers to identifying older adults' food and housing insecurity using cTAKES.

Racial Disparities in Perioperative Outcomes for Patients With Head and Neck Cancer

OBJECTIVE

To characterize the perioperative complications after ablative and reconstructive surgery in patients with head and neck cancer (HNC) based on race.

METHODS

We conducted a retrospective study of the 2015-2020 National Surgical Quality Improvement Program Database. We compared the perioperative outcomes between White, Asian, Black, Native Hawaiian or Pacific Islander, and American Indian or Alaskan Native patients with bivariate analysis. Multivariate logistic regression assessed the independent association of race with perioperative complications.

RESULTS

Black patients experienced longer surgeries (aβ, 43; 95% CI, 33, 53), longer hospital stays (aβ, 1.6 [95% CI, 1.1-2.1]), and were less likely to be discharged home (aOR, 0.64; [95% CI, 0.54, 0.76]). Black patients also had higher major complications risk (aOR, 1.38; [95% CI, 1.13-1.67]) with the most common being reintubation/ventilation (Black, 4.4% vs. White 2.7%; p = 0.003) and sepsis/septic shock (Black, 3.4% vs. White 1.8%; p = < 0.001). Black patients had higher reoperation rates (aOR, 1.33; [95% CI, 1.12-1.56]) with incision and drainage of abscess and hematoma, exploration of postoperative hemorrhage, thrombosis or infection, or surgical debridement being the top reasons for reoperation. Concordantly, they were at higher risk of postoperative transfusion (Black, 18%; White, 7.2%; p = < 0.001) and wound dehiscence (Black, 4.1%; White, 2.1%; p = < 0.001).

CONCLUSION

There is evidence of racial disparities in HNC surgery perioperatively. Black patients face an increased risk of major complications, reoperation, extended hospital stay, and non-home discharge. Developing a comprehensive surgical database with more social determinants of health variables and using a socioecological framework of health can help us identify contributors to these disparities and design high-leverage solutions.

Natural Language Processing Application in Nursing Research: A Study Using Text Network Analysis and Topic Modeling

Although the potential of natural language processing and an increase in its application in nursing research is evident, there is a lack of understanding of the research trends. This study conducts text network analysis and topic modeling to uncover the underlying knowledge structures, research trends, and emergent research themes within nursing literature related to natural language processing. In addition, this study aims to provide a foundation for future scholarly inquiries and enhance the integration of natural language processing in the analysis of nursing research. We analyzed 443 literature abstracts and performed core keyword analysis and topic modeling based on frequency and centrality. The following topics emerged: (1) Term Identification and Communication; (2) Application of Machine Learning; (3) Exploration of Health Outcome Factors; (4) Intervention and Participant Experience; and (5) Disease-Related Algorithms. Nursing meta-paradigm elements were identified within the core keyword analysis, which led to understanding and expanding the meta-paradigm. Although still in its infancy in nursing research with limited topics and research volumes, natural language processing can potentially enhance research efficiency and nursing quality. The findings emphasize the possibility of integrating natural language processing in nursing-related subjects, validating nursing value, and fostering the exploration of essential paradigms in nursing science.

Using Large Language Models to Abstract Complex Social Determinants of Health From Original and Deidentified Medical Notes: Development and Validation Study

BACKGROUND

Social determinants of health (SDoH) such as housing insecurity are known to be intricately linked to patients' health status. More efficient methods for abstracting structured data on SDoH can help accelerate the inclusion of exposome variables in biomedical research and support health care systems in identifying patients who could benefit from proactive outreach. Large language models (LLMs) developed from Generative Pre-trained Transformers (GPTs) have shown potential for performing complex abstraction tasks on unstructured clinical notes.

OBJECTIVE

Here, we assess the performance of GPTs on identifying temporal aspects of housing insecurity and compare results between both original and deidentified notes.

METHODS

We compared the ability of GPT-3.5 and GPT-4 to identify instances of both current and past housing instability, as well as general housing status, from 25,217 notes from 795 pregnant women. Results were compared with manual abstraction, a named entity recognition model, and regular expressions.

RESULTS

Compared with GPT-3.5 and the named entity recognition model, GPT-4 had the highest performance and had a much higher recall (0.924) than human abstractors (0.702) in identifying patients experiencing current or past housing instability, although precision was lower (0.850) compared with human abstractors (0.971). GPT-4's precision improved slightly (0.936 original, 0.939 deidentified) on deidentified versions of the same notes, while recall dropped (0.781 original, 0.704 deidentified).

CONCLUSIONS

This work demonstrates that while manual abstraction is likely to yield slightly more accurate results overall, LLMs can provide a scalable, cost-effective solution with the advantage of greater recall. This could support semiautomated abstraction, but given the potential risk for harm, human review would be essential before using results for any patient engagement or care decisions. Furthermore, recall was lower when notes were deidentified prior to LLM abstraction.

Realizing the potential of social determinants data in EHR systems: A scoping review of approaches for screening, linkage, extraction, analysis, and interventions

Background

Social determinants of health (SDoH), such as socioeconomics and neighborhoods, strongly influence health outcomes. However, the current state of standardized SDoH data in electronic health records (EHRs) is lacking, a significant barrier to research and care quality.

Methods

We conducted a PubMed search using "SDOH" and "EHR" Medical Subject Headings terms, analyzing included articles across five domains: 1) SDoH screening and assessment approaches, 2) SDoH data collection and documentation, 3) Use of natural language processing (NLP) for extracting SDoH, 4) SDoH data and health outcomes, and 5) SDoH-driven interventions.

Results

Of 685 articles identified, 324 underwent full review. Key findings include implementation of tailored screening instruments, census and claims data linkage for contextual SDoH profiles, NLP systems extracting SDoH from notes, associations between SDoH and healthcare utilization and chronic disease control, and integrated care management programs. However, variability across data sources, tools, and outcomes underscores the need for standardization.

Discussion

Despite progress in identifying patient social needs, further development of standards, predictive models, and coordinated interventions is critical for SDoH-EHR integration. Additional database searches could strengthen this scoping review. Ultimately, widespread capture, analysis, and translation of multidimensional SDoH data into clinical care is essential for promoting health equity.

Use of SNOMED CT in Large Language Models: Scoping Review

BACKGROUND

Large language models (LLMs) have substantially advanced natural language processing (NLP) capabilities but often struggle with knowledge-driven tasks in specialized domains such as biomedicine. Integrating biomedical knowledge sources such as SNOMED CT into LLMs may enhance their performance on biomedical tasks. However, the methodologies and effectiveness of incorporating SNOMED CT into LLMs have not been systematically reviewed.

OBJECTIVE

This scoping review aims to examine how SNOMED CT is integrated into LLMs, focusing on (1) the types and components of LLMs being integrated with SNOMED CT, (2) which contents of SNOMED CT are being integrated, and (3) whether this integration improves LLM performance on NLP tasks.

METHODS

Following the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines, we searched ACM Digital Library, ACL Anthology, IEEE Xplore, PubMed, and Embase for relevant studies published from 2018 to 2023. Studies were included if they incorporated SNOMED CT into LLM pipelines for natural language understanding or generation tasks. Data on LLM types, SNOMED CT integration methods, end tasks, and performance metrics were extracted and synthesized.

RESULTS

The review included 37 studies. Bidirectional Encoder Representations from Transformers and its biomedical variants were the most commonly used LLMs. Three main approaches for integrating SNOMED CT were identified: (1) incorporating SNOMED CT into LLM inputs (28/37, 76%), primarily using concept descriptions to expand training corpora; (2) integrating SNOMED CT into additional fusion modules (5/37, 14%); and (3) using SNOMED CT as an external knowledge retriever during inference (5/37, 14%). The most frequent end task was medical concept normalization (15/37, 41%), followed by entity extraction or typing and classification. While most studies (17/19, 89%) reported performance improvements after SNOMED CT integration, only a small fraction (19/37, 51%) provided direct comparisons. The reported gains varied widely across different metrics and tasks, ranging from 0.87% to 131.66%. However, some studies showed either no improvement or a decline in certain performance metrics.

CONCLUSIONS

This review demonstrates diverse approaches for integrating SNOMED CT into LLMs, with a focus on using concept descriptions to enhance biomedical language understanding and generation. While the results suggest potential benefits of SNOMED CT integration, the lack of standardized evaluation methods and comprehensive performance reporting hinders definitive conclusions about its effectiveness. Future research should prioritize consistent reporting of performance comparisons and explore more sophisticated methods for incorporating SNOMED CT's relational structure into LLMs. In addition, the biomedical NLP community should develop standardized evaluation frameworks to better assess the impact of ontology integration on LLM performance.

On the development and validation of large language model-based classifiers for identifying social determinants of health

The assessment of social determinants of health (SDoH) within healthcare systems is crucial for comprehensive patient care and addressing health disparities. Current challenges arise from the limited inclusion of structured SDoH information within electronic health record (EHR) systems, often due to the lack of standardized diagnosis codes. This study delves into the transformative potential of large language models (LLM) to overcome these challenges. LLM-based classifiers-using Bidirectional Encoder Representations from Transformers (BERT) and A Robustly Optimized BERT Pretraining Approach (RoBERTa)-were developed for SDoH concepts, including homelessness, food insecurity, and domestic violence, using synthetic training datasets generated by generative pre-trained transformers combined with authentic clinical notes. Models were then validated on separate datasets: Medical Information Mart for Intensive Care-III and our institutional EHR data. When training the model with a combination of synthetic and authentic notes, validation on our institutional dataset yielded an area under the receiver operating characteristics curve of 0.78 for detecting homelessness, 0.72 for detecting food insecurity, and 0.83 for detecting domestic violence. This study underscores the potential of LLMs in extracting SDoH information from clinical text. Automated detection of SDoH may be instrumental for healthcare providers in identifying at-risk patients, guiding targeted interventions, and contributing to population health initiatives aimed at mitigating disparities.

Social Determinants of Health and Diabetes in Pregnancy

Social determinants of health (SDOH) are the conditions in which people are born, grow, work, live, and age. SDOH are systemic factors that may explain, perpetuate, and exacerbate disparities in health outcomes for different populations and can be measured at both an individual and neighborhood or community level (iSDOH, nSDOH). In pregnancy, increasing evidence shows that adverse iSDOH and/or nSDOH are associated with a greater likelihood that diabetes develops, and that when it develops, there is worse glycemic control and a greater frequency of adverse pregnancy outcomes. Future research should not only continue to examine the relationships between SDOH and adverse pregnancy outcomes with diabetes but should determine whether multi-level interventions that seek to mitigate adverse SDOH result in equitable maternal care and improved patient health outcomes for pregnant individuals living with diabetes. KEY POINTS: · SDOH are conditions in which people are born, grow, work, live, and age.. · SDOH are systemic factors that may explain, perpetuate, and exacerbate disparities in health outcomes.. · SDOH can be measured at the individual and neighborhood level.. · Adverse SDOH are associated with worse outcomes for pregnant individuals living with diabetes.. · Interventions that mitigate adverse SDOH to improve maternal health equity and outcomes are needed..

Improving Clinical Decision Making With a Two-Stage Recommender System

Clinical decision-making is complex and time-intensive. To help in this effort, clinical recommender systems (RS) have been designed to facilitate healthcare practitioners with personalized advice. However, designing an effective clinical RS poses challenges due to the multifaceted nature of clinical data and the demand for tailored recommendations. In this article, we introduce a 2-Stage Recommendation framework for clinical decision-making, which leverages a publicly accessible dataset of electronic health records. In the first stage, a deep neural network-based model is employed to extract a set of candidate items, such as diagnoses, medications, and prescriptions, from a patient's electronic health records. Subsequently, the second stage utilizes a deep learning model to rank and pinpoint the most relevant items for healthcare providers. Both retriever and ranker are based on pre-trained transformer models that are stacked together as a pipeline. To validate our model, we compared its performance against several baseline models using different evaluation metrics. The results reveal that our proposed model attains a performance gain of approximately 12.3% macro-average F1 compared to the second best performing baseline. Qualitative analysis across various dimensions also confirms the model's high performance. Furthermore, we discuss challenges like data availability, privacy concerns, and shed light on future exploration in this domain.

Large language models in psychiatry: Opportunities and challenges

The ability of Large Language Models (LLMs) to analyze and respond to freely written text is causing increasing excitement in the field of psychiatry; the application of such models presents unique opportunities and challenges for psychiatric applications. This review article seeks to offer a comprehensive overview of LLMs in psychiatry, their model architecture, potential use cases, and clinical considerations. LLM frameworks such as ChatGPT/GPT-4 are trained on huge amounts of text data that are sometimes fine-tuned for specific tasks. This opens up a wide range of possible psychiatric applications, such as accurately predicting individual patient risk factors for specific disorders, engaging in therapeutic intervention, and analyzing therapeutic material, to name a few. However, adoption in the psychiatric setting presents many challenges, including inherent limitations and biases in LLMs, concerns about explainability and privacy, and the potential damage resulting from produced misinformation. This review covers potential opportunities and limitations and highlights potential considerations when these models are applied in a real-world psychiatric context.

Developing an individualized treatment rule for Veterans with major depressive disorder using electronic health records

Efforts to develop an individualized treatment rule (ITR) to optimize major depressive disorder (MDD) treatment with antidepressant medication (ADM), psychotherapy, or combined ADM-psychotherapy have been hampered by small samples, small predictor sets, and suboptimal analysis methods. Analyses of large administrative databases designed to approximate experiments followed iteratively by pragmatic trials hold promise for resolving these problems. The current report presents a proof-of-concept study using electronic health records (EHR) of n = 43,470 outpatients beginning MDD treatment in Veterans Health Administration Primary Care Mental Health Integration (PC-MHI) clinics, which offer access not only to ADMs but also psychotherapy and combined ADM-psychotherapy. EHR and geospatial databases were used to generate an extensive baseline predictor set (5,865 variables). The outcome was a composite measure of at least one serious negative event (suicide attempt, psychiatric emergency department visit, psychiatric hospitalization, suicide death) over the next 12 months. Best-practices methods were used to adjust for nonrandom treatment assignment and to estimate a preliminary ITR in a 70% training sample and to evaluate the ITR in the 30% test sample. Statistically significant aggregate variation was found in overall probability of the outcome related to baseline predictors (AU-ROC = 0.68, S.E. = 0.01), with test sample outcome prevalence of 32.6% among the 5% of patients having highest predicted risk compared to 7.1% in the remainder of the test sample. The ITR found that psychotherapy-only was the optimal treatment for 56.0% of patients (roughly 20% lower risk of the outcome than if receiving one of the other treatments) and that treatment type was unrelated to outcome risk among other patients. Change in aggregate treatment costs of implementing this ITR would be negligible, as 16.1% fewer patients would be prescribed ADMs and 2.9% more would receive psychotherapy. A pragmatic trial would be needed to confirm the accuracy of the ITR.

Question-based computational language approach outperforms rating scales in quantifying emotional states

Psychological constructs are commonly quantified with closed-ended rating scales. However, recent advancements in natural language processing (NLP) enable the quantification of open-ended language responses. Here we demonstrate that descriptive word responses analyzed using NLP show higher accuracy in categorizing emotional states compared to traditional rating scales. One group of participants (N = 297) generated narratives related to depression, anxiety, satisfaction, or harmony, summarized them with five descriptive words, and rated them using rating scales. Another group (N = 434) evaluated these narratives (with descriptive words and rating scales) from the author's perspective. The descriptive words were quantified using NLP, and machine learning was used to categorize the responses into the corresponding emotional states. The results showed a significantly higher number of accurate categorizations of the narratives based on descriptive words (64%) than on rating scales (44%), questioning the notion that rating scales are more precise in measuring emotional states than language-based measures.

Large Language Models for Social Determinants of Health Information Extraction from Clinical Notes - A Generalizable Approach across Institutions

The consistent and persuasive evidence illustrating the influence of social determinants on health has prompted a growing realization throughout the health care sector that enhancing health and health equity will likely depend, at least to some extent, on addressing detrimental social determinants. However, detailed social determinants of health (SDoH) information is often buried within clinical narrative text in electronic health records (EHRs), necessitating natural language processing (NLP) methods to automatically extract these details. Most current NLP efforts for SDoH extraction have been limited, investigating on limited types of SDoH elements, deriving data from a single institution, focusing on specific patient cohorts or note types, with reduced focus on generalizability. This study aims to address these issues by creating cross-institutional corpora spanning different note types and healthcare systems, and developing and evaluating the generalizability of classification models, including novel large language models (LLMs), for detecting SDoH factors from diverse types of notes from four institutions: Harris County Psychiatric Center, University of Texas Physician Practice, Beth Israel Deaconess Medical Center, and Mayo Clinic. Four corpora of deidentified clinical notes were annotated with 21 SDoH factors at two levels: level 1 with SDoH factor types only and level 2 with SDoH factors along with associated values. Three traditional classification algorithms (XGBoost, TextCNN, Sentence BERT) and an instruction tuned LLM-based approach (LLaMA) were developed to identify multiple SDoH factors. Substantial variation was noted in SDoH documentation practices and label distributions based on patient cohorts, note types, and hospitals. The LLM achieved top performance with micro-averaged F1 scores over 0.9 on level 1 annotated corpora and an F1 over 0.84 on level 2 annotated corpora. While models performed well when trained and tested on individual datasets, cross-dataset generalization highlighted remaining obstacles. To foster collaboration, access to partial annotated corpora and models trained by merging all annotated datasets will be made available on the PhysioNet repository.

Identifying social determinants of health from clinical narratives: A study of performance, documentation ratio, and potential bias

OBJECTIVE

To develop a natural language processing (NLP) package to extract social determinants of health (SDoH) from clinical narratives, examine the bias among race and gender groups, test the generalizability of extracting SDoH for different disease groups, and examine population-level extraction ratio.

METHODS

We developed SDoH corpora using clinical notes identified at the University of Florida (UF) Health. We systematically compared 7 transformer-based large language models (LLMs) and developed an open-source package - SODA (i.e., SOcial DeterminAnts) to facilitate SDoH extraction from clinical narratives. We examined the performance and potential bias of SODA for different race and gender groups, tested the generalizability of SODA using two disease domains including cancer and opioid use, and explored strategies for improvement. We applied SODA to extract 19 categories of SDoH from the breast (n = 7,971), lung (n = 11,804), and colorectal cancer (n = 6,240) cohorts to assess patient-level extraction ratio and examine the differences among race and gender groups.

RESULTS

We developed an SDoH corpus using 629 clinical notes of cancer patients with annotations of 13,193 SDoH concepts/attributes from 19 categories of SDoH, and another cross-disease validation corpus using 200 notes from opioid use patients with 4,342 SDoH concepts/attributes. We compared 7 transformer models and the GatorTron model achieved the best mean average strict/lenient F1 scores of 0.9122 and 0.9367 for SDoH concept extraction and 0.9584 and 0.9593 for linking attributes to SDoH concepts. There is a small performance gap (∼4%) between Males and Females, but a large performance gap (>16 %) among race groups. The performance dropped when we applied the cancer SDoH model to the opioid cohort; fine-tuning using a smaller opioid SDoH corpus improved the performance. The extraction ratio varied in the three cancer cohorts, in which 10 SDoH could be extracted from over 70 % of cancer patients, but 9 SDoH could be extracted from less than 70 % of cancer patients. Individuals from the White and Black groups have a higher extraction ratio than other minority race groups.

CONCLUSIONS

Our SODA package achieved good performance in extracting 19 categories of SDoH from clinical narratives. The SODA package with pre-trained transformer models is available at https://github.com/uf-hobi-informatics-lab/SODA_Docker.

Using Large Language Models to Annotate Complex Cases of Social Determinants of Health in Longitudinal Clinical Records

Social Determinants of Health (SDoH) are an important part of the exposome and are known to have a large impact on variation in health outcomes. In particular, housing stability is known to be intricately linked to a patient's health status, and pregnant women experiencing housing instability (HI) are known to have worse health outcomes. Most SDoH information is stored in electronic health records (EHRs) as free text (unstructured) clinical notes, which traditionally required natural language processing (NLP) for automatic identification of relevant text or keywords. A patient's housing status can be ambiguous or subjective, and can change from note to note or within the same note, making it difficult to use existing NLP solutions. New developments in NLP allow researchers to prompt LLMs to perform complex, subjective annotation tasks that require reasoning that previously could only be attempted by human annotators. For example, large language models (LLMs) such as GPT (Generative Pre-trained Transformer) enable researchers to analyze complex, unstructured data using simple prompts. We used a secure platform within a large healthcare system to compare the ability of GPT-3.5 and GPT-4 to identify instances of both current and past housing instability, as well as general housing status, from 25,217 notes from 795 pregnant women. Results from these LLMs were compared with results from manual annotation, a named entity recognition (NER) model, and regular expressions (RegEx). We developed a chain-of-thought prompt requiring evidence and justification for each note from the LLMs, to help maximize the chances of finding relevant text related to HI while minimizing hallucinations and false positives. Compared with GPT-3.5 and the NER model, GPT-4 had the highest performance and had a much higher recall (0.924) than human annotators (0.702) in identifying patients experiencing current or past housing instability, although precision was lower (0.850) compared with human annotators (0.971). In most cases, the evidence output by GPT-4 was similar or identical to that of human annotators, and there was no evidence of hallucinations in any of the outputs from GPT-4. Most cases where the annotators and GPT-4 differed were ambiguous or subjective, such as "living in an apartment with too many people". We also looked at GPT-4 performance on de-identified versions of the same notes and found that precision improved slightly (0.936 original, 0.939 de-identified), while recall dropped (0.781 original, 0.704 de-identified). This work demonstrates that, while manual annotation is likely to yield slightly more accurate results overall, LLMs, when compared with manual annotation, provide a scalable, cost-effective solution with the advantage of greater recall. At the same time, further evaluation is needed to address the risk of missed cases and bias in the initial selection of housing-related notes. Additionally, while it was possible to reduce confabulation, signs of unusual justifications remained. Given these factors, together with changes in both LLMs and charting over time, this approach is not yet appropriate for use as a fully-automated process. However, these results demonstrate the potential for using LLMs for computer-assisted annotation with human review, reducing cost and increasing recall. More efficient methods for obtaining structured SDoH data can help accelerate inclusion of exposome variables in biomedical research, and support healthcare systems in identifying patients who could benefit from proactive outreach.

