Braja Gopal Patra

Background: Postpartum depression (PPD) remains vastly underdiagnosed, and its clinical heterogeneity is not well understood. Diagnosis codes in electronic health records (EHRs) alone may not identify all PPD cases, highlighting a need for novel detection approaches. Objective: To develop a transformer-based natural language processing (NLP) method to identify patients with PPD from clinical notes in EHRs and to examine demographic and clinical heterogeneity among identified cases. Methods: Clinical notes from 64 426 patients who gave birth between 2010 and 2023 at a major US academic medical centre were used to develop and evaluate the NLP method. By augmenting the NLP output with International Classification of Diseases (ICD-9/10) diagnosis codes, three subgroups of individuals with PPD were identified: patients identified by ICD only (PPD-ICD), NLP only (PPD-NLP) and both ICD and NLP (PPD-BOTH). Demographics, mental health and substance use disorders (SUDs), antidepressant treatment, behavioural therapy and healthcare utilisation were compared across PPD subgroups and a non-PPD control group. Longitudinal associations of depression and anxiety were also examined. Findings: The NLP method identified an additional 29.6% of patients whose clinical notes indicated symptoms suggestive of PPD but who lacked an ICD diagnosis. Significant variation was observed among PPD subgroups in comorbid psychiatric disorders, SUDs, treatment patterns and healthcare utilisation. During the 24 months post-delivery, the PPD-BOTH subgroup exhibited the highest rates of anxiety disorder diagnoses (vs PPD-ICD: OR 1.69, 95% CI 1.49 to 1.93; vs PPD-NLP: OR 4.46, 95% CI 3.82 to 5.22), antidepressant prescriptions (vs PPD-ICD: OR 1.95, 95% CI 1.71 to 2.22; vs PPD-NLP: OR 5.98, 95% CI 5.11 to 7.01) and mental health outpatient visits (vs PPD-ICD: OR 1.45, 95% CI 1.24 to 1.7; vs PPD-NLP: OR 4.94, 95% CI 3.9 to 6.31), suggesting higher symptom severity (all p<0.001). Comorbid depression and anxiety diagnoses were most prevalent during the postpartum period and declined over time. Conclusions: Augmenting NLP-based identification with ICD codes yielded more individuals with distinct demographic and clinical profiles, demonstrating the method’s ability to improve case detection and characterise heterogeneity. Clinical implications: Given that PPD is underdiagnosed and undertreated, this novel approach demonstrates further potential for NLP in healthcare settings to capture more cases, enabling earlier and more personalised interventions that reach patients who may otherwise be overlooked.

Social support (SS) and social isolation (SI) are social determinants of health (SDOH) associated with psychiatric outcomes. In electronic health records (EHRs), individual-level SS/SI is typically documented in narrative clinical notes rather than as structured coded data. Natural language processing (NLP) algorithms can automate the otherwise labor-intensive process of extraction of such information. Psychiatric encounter notes from Mount Sinai Health System (MSHS, n = 300) and Weill Cornell Medicine (WCM, n = 225) were annotated to create a gold-standard corpus. A rule-based system (RBS) involving lexicons and a large language model (LLM) using FLAN-T5-XL were developed to identify mentions of SS and SI and their subcategories (eg, social network, instrumental support, and loneliness). For extracting SS/SI, the RBS obtained higher macroaveraged F1-scores than the LLM at both MSHS (0.89 versus 0.65) and WCM (0.85 versus 0.82). For extracting the subcategories, the RBS also outperformed the LLM at both MSHS (0.90 versus 0.62) and WCM (0.82 versus 0.81). Unexpectedly, the RBS outperformed the LLMs across all metrics. An intensive review demonstrates that this finding is due to the divergent approach taken by the RBS and LLM. The RBS was designed and refined to follow the same specific rules as the gold-standard annotations. Conversely, the LLM was more inclusive with categorization and conformed to common English-language understanding. Both approