Identifying individual social risk factors using unstructured data in electronic health records and their relationship with adverse clinical outcomes

Rikard, S. Michaela; Kim, Bommae; Michel, Jonathan D.; Peirce, Shayn M.; Barnes, Laura E.; Williams, Michael D.

doi:10.1016/j.ssmph.2022.101210

Cited by 2 publications

(2 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[40][41][42] NLP has emerged as an efficient mechanism for addressing the analytical challenges of extracting SDoH from medical notes. 38,[42][43][44][45][46][47][48][49] In terms of the methods for extracting SDoH information, rule-based, supervised machine learning, and deep learning approaches are the most commonly employed techniques encountered in the vast majority of studies, 42 while multiple publications have used unsupervised approaches or previously developed NLP infrastructure based on lexicons and rules. [50][51][52][53] Despite the growing literature on using NLP algorithms to identify social and behavioral factors for various healthcare outcomes, there is a paucity of investigations comparing various NLP approaches to leveraging SDoH information from unstructured EHRs specifically for patients with ADRD.…”

Section: Introductionmentioning

confidence: 99%

“…SDoH items have been conventionally recorded in physician notes, nurse notes, and other types of unstructured free‐text narratives, but have not been given sufficient priority to be collected and recorded in structured EHR data 40–42 . NLP has emerged as an efficient mechanism for addressing the analytical challenges of extracting SDoH from medical notes 38,42–49 . In terms of the methods for extracting SDoH information, rule‐based, supervised machine learning, and deep learning approaches are the most commonly employed techniques encountered in the vast majority of studies, 42 while multiple publications have used unsupervised approaches or previously developed NLP infrastructure based on lexicons and rules 50–53 .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Wu,

Holkeboer,

Kolawole

et al. 2023

Health Services Research

View full text Add to dashboard Cite

ObjectiveTo 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 SettingWe 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 DesignWe 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 MethodsSocial worker notes used in this study were extracted from the Michigan Medicine EHR database.Principal FindingsOf 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.ConclusionsThe 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.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

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

Wu,

Holkeboer,

Kolawole

et al. 2023

Health Services Research

View full text Add to dashboard Cite

show abstract

Conducting Human Biology Research Using Invasive Clinical Samples: Methods, Strengths, and Limitations

Friedrich,

Hoke,

Schurr

2024

American J Hum Biol

View full text Add to dashboard Cite

Invasive biological samples collected during clinical care represent a valuable yet underutilized source of information about human biology. However, the challenges of working with clinical personnel and the invasive nature of sample collection in biomedical studies can hinder the acquisition of sufficiently large sample sizes for robust statistical analyses. In addition, the incorporation of demographic data from participants is crucial for ensuring the inclusiveness of representative populations, identifying at‐risk groups, and addressing healthcare disparities. Drawing on both research experiences and the existing literature, this article provides recommendations for researchers aiming to undertake efficient and impactful projects involving invasive human samples. The suggested strategies include: (1) establishing productive collaborations with clinicians; (2) optimizing sample quality through meticulous collection and handling procedures; and (3) strategically implementing a retrospective model to capitalize on existing invasive sample repositories. When established, cooperative work between clinical health care workers and biological anthropologists can yield insights into human biology that have the potential to improve human health and wellbeing.

show abstract

Identifying individual social risk factors using unstructured data in electronic health records and their relationship with adverse clinical outcomes

Cited by 2 publications

References 30 publications

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

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

Conducting Human Biology Research Using Invasive Clinical Samples: Methods, Strengths, and Limitations

Contact Info

Product

Resources

About