Question-answering system extracts information on injection drug use from clinical notes

BACKGROUND

Injection drug use (IDU) can increase mortality and morbidity. Therefore, identifying IDU early and initiating harm reduction interventions can benefit individuals at risk. However, extracting IDU behaviors from patients' electronic health records (EHR) is difficult because there is no other structured data available, such as International Classification of Disease (ICD) codes, and IDU is most often documented in unstructured free-text clinical notes. Although natural language processing can efficiently extract this information from unstructured data, there are no validated tools.

METHODS

To address this gap in clinical information, we design a question-answering (QA) framework to extract information on IDU from clinical notes for use in clinical operations. Our framework involves two main steps: (1) generating a gold-standard QA dataset and (2) developing and testing the QA model. We use 2323 clinical notes of 1145 patients curated from the US Department of Veterans Affairs (VA) Corporate Data Warehouse to construct the gold-standard dataset for developing and evaluating the QA model. We also demonstrate the QA model's ability to extract IDU-related information from temporally out-of-distribution data.

RESULTS

Here, we show that for a strict match between gold-standard and predicted answers, the QA model achieves a 51.65% F1 score. For a relaxed match between the gold-standard and predicted answers, the QA model obtains a 78.03% F1 score, along with 85.38% Precision and 79.02% Recall scores. Moreover, the QA model demonstrates consistent performance when subjected to temporally out-of-distribution data.

CONCLUSIONS

Our study introduces a QA framework designed to extract IDU information from clinical notes, aiming to enhance the accurate and efficient detection of people who inject drugs, extract relevant information, and ultimately facilitate informed patient care.

Hierarchy of demographic and social determinants of mental health: analysis of cross-sectional survey data from the Global Mind Project

OBJECTIVES

To understand the extent to which various demographic and social determinants predict mental health status and their relative hierarchy of predictive power in order to prioritise and develop population-based preventative approaches.

DESIGN

Cross-sectional analysis of survey data.

SETTING

Internet-based survey from 32 countries across North America, Europe, Latin America, Middle East and North Africa, Sub-Saharan Africa, South Asia and Australia, collected between April 2020 and December 2021.

PARTICIPANTS

270 000 adults aged 18-85+ years who participated in the Global Mind Project.

OUTCOME MEASURES

We used 120+ demographic and social determinants to predict aggregate mental health status and scores of individuals (mental health quotient (MHQ)) and determine their relative predictive influence using various machine learning models including gradient boosting and random forest classification for various demographic stratifications by age, gender, geographical region and language. Outcomes reported include model performance metrics of accuracy, precision, recall, F1 scores and importance of individual factors determined by reduction in the squared error attributable to that factor.

RESULTS

Across all demographic classification models, 80% of those with negative MHQs were correctly identified, while regression models predicted specific MHQ scores within ±15% of the position on the scale. Predictions were higher for older ages (0.9+ accuracy, 0.9+ F1 Score; 65+ years) and poorer for younger ages (0.68 accuracy, 0.68 F1 Score; 18-24 years). Across all age groups, genders, regions and language groups, lack of social interaction and sufficient sleep were several times more important than all other factors. For younger ages (18-24 years), other highly predictive factors included cyberbullying and sexual abuse while not being able to work was high for ages 45-54 years.

CONCLUSION

Social determinants of traumas, adversities and lifestyle can account for 60%-90% of mental health challenges. However, additional factors are at play, particularly for younger ages, that are not included in these data and need further investigation.

Development of a Social Risk Score in the Electronic Health Record to Identify Social Needs Among Underserved Populations: Retrospective Study

BACKGROUND

Patients with unmet social needs and social determinants of health (SDOH) challenges continue to face a disproportionate risk of increased prevalence of disease, health care use, higher health care costs, and worse outcomes. Some existing predictive models have used the available data on social needs and SDOH challenges to predict health-related social needs or the need for various social service referrals. Despite these one-off efforts, the work to date suggests that many technical and organizational challenges must be surmounted before SDOH-integrated solutions can be implemented on an ongoing, wide-scale basis within most US-based health care organizations.

OBJECTIVE

We aimed to retrieve available information in the electronic health record (EHR) relevant to the identification of persons with social needs and to develop a social risk score for use within clinical practice to better identify patients at risk of having future social needs.

METHODS

We conducted a retrospective study using EHR data (2016-2021) and data from the US Census American Community Survey. We developed a prospective model using current year-1 risk factors to predict future year-2 outcomes within four 2-year cohorts. Predictors of interest included demographics, previous health care use, comorbidity, previously identified social needs, and neighborhood characteristics as reflected by the area deprivation index. The outcome variable was a binary indicator reflecting the likelihood of the presence of a patient with social needs. We applied a generalized estimating equation approach, adjusting for patient-level risk factors, the possible effect of geographically clustered data, and the effect of multiple visits for each patient.

RESULTS

The study population of 1,852,228 patients included middle-aged (mean age range 53.76-55.95 years), White (range 324,279/510,770, 63.49% to 290,688/488,666, 64.79%), and female (range 314,741/510,770, 61.62% to 278,488/448,666, 62.07%) patients from neighborhoods with high socioeconomic status (mean area deprivation index percentile range 28.76-30.31). Between 8.28% (37,137/448,666) and 11.55% (52,037/450,426) of patients across the study cohorts had at least 1 social need documented in their EHR, with safety issues and economic challenges (ie, financial resource strain, employment, and food insecurity) being the most common documented social needs (87,152/1,852,228, 4.71% and 58,242/1,852,228, 3.14% of overall patients, respectively). The model had an area under the curve of 0.702 (95% CI 0.699-0.705) in predicting prospective social needs in the overall study population. Previous social needs (odds ratio 3.285, 95% CI 3.237-3.335) and emergency department visits (odds ratio 1.659, 95% CI 1.634-1.684) were the strongest predictors of future social needs.

CONCLUSIONS

Our model provides an opportunity to make use of available EHR data to help identify patients with high social needs. Our proposed social risk score could help identify the subset of patients who would most benefit from further social needs screening and data collection to avoid potentially more burdensome primary data collection on all patients in a target population of interest.

