AI Article Synopsis

  • Social determinants of health (SDOH) significantly affect health outcomes, but gathering this data in emergency departments (EDs) is complex, prompting the need for innovative solutions.
  • This scoping review assesses the use of AI and data science in modeling and extracting SDOH data in EDs, highlighting areas that need further research and improvement.
  • Out of 1047 studies, 26 were relevant, with 35% focusing solely on ED patients; findings showed that machine learning, particularly natural language processing, was frequently used and showed good predictive accuracy for clinical outcomes.

Article Abstract

Background: Social determinants of health (SDOH) are critical drivers of health disparities and patient outcomes. However, accessing and collecting patient-level SDOH data can be operationally challenging in the emergency department (ED) clinical setting, requiring innovative approaches.

Objective: This scoping review examines the potential of AI and data science for modeling, extraction, and incorporation of SDOH data specifically within EDs, further identifying areas for advancement and investigation.

Methods: We conducted a standardized search for studies published between 2015 and 2022, across Medline (Ovid), Embase (Ovid), CINAHL, Web of Science, and ERIC databases. We focused on identifying studies using AI or data science related to SDOH within emergency care contexts or conditions. Two specialized reviewers in emergency medicine (EM) and clinical informatics independently assessed each article, resolving discrepancies through iterative reviews and discussion. We then extracted data covering study details, methodologies, patient demographics, care settings, and principal outcomes.

Results: Of the 1047 studies screened, 26 met the inclusion criteria. Notably, 9 out of 26 (35%) studies were solely concentrated on ED patients. Conditions studied spanned broad EM complaints and included sepsis, acute myocardial infarction, and asthma. The majority of studies (n=16) explored multiple SDOH domains, with homelessness/housing insecurity and neighborhood/built environment predominating. Machine learning (ML) techniques were used in 23 of 26 studies, with natural language processing (NLP) being the most commonly used approach (n=11). Rule-based NLP (n=5), deep learning (n=2), and pattern matching (n=4) were the most commonly used NLP techniques. NLP models in the reviewed studies displayed significant predictive performance with outcomes, with F1-scores ranging between 0.40 and 0.75 and specificities nearing 95.9%.

Conclusions: Although in its infancy, the convergence of AI and data science techniques, especially ML and NLP, with SDOH in EM offers transformative possibilities for better usage and integration of social data into clinical care and research. With a significant focus on the ED and notable NLP model performance, there is an imperative to standardize SDOH data collection, refine algorithms for diverse patient groups, and champion interdisciplinary synergies. These efforts aim to harness SDOH data optimally, enhancing patient care and mitigating health disparities. Our research underscores the vital need for continued investigation in this domain.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11539921PMC
http://dx.doi.org/10.2196/57124DOI Listing

Publication Analysis

Top Keywords

data science
16
sdoh data
16
data
10
integration social
8
social determinants
8
determinants health
8
emergency medicine
8
scoping review
8
sdoh
8
health disparities
8

Similar Publications

Longitudinal Outcomes in Noonan Syndrome.

Genet Med

January 2025

Division of Human Genetics, Children's Hospital of Philadelphia; Department of Pediatrics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA.

Purpose: Noonan syndrome and related disorders (NS) are multisystemic conditions affecting approximately 1:1000 individuals. Previous natural history studies were conducted prior to widespread comprehensive genetic testing. This study provides updated longitudinal natural history data in participants with molecularly confirmed NS.

View Article and Find Full Text PDF

Introduction: Many patients acutely self-poisoned with organophosphorus insecticides have co-ingested ethanol. Currently, profenofos 50% emulsifiable concentrate (EC50) is commonly ingested for self-harm in Sri Lanka. Clinical experience suggests that ethanol co-ingestion makes management more difficult.

View Article and Find Full Text PDF

Metabolic syndrome-related diseases frequently involve disturbances in skeletal muscle lipid metabolism. The accumulation of lipid metabolites, lipid-induced mitochondrial stress in skeletal muscle cells, as well as the inflammation of adjacent adipose tissue, are associated with the development of insulin resistance and metabolic dysfunction. Consequently, when antidiabetic medications are used to treat various chronic conditions related to hyperglycaemia, the impact on skeletal muscle lipid metabolism should not be overlooked.

View Article and Find Full Text PDF

Impact of Frailty on Antihypertensive Treatment in Older Adults.

Hypertension

January 2025

The George Institute for Global Health, Faculty of Medicine, University of New South Wales, Newtown, Australia (L.C., S.Y., N.E., M.W., T.L., Y.G., C.S.A., K.H., X.C., R.P.).

Background: The association between systolic blood pressure and all-cause mortality differs between frail and nonfrail individuals, highlighting uncertainties about the effectiveness of antihypertensive treatments in frail populations.

Methods: Using data from the SHEP trial (Systolic Hypertension in the Elderly Program), a baseline frailty index (FI), including 55 variables, was constructed. Fine-Gray subdistribution hazard models and Cox proportional hazards regression models were used to explore the association between baseline FI and the risks of stroke, cardiovascular disease, and all-cause death, as well as to examine whether the impact of antihypertensive treatment on these outcomes was modified by baseline FI.

View Article and Find Full Text PDF

Objective: This study investigated the association between loss of MSH2/MSH6 versus loss of MLH1/PMS2 expression and overall survival and disease-free survival in patients with localized colorectal cancer.

Background: The risk of developing colorectal cancer varies depending on the expression of mismatch repair proteins. However, it is unknown if the prognosis differs accordingly.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!