Prediction of Future Health Care Utilization Through Note-extracted Psychosocial Factors

Differences in Healthcare Utilization Across 2 Social Health Support Modalities: Results From a Randomized Pilot Evaluation

Introduction

The aim of this study was to assess differences in utilization outcomes among patients with social needs as part of a pilot social health integration program in 2 clinics in an integrated health system in the Pacific Northwest.

Methods

Patients who reported social needs between October 2022 and January 2023 were randomized to receive support from either local, clinic-based community resource specialists or a centralized Connections Call Center. The authors used administrative and claims data for 534 participants to compare the following utilization outcomes between arms over 9 months after randomization: primary care encounters, specialty care encounters, behavioral health encounters, emergency department encounters, inpatient admissions, urgent care encounters, and secure patient messages. Using an intent-to-treat approach, the authors used negative binomial regression models to compare visit counts and logistic regression to estimate differences in the probability of any emergency department visit or inpatient admissions between groups. The authors conducted secondary as-treated analyses comparing participants who received resource information from community resource specialists with those who did not.

Results

Unadjusted results showed no statistically significant differences between community resource specialists and Connections Call Center. Adjusted results showed that community resource specialist participants received 1.04 more primary care encounters than Connections Call Center participants (95% CI=0.336, 1.746). As-treated results showed that participants who received support from community resource specialists had higher counts of primary care encounters, specialty care encounters, and patient messages than those who did not.

Conclusions

Beyond social needs navigation, clinic-based supports may be better integrated with care teams to provide ongoing support for patients' medical needs. Findings from this primary care social health pilot program showed that local, clinic-based support was associated with greater outpatient utilization than a call center support.

Comparison of clinic-based assistance versus a centralized call center on patient-reported social needs: findings from a randomized pilot social health integration program

BACKGROUND

As social need screening and intervention activities increase, the long-term objective of our work is to inform how to implement social health into healthcare settings. The purpose of this study is to assess changes in social needs over time between two social health support programs as part of a social health integration effort in two primary care clinics within an integrated health system in Washington state.

METHODS

We used stratified randomization to assign 535 patients who self-reported social needs on a screener between October 2022-January 2023 to one of two social health support programs: local, clinic-based Community Resource Specialists (CRS) or a centralized Connections Call Center (CCC). Participants were assessed at 2- and 5-months post-randomization. We compared the count of social needs across programs at each timepoint using joint tests, and estimated differences between programs using generalized linear mixed effects models at each timepoint.

RESULTS

We randomized 535 participants, with 270 assigned to CCC and 272 to CRS. Of those randomized, 61% completed at least one follow-up survey (N = 329). This analytic sample consisted of 153 CCC participants and 176 participants under CRS. CRS participants reported 0.08 (95% CI: -0.710, 0.864) more needs at 2 months and 0.42 (CI: -0.288, 1.126) more needs at 5 months compared to CCC participants (p > 0.05). An exploratory as-treated analysis within the CRS group suggested that referral receipt was associated with fewer needs over time.

CONCLUSIONS

There were no significant differences between CRS and CCC participants' social needs over time. However, receiving referrals to social services may lead to reduced social needs.

Reverse Time-to-Death as Time-Scale in Time-to-Event Analysis for Studies of Advanced Illness and Palliative Care

Incidence of adverse outcome events rises as patients with advanced illness approach end-of-life. Exposures that tend to occur near end-of-life, for example, use of wheelchair, oxygen therapy and palliative care, may therefore be found associated with the incidence of the adverse outcomes. We propose a concept of reverse time-to-death (rTTD) and its use for the time-scale in time-to-event analysis based on partial likelihood to mitigate the time-varying confounding. We used data on community-based palliative care uptake (exposure) and emergency department visits (outcome) among patients with advanced cancer in Singapore to illustrate. We compare the results against that of the common practice of using time-on-study (TOS) as time-scale. Graphical analysis demonstrated that cancer patients receiving palliative care had higher rate of emergency department visits than non-recipients mainly because they were closer to end-of-life, and that rTTD analysis made comparison between patients at the same time-to-death. In analysis of a decedent cohort, emergency department visits in relation to palliative care using TOS time-scale showed significant increase in hazard ratio estimate when observed time-varying covariates were omitted from statistical adjustment (% change-in-estimate = 16.2%; 95% CI 6.4% to 25.6%). There was no such change in otherwise the same analysis using rTTD (% change-in-estimate = 3.1%; 95% CI -1.0% to 8.5%), demonstrating the ability of rTTD time-scale to mitigate confounding that intensifies in relation to time-to-death. A similar pattern was found in the full cohort. Simulations demonstrated that the proposed method had smaller relative bias and root mean square error than TOS-based analysis. In conclusion, use of rTTD as time-scale in time-to-event analysis provides a simple and robust approach to control time-varying confounding in studies of advanced illness, even if the confounders are unmeasured.

Natural Language Processing and Social Determinants of Health in Mental Health Research: AI-Assisted Scoping Review

Background

The use of natural language processing (NLP) in mental health research is increasing, with a wide range of applications and datasets being investigated.

Objective

This review aims to summarize the use of NLP in mental health research, with a special focus on the types of text datasets and the use of social determinants of health (SDOH) in NLP projects related to mental health.

Methods

The search was conducted in September 2024 using a broad search strategy in PubMed, Scopus, and CINAHL Complete. All citations were uploaded to Covidence (Veritas Health Innovation) software. The screening and extraction process took place in Covidence with the help of a custom large language model (LLM) module developed by our team. This LLM module was calibrated and tuned to automate many aspects of the review process.