Structured and unstructured social risk factor documentation in the electronic health record underestimates patients' self-reported risks

OBJECTIVES

National attention has focused on increasing clinicians' responsiveness to the social determinants of health, for example, food security. A key step toward designing responsive interventions includes ensuring that information about patients' social circumstances is captured in the electronic health record (EHR). While prior work has assessed levels of EHR "social risk" documentation, the extent to which documentation represents the true prevalence of social risk is unknown. While no gold standard exists to definitively characterize social risks in clinical populations, here we used the best available proxy: social risks reported by patient survey.

MATERIALS AND METHODS

We compared survey results to respondents' EHR social risk documentation (clinical free-text notes and International Statistical Classification of Diseases and Related Health Problems [ICD-10] codes).

RESULTS

Surveys indicated much higher rates of social risk (8.2%-40.9%) than found in structured (0%-2.0%) or unstructured (0%-0.2%) documentation.

DISCUSSION

Ideally, new care standards that include incentives to screen for social risk will increase the use of documentation tools and clinical teams' awareness of and interventions related to social adversity, while balancing potential screening and documentation burden on clinicians and patients.

CONCLUSION

EHR documentation of social risk factors currently underestimates their prevalence.

Realizing the Potential of Social Determinants Data: A Scoping Review of Approaches for Screening, Linkage, Extraction, Analysis and Interventions

Background

Social determinants of health (SDoH) like socioeconomics and neighborhoods strongly influence outcomes, yet standardized SDoH data is lacking in electronic health records (EHR), limiting research and care quality.

Methods

We searched PubMed using keywords "SDOH" and "EHR", underwent title/abstract and full-text screening. Included records were analyzed under five domains: 1) SDoH screening and assessment approaches, 2) SDoH data collection and documentation, 3) Use of natural language processing (NLP) for extracting SDoH, 4) SDoH data and health outcomes, and 5) SDoH-driven interventions.

Results

We identified 685 articles, of which 324 underwent full review. Key findings include tailored screening instruments implemented across settings, census and claims data linkage providing contextual SDoH profiles, rule-based and neural network systems extracting SDoH from notes using NLP, connections found between SDoH data and healthcare utilization/chronic disease control, and integrated care management programs executed. However, considerable variability persists across data sources, tools, and outcomes.

Discussion

Despite progress identifying patient social needs, further development of standards, predictive models, and coordinated interventions is critical to fulfill the potential of SDoH-EHR integration. Additional database searches could strengthen this scoping review. Ultimately widespread capture, analysis, and translation of multidimensional SDoH data into clinical care is essential for promoting health equity.

Large language models to identify social determinants of health in electronic health records

Social determinants of health (SDoH) play a critical role in patient outcomes, yet their documentation is often missing or incomplete in the structured data of electronic health records (EHRs). Large language models (LLMs) could enable high-throughput extraction of SDoH from the EHR to support research and clinical care. However, class imbalance and data limitations present challenges for this sparsely documented yet critical information. Here, we investigated the optimal methods for using LLMs to extract six SDoH categories from narrative text in the EHR: employment, housing, transportation, parental status, relationship, and social support. The best-performing models were fine-tuned Flan-T5 XL for any SDoH mentions (macro-F1 0.71), and Flan-T5 XXL for adverse SDoH mentions (macro-F1 0.70). Adding LLM-generated synthetic data to training varied across models and architecture, but improved the performance of smaller Flan-T5 models (delta F1 + 0.12 to +0.23). Our best-fine-tuned models outperformed zero- and few-shot performance of ChatGPT-family models in the zero- and few-shot setting, except GPT4 with 10-shot prompting for adverse SDoH. Fine-tuned models were less likely than ChatGPT to change their prediction when race/ethnicity and gender descriptors were added to the text, suggesting less algorithmic bias (p < 0.05). Our models identified 93.8% of patients with adverse SDoH, while ICD-10 codes captured 2.0%. These results demonstrate the potential of LLMs in improving real-world evidence on SDoH and assisting in identifying patients who could benefit from resource support.

An R Shiny Application (SDOH) for Predictive Modeling Using Regional Social Determinants of Health Survey Responses

Social determinants of health (SDoH) surveys are data sets that provide useful health-related information about individuals and communities. This study aims to develop a user-friendly web application that allows clinicians to get a predictive insight into the social needs of their patients before their in-patient visits using SDoH survey data to provide an improved and personalized service. The study used a longitudinal survey that consisted of 108,563 patient responses to 12 questions. Questions were designed to have a binary outcome as the response and the patient's most recent responses for each of these questions were modeled independently by incorporating explanatory variables. Multiple classification and regression techniques were used, including logistic regression, Bayesian generalized linear model, extreme gradient boosting, gradient boosting, neural networks, and random forests. Based on the area under the curve values, gradient boosting models provided the highest precision values. Finally, the models were incorporated into an R Shiny application, enabling users to predict and compare the impact of SDoH on patients' lives. The tool is freely hosted online by the University of Kansas Medical Center's Department of Biostatistics and Data Science. The supporting materials for the application are publicly accessible on GitHub.

Addressing Health-Related Social Needs and Mental Health Needs in the Neonatal Intensive Care Unit: Exploring Challenges and the Potential of Technology

Unaddressed health-related social needs (HRSNs) and parental mental health needs in an infant's environment can negatively affect their health outcomes. This study examines the challenges and potential technological solutions for addressing these needs in the neonatal intensive care unit (NICU) setting and beyond. In all, 22 semistructured interviews were conducted with members of the NICU care team and other relevant stakeholders, based on an interpretive description approach. The participants were selected from three safety net hospitals in the U.S. with level IV NICUs. The challenges identified include navigating the multitude of burdens families in the NICU experience, resource constraints within and beyond the health system, a lack of streamlined or consistent processes, no closed-loop referrals to track status and outcomes, and gaps in support postdischarge. Opportunities for leveraging technology to facilitate screening and referral include automating screening, initiating risk-based referrals, using remote check-ins, facilitating resource navigation, tracking referrals, and providing language support. However, technological implementations should avoid perpetuating disparities and consider potential privacy or data-sharing concerns. Although advances in technological health tools alone cannot address all the challenges, they have the potential to offer dynamic tools to support the healthcare setting in identifying and addressing the unique needs and circumstances of each family in the NICU.

Development of a social and environmental determinants of health informatics maturity model

Introduction

Integrating social and environmental determinants of health (SEDoH) into enterprise-wide clinical workflows and decision-making is one of the most important and challenging aspects of improving health equity. We engaged domain experts to develop a SEDoH informatics maturity model (SIMM) to help guide organizations to address technical, operational, and policy gaps.

Methods

We established a core expert group consisting of developers, informaticists, and subject matter experts to identify different SIMM domains and define maturity levels. The candidate model (v0.9) was evaluated by 15 informaticists at a Center for Data to Health community meeting. After incorporating feedback, a second evaluation round for v1.0 collected feedback and self-assessments from 35 respondents from the National COVID Cohort Collaborative, the Center for Leading Innovation and Collaboration's Informatics Enterprise Committee, and a publicly available online self-assessment tool.

Results

We developed a SIMM comprising seven maturity levels across five domains: data collection policies, data collection methods and technologies, technology platforms for analysis and visualization, analytics capacity, and operational and strategic impact. The evaluation demonstrated relatively high maturity in analytics and technological capacity, but more moderate maturity in operational and strategic impact among academic medical centers. Changes made to the tool in between rounds improved its ability to discriminate between intermediate maturity levels.

Conclusion

The SIMM can help organizations identify current gaps and next steps in improving SEDoH informatics. Improving the collection and use of SEDoH data is one important component of addressing health inequities.

Social Risk Factors are Associated with Risk for Hospitalization in Home Health Care: A Natural Language Processing Study

OBJECTIVE

This study aimed to develop a natural language processing (NLP) system that identified social risk factors in home health care (HHC) clinical notes and to examine the association between social risk factors and hospitalization or an emergency department (ED) visit.

DESIGN

Retrospective cohort study.

SETTING AND PARTICIPANTS

We used standardized assessments and clinical notes from one HHC agency located in the northeastern United States. This included 86,866 episodes of care for 65,593 unique patients. Patients received HHC services between 2015 and 2017.

METHODS

Guided by HHC experts, we created a vocabulary of social risk factors that influence hospitalization or ED visit risk in the HHC setting. We then developed an NLP system to automatically identify social risk factors documented in clinical notes. We used an adjusted logistic regression model to examine the association between the NLP-based social risk factors and hospitalization or an ED visit.

RESULTS

On the basis of expert consensus, the following social risk factors emerged: Social Environment, Physical Environment, Education and Literacy, Food Insecurity, Access to Care, and Housing and Economic Circumstances. Our NLP system performed "very good" with an F score of 0.91. Approximately 4% of clinical notes (33% episodes of care) documented a social risk factor. The most frequently documented social risk factors were Physical Environment and Social Environment. Except for Housing and Economic Circumstances, all NLP-based social risk factors were associated with higher odds of hospitalization and ED visits.

CONCLUSIONS AND IMPLICATIONS

HHC clinicians assess and document social risk factors associated with hospitalizations and ED visits in their clinical notes. Future studies can explore the social risk factors documented in HHC to improve communication across the health care system and to predict patients at risk for being hospitalized or visiting the ED.

Natural language processing to identify social determinants of health in Alzheimer's disease and related dementia from electronic health records

OBJECTIVE

To develop a natural language processing (NLP) algorithm that identifies social determinants of health (SDoH), including housing, transportation, food, and medication insecurities, social isolation, abuse, neglect, or exploitation, and financial difficulties for patients with Alzheimer's disease and related dementias (ADRD) from unstructured electronic health records (EHRs).

DATA SOURCES AND STUDY SETTING

We leveraged 1000 medical notes randomly selected from 7401 emergency department and inpatient social worker notes generated between 2015 and 2019 for 231 unique patients diagnosed with ADRD at Michigan Medicine.

STUDY DESIGN

We developed a rule-based NLP algorithm for the identification of seven domains of SDoH noted above. We also compared the rule-based algorithm with deep learning and regularized logistic regression approaches. These models were compared using accuracy, sensitivity, specificity, F1 score, and the area under the receiver operating characteristic curve (AUC). All notes were split into 700 notes for training NLP algorithms, and 300 notes for validation.

DATA COLLECTION/EXTRACTION METHODS

Social worker notes used in this study were extracted from the Michigan Medicine EHR database.

PRINCIPAL FINDINGS

Of the 700 notes for training, F1 and AUC for the rule-based algorithm were at least 0.94 and 0.95, respectively, for all SDoH categories. Of the 300 notes for validation, F1 and AUC were at least 0.80 and 0.97, respectively, for all SDoH except housing and medication insecurities. The deep learning and regularized logistic regression algorithms had unsatisfactory performance.

CONCLUSIONS

The rule-based algorithm can accurately extract SDoH information in all seven domains of SDoH except housing and medication insecurities. Findings from the algorithm can be used by clinicians and social workers to proactively address social needs of patients with ADRD and other vulnerable patient populations.

Polysocial Risk Scores: Implications for Cardiovascular Disease Risk Assessment and Management

PURPOSE OF REVIEW

To review current evidence, discuss key knowledge gaps and identify opportunities for development, validation and application of polysocial risk scores (pSRS) for cardiovascular disease (CVD) risk prediction and population cardiovascular health management.

RECENT FINDINGS

Limited existing evidence suggests that pSRS are promising tools to capture cumulative social determinants of health (SDOH) burden and improve CVD risk prediction beyond traditional risk factors. However, available tools lack generalizability, are cross-sectional in nature or do not assess social risk holistically across SDOH domains. Available SDOH and clinical risk factor data in large population-based databases are under-utilized for pSRS development. Recent advances in machine learning and artificial intelligence present unprecedented opportunities for SDOH integration and assessment in real-world data, with implications for pSRS development and validation for both clinical and healthcare utilization outcomes. pSRS presents unique opportunities to potentially improve traditional "clinical" models of CVD risk prediction. Future efforts should focus on fully utilizing available SDOH data in large epidemiological databases, testing pSRS efficacy in diverse population subgroups, and integrating pSRS into real-world clinical decision support systems to inform clinical care and advance cardiovascular health equity.

Using nursing science to advance policy and practice in the context of social and structural determinants of health

BACKGROUND

Social and structural determinants of health play a large role in health inequities.

PURPOSE

To highlight how nursing science can be used to advance policy and practice in the context of social and structural determinants of health.

METHODS

This paper reports on the author's keynote presentation from the 2022 State of The Science Conference on Social and Structural Determinants of Health presented by the Council for the Advancement of Nursing Science. Key concepts are overviewed and defined, followed by examples of two community-engaged research projects with findings that inform practice and policy. The author concludes with individual-, social- and structural-level recommendations as a clarion call for nurses to use research to eliminate health inequities and promote justice for all.

CONCLUSION

What we know is, in part, only as good as what we do with that knowledge. When lives are at stake, gone are the days of knowing something and failing to act on that knowledge.

Mapping the delineation of practice to the AMIA foundational domains for applied health informatics

OBJECTIVE

This article reports on the alignment between the foundational domains and the delineation of practice (DoP) for health informatics, both developed by the American Medical Informatics Association (AMIA). Whereas the foundational domains guide graduate-level curriculum development and accreditation assessment, providing an educational pathway to the minimum competencies needed as a health informatician, the DoP defines the domains, tasks, knowledge, and skills that a professional needs to competently perform in the discipline of health informatics. The purpose of this article is to determine whether the foundational domains need modification to better reflect applied practice.

MATERIALS AND METHODS

Using an iterative process and through individual and collective approaches, the foundational domains and the DoP statements were analyzed for alignment and eventual harmonization. Tables and Sankey plot diagrams were used to detail and illustrate the resulting alignment.

RESULTS

We were able to map all the individual DoP knowledge statements and tasks to the AMIA foundational domains, but the statements within a single DoP domain did not all map to the same foundational domain. Even though the AMIA foundational domains and DoP domains are not in perfect alignment, the DoP provides good examples of specific health informatics competencies for most of the foundational domains. There are, however, limited DoP knowledge statements and tasks mapping to foundational domain 6-Social and Behavioral Aspects of Health.