Results

The screening process, assisted by the custom LLM, led to the inclusion of 1768 studies in the final review. Most of the reviewed studies (n=665, 42.8%) used clinical data as their primary text dataset, followed by social media datasets (n=523, 33.7%). The United States contributed the highest number of studies (n=568, 36.6%), with depression (n=438, 28.2%) and suicide (n=240, 15.5%) being the most frequently investigated mental health issues. Traditional demographic variables, such as age (n=877, 56.5%) and gender (n=760, 49%), were commonly extracted, while SDOH factors were less frequently reported, with urban or rural status being the most used (n=19, 1.2%). Over half of the citations (n=826, 53.2%) did not provide clear information on dataset accessibility, although a sizable number of studies (n=304, 19.6%) made their datasets publicly available.

Conclusions

This scoping review underscores the significant role of clinical notes and social media in NLP-based mental health research. Despite the clear relevance of SDOH to mental health, their underutilization presents a gap in current research. This review can be a starting point for researchers looking for an overview of mental health projects using text data. Shared datasets could be used to place more emphasis on SDOH in future studies.

Case Identification of Depression in Inpatient Electronic Medical Records: Scoping Review

Background

Electronic medical records (EMRs) contain large amounts of detailed clinical information. Using medical record review to identify conditions within large quantities of EMRs can be time-consuming and inefficient. EMR-based phenotyping using machine learning and natural language processing algorithms is a continually developing area of study that holds potential for numerous mental health disorders.

Objective

This review evaluates the current state of EMR-based case identification for depression and provides guidance on using current algorithms and constructing new ones.

Methods

A scoping review of EMR-based algorithms for phenotyping depression was completed. This research encompassed studies published from January 2000 to May 2023. The search involved 3 databases: Embase, MEDLINE, and APA PsycInfo. This was carried out using selected keywords that fell into 3 categories: terms connected with EMRs, terms connected to case identification, and terms pertaining to depression. This study adhered to the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines.

Results

A total of 20 papers were assessed and summarized in the review. Most of these studies were undertaken in the United States, accounting for 75% (15/20). The United Kingdom and Spain followed this, accounting for 15% (3/20) and 10% (2/20) of the studies, respectively. Both data-driven and clinical rule-based methodologies were identified. The development of EMR-based phenotypes and algorithms indicates the data accessibility permitted by each health system, which led to varying performance levels among different algorithms.

Conclusions

Better use of structured and unstructured EMR components through techniques such as machine learning and natural language processing has the potential to improve depression phenotyping. However, more validation must be carried out to have confidence in depression case identification algorithms in general.

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.

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.

The Growing Impact of Natural Language Processing in Healthcare and Public Health

Natural Language Processing (NLP) is a subset of Artificial Intelligence, specifically focused on understanding and generating human language. NLP technologies are becoming more prevalent in healthcare and hold potential solutions to current problems. Some examples of existing and future uses include: public sentiment analysis in relation to health policies, electronic health record (EHR) screening, use of speech to text technology for extracting EHR data from point of care, patient communications, accelerated identification of eligible clinical trial candidates through automated searches and access of health data to assist in informed treatment decisions. This narrative review aims to summarize the current uses of NLP in healthcare, highlight successful implementation of computational linguistics-based approaches, and identify gaps, limitations, and emerging trends within the subfield of NLP in public health. The online databases Google Scholar and PubMed were scanned for papers published between 2018 and 2023. Keywords "Natural Language Processing, Health Policy, Large Language Models" were utilized in the initial search. Then, papers were limited to those written in English. Each of the 27 selected papers was subject to careful analysis, and their relevance in relation to NLP and healthcare respectively is utilized in this review. NLP and deep learning technologies scan large datasets, extracting valuable insights in various realms. This is especially significant in healthcare where huge amounts of data exist in the form of unstructured text. Automating labor intensive and tedious tasks with language processing algorithms, using text analytics systems and machine learning to analyze social media data and extracting insights from unstructured data allows for better public sentiment analysis, enhancement of risk prediction models, improved patient communication, and informed treatment decisions. In the recent past, some studies have applied NLP tools to social media posts to evaluate public sentiment regarding COVID-19 vaccine use. Social media data also has the capacity to be harnessed to develop pandemic prediction models based on reported symptoms. Furthermore, NLP has the potential to enhance healthcare delivery across the globe. Advanced language processing techniques such as Speech Recognition (SR) and Natural Language Understanding (NLU) tools can help overcome linguistic barriers and facilitate efficient communication between patients and healthcare providers.

Improving ascertainment of suicidal ideation and suicide attempt with natural language processing

Methods relying on diagnostic codes to identify suicidal ideation and suicide attempt in Electronic Health Records (EHRs) at scale are suboptimal because suicide-related outcomes are heavily under-coded. We propose to improve the ascertainment of suicidal outcomes using natural language processing (NLP). We developed information retrieval methodologies to search over 200 million notes from the Vanderbilt EHR. Suicide query terms were extracted using word2vec. A weakly supervised approach was designed to label cases of suicidal outcomes. The NLP validation of the top 200 retrieved patients showed high performance for suicidal ideation (area under the receiver operator curve [AUROC]: 98.6, 95% confidence interval [CI] 97.1-99.5) and suicide attempt (AUROC: 97.3, 95% CI 95.2-98.7). Case extraction produced the best performance when combining NLP and diagnostic codes and when accounting for negated suicide expressions in notes. Overall, we demonstrated that scalable and accurate NLP methods can be developed to identify suicidal behavior in EHRs to enhance prevention efforts, predictive models, and precision medicine.