DISCUSSION

Both the foundational domains and the DoP were developed independently, several years apart, and for different purposes. The mapping analyses reveal similarities and differences between the practice experience and the curricular needs of health informaticians.

CONCLUSIONS

The overall alignment of both domains may be explained by the fact that both describe the current and/or future health informatics professional. One can think of the foundational domains as representing the broad foci for educational programs for health informaticians and, hence, they are appropriately the focus of organizations that accredit these programs.

Leveraging natural language processing to augment structured social determinants of health data in the electronic health record

OBJECTIVE

Social determinants of health (SDOH) impact health outcomes and are documented in the electronic health record (EHR) through structured data and unstructured clinical notes. However, clinical notes often contain more comprehensive SDOH information, detailing aspects such as status, severity, and temporality. This work has two primary objectives: (1) develop a natural language processing information extraction model to capture detailed SDOH information and (2) evaluate the information gain achieved by applying the SDOH extractor to clinical narratives and combining the extracted representations with existing structured data.

MATERIALS AND METHODS

We developed a novel SDOH extractor using a deep learning entity and relation extraction architecture to characterize SDOH across various dimensions. In an EHR case study, we applied the SDOH extractor to a large clinical data set with 225 089 patients and 430 406 notes with social history sections and compared the extracted SDOH information with existing structured data.

RESULTS

The SDOH extractor achieved 0.86 F1 on a withheld test set. In the EHR case study, we found extracted SDOH information complements existing structured data with 32% of homeless patients, 19% of current tobacco users, and 10% of drug users only having these health risk factors documented in the clinical narrative.

CONCLUSIONS

Utilizing EHR data to identify SDOH health risk factors and social needs may improve patient care and outcomes. Semantic representations of text-encoded SDOH information can augment existing structured data, and this more comprehensive SDOH representation can assist health systems in identifying and addressing these social needs.

Extracting social determinants of health from clinical note text with classification and sequence-to-sequence approaches

OBJECTIVE

Social determinants of health (SDOH) are nonmedical factors that can influence health outcomes. This paper seeks to extract SDOH from clinical texts in the context of the National NLP Clinical Challenges (n2c2) 2022 Track 2 Task.

MATERIALS AND METHODS

Annotated and unannotated data from the Medical Information Mart for Intensive Care III (MIMIC-III) corpus, the Social History Annotation Corpus, and an in-house corpus were used to develop 2 deep learning models that used classification and sequence-to-sequence (seq2seq) approaches.

RESULTS

The seq2seq approach had the highest overall F1 scores in the challenge's 3 subtasks: 0.901 on the extraction subtask, 0.774 on the generalizability subtask, and 0.889 on the learning transfer subtask.

DISCUSSION

Both approaches rely on SDOH event representations that were designed to be compatible with transformer-based pretrained models, with the seq2seq representation supporting an arbitrary number of overlapping and sentence-spanning events. Models with adequate performance could be produced quickly, and the remaining mismatch between representation and task requirements was then addressed in postprocessing. The classification approach used rules to generate entity relationships from its sequence of token labels, while the seq2seq approach used constrained decoding and a constraint solver to recover entity text spans from its sequence of potentially ambiguous tokens.

CONCLUSION

We proposed 2 different approaches to extract SDOH from clinical texts with high accuracy. However, accuracy suffers on text from new healthcare institutions not present in the training data, and thus generalization remains an important topic for future study.

Natural language processing-driven state machines to extract social factors from unstructured clinical documentation

Objective

This study sought to create natural language processing algorithms to extract the presence of social factors from clinical text in 3 areas: (1) housing, (2) financial, and (3) unemployment. For generalizability, finalized models were validated on data from a separate health system for generalizability.

Materials and Methods

Notes from 2 healthcare systems, representing a variety of note types, were utilized. To train models, the study utilized n-grams to identify keywords and implemented natural language processing (NLP) state machines across all note types. Manual review was conducted to determine performance. Sampling was based on a set percentage of notes, based on the prevalence of social need. Models were optimized over multiple training and evaluation cycles. Performance metrics were calculated using positive predictive value (PPV), negative predictive value, sensitivity, and specificity.

Results

PPV for housing rose from 0.71 to 0.95 over 3 training runs. PPV for financial rose from 0.83 to 0.89 over 2 training iterations, while PPV for unemployment rose from 0.78 to 0.88 over 3 iterations. The test data resulted in PPVs of 0.94, 0.97, and 0.95 for housing, financial, and unemployment, respectively. Final specificity scores were 0.95, 0.97, and 0.95 for housing, financial, and unemployment, respectively.

Discussion

We developed 3 rule-based NLP algorithms, trained across health systems. While this is a less sophisticated approach, the algorithms demonstrated a high degree of generalizability, maintaining >0.85 across all predictive performance metrics.

Conclusion

The rule-based NLP algorithms demonstrated consistent performance in identifying 3 social factors within clinical text. These methods may be a part of a strategy to measure social factors within an institution.

Natural Language Processing Methods to Empirically Explore Social Contexts and Needs in Cancer Patient Notes

PURPOSE

There is an unmet need to empirically explore and understand drivers of cancer disparities, particularly social determinants of health. We explored natural language processing methods to automatically and empirically extract clinical documentation of social contexts and needs that may underlie disparities.

METHODS

This was a retrospective analysis of 230,325 clinical notes from 5,285 patients treated with radiotherapy from 2007 to 2019. We compared linguistic features among White versus non-White, low-income insurance versus other insurance, and male versus female patients' notes. Log odds ratios with an informative Dirichlet prior were calculated to compare words over-represented in each group. A variational autoencoder topic model was applied, and topic probability was compared between groups. The presence of machine-learnable bias was explored by developing statistical and neural demographic group classifiers.

RESULTS

Terms associated with varied social contexts and needs were identified for all demographic group comparisons. For example, notes of non-White and low-income insurance patients were over-represented with terms associated with housing and transportation, whereas notes of White and other insurance patients were over-represented with terms related to physical activity. Topic models identified a social history topic, and topic probability varied significantly between the demographic group comparisons. Classification models performed poorly at classifying notes of non-White and low-income insurance patients (F1 of 0.30 and 0.23, respectively).

CONCLUSION

Exploration of linguistic differences in clinical notes between patients of different race/ethnicity, insurance status, and sex identified social contexts and needs in patients with cancer and revealed high-level differences in notes. Future work is needed to validate whether these findings may play a role in cancer disparities.

A Review on Electronic Health Record Text-Mining for Biomedical Name Entity Recognition in Healthcare Domain

Biomedical-named entity recognition (bNER) is critical in biomedical informatics. It identifies biomedical entities with special meanings, such as people, places, and organizations, as predefined semantic types in electronic health records (EHR). bNER is essential for discovering novel knowledge using computational methods and Information Technology. Early bNER systems were configured manually to include domain-specific features and rules. However, these systems were limited in handling the complexity of the biomedical text. Recent advances in deep learning (DL) have led to the development of more powerful bNER systems. DL-based bNER systems can learn the patterns of biomedical text automatically, making them more robust and efficient than traditional rule-based systems. This paper reviews the healthcare domain of bNER, using DL techniques and artificial intelligence in clinical records, for mining treatment prediction. bNER-based tools are categorized systematically and represent the distribution of input, context, and tag (encoder/decoder). Furthermore, to create a labeled dataset for our machine learning sentiment analyzer to analyze the sentiment of a set of tweets, we used a manual coding approach and the multi-task learning method to bias the training signals with domain knowledge inductively. To conclude, we discuss the challenges facing bNER systems and future directions in the healthcare field.

Identifying Military Service Status in Electronic Healthcare Records from Psychiatric Secondary Healthcare Services: A Validation Exercise Using the Military Service Identification Tool

Electronic healthcare records (EHRs) are a rich source of information with a range of uses in secondary research. In the United Kingdom, there is no pan-national or nationally accepted marker indicating veteran status across all healthcare services. This presents significant obstacles to determining the healthcare needs of veterans using EHRs. To address this issue, we developed the Military Service Identification Tool (MSIT), using an iterative two-staged approach. In the first stage, a Structured Query Language approach was developed to identify veterans using a keyword rule-based approach. This informed the second stage, which was the development of the MSIT using machine learning, which, when tested, obtained an accuracy of 0.97, a positive predictive value of 0.90, a sensitivity of 0.91, and a negative predictive value of 0.98. To further validate the performance of the MSIT, the present study sought to verify the accuracy of the EHRs that trained the MSIT models. To achieve this, we surveyed 902 patients of a local specialist mental healthcare service, with 146 (16.2%) being asked if they had or had not served in the Armed Forces. In total 112 (76.7%) reported that they had not served, and 34 (23.3%) reported that they had served in the Armed Forces (accuracy: 0.84, sensitivity: 0.82, specificity: 0.91). The MSIT has the potential to be used for identifying veterans in the UK from free-text clinical documents and future use should be explored.

Machine learning approaches for electronic health records phenotyping: a methodical review

OBJECTIVE

Accurate and rapid phenotyping is a prerequisite to leveraging electronic health records for biomedical research. While early phenotyping relied on rule-based algorithms curated by experts, machine learning (ML) approaches have emerged as an alternative to improve scalability across phenotypes and healthcare settings. This study evaluates ML-based phenotyping with respect to (1) the data sources used, (2) the phenotypes considered, (3) the methods applied, and (4) the reporting and evaluation methods used.

MATERIALS AND METHODS

We searched PubMed and Web of Science for articles published between 2018 and 2022. After screening 850 articles, we recorded 37 variables on 100 studies.

RESULTS

Most studies utilized data from a single institution and included information in clinical notes. Although chronic conditions were most commonly considered, ML also enabled the characterization of nuanced phenotypes such as social determinants of health. Supervised deep learning was the most popular ML paradigm, while semi-supervised and weakly supervised learning were applied to expedite algorithm development and unsupervised learning to facilitate phenotype discovery. ML approaches did not uniformly outperform rule-based algorithms, but deep learning offered a marginal improvement over traditional ML for many conditions.

DISCUSSION

Despite the progress in ML-based phenotyping, most articles focused on binary phenotypes and few articles evaluated external validity or used multi-institution data. Study settings were infrequently reported and analytic code was rarely released.

CONCLUSION

Continued research in ML-based phenotyping is warranted, with emphasis on characterizing nuanced phenotypes, establishing reporting and evaluation standards, and developing methods to accommodate misclassified phenotypes due to algorithm errors in downstream applications.

Machine Learning Techniques to Explore Clinical Presentations of COVID-19 Severity and to Test the Association With Unhealthy Opioid Use: Retrospective Cross-sectional Cohort Study

BACKGROUND

The COVID-19 pandemic has exacerbated health inequities in the United States. People with unhealthy opioid use (UOU) may face disproportionate challenges with COVID-19 precautions, and the pandemic has disrupted access to opioids and UOU treatments. UOU impairs the immunological, cardiovascular, pulmonary, renal, and neurological systems and may increase severity of outcomes for COVID-19.

OBJECTIVE

We applied machine learning techniques to explore clinical presentations of hospitalized patients with UOU and COVID-19 and to test the association between UOU and COVID-19 disease severity.

METHODS

This retrospective, cross-sectional cohort study was conducted based on data from 4110 electronic health record patient encounters at an academic health center in Chicago between January 1, 2020, and December 31, 2020. The inclusion criterion was an unplanned admission of a patient aged ≥18 years; encounters were counted as COVID-19-positive if there was a positive test for COVID-19 or 2 COVID-19 International Classification of Disease, Tenth Revision codes. Using a predefined cutoff with optimal sensitivity and specificity to identify UOU, we ran a machine learning UOU classifier on the data for patients with COVID-19 to estimate the subcohort of patients with UOU. Topic modeling was used to explore and compare the clinical presentations documented for 2 subgroups: encounters with UOU and COVID-19 and those with no UOU and COVID-19. Mixed effects logistic regression accounted for multiple encounters for some patients and tested the association between UOU and COVID-19 outcome severity. Severity was measured with 3 utilization metrics: low-severity unplanned admission, medium-severity unplanned admission and receiving mechanical ventilation, and high-severity unplanned admission with in-hospital death. All models controlled for age, sex, race/ethnicity, insurance status, and BMI.

RESULTS

Topic modeling yielded 10 topics per subgroup and highlighted unique comorbidities associated with UOU and COVID-19 (eg, HIV) and no UOU and COVID-19 (eg, diabetes). In the regression analysis, each incremental increase in the classifier's predicted probability of UOU was associated with 1.16 higher odds of COVID-19 outcome severity (odds ratio 1.16, 95% CI 1.04-1.29; P=.009).

CONCLUSIONS

Among patients hospitalized with COVID-19, UOU is an independent risk factor associated with greater outcome severity, including in-hospital death. Social determinants of health and opioid-related overdose are unique comorbidities in the clinical presentation of the UOU patient subgroup. Additional research is needed on the role of COVID-19 therapeutics and inpatient management of acute COVID-19 pneumonia for patients with UOU. Further research is needed to test associations between expanded evidence-based harm reduction strategies for UOU and vaccination rates, hospitalizations, and risks for overdose and death among people with UOU and COVID-19. Machine learning techniques may offer more exhaustive means for cohort discovery and a novel mixed methods approach to population health.

Deep Learning Analysis of Polish Electronic Health Records for Diagnosis Prediction in Patients with Cardiovascular Diseases

Electronic health records naturally contain most of the medical information in the form of doctor’s notes as unstructured or semi-structured texts. Current deep learning text analysis approaches allow researchers to reveal the inner semantics of text information and even identify hidden consequences that can offer extra decision support to doctors. In the presented article, we offer a new automated analysis of Polish summary texts of patient hospitalizations. The presented models were found to be able to predict the final diagnosis with almost 70% accuracy based just on the patient’s medical history (only 132 words on average), with possible accuracy increases when adding further sentences from hospitalization results; even one sentence was found to improve the results by 4%, and the best accuracy of 78% was achieved with five extra sentences. In addition to detailed descriptions of the data and methodology, we present an evaluation of the analysis using more than 50,000 Polish cardiology patient texts and dive into a detailed error analysis of the approach. The results indicate that the deep analysis of just the medical history summary can suggest the direction of diagnosis with a high probability that can be further increased just by supplementing the records with further examination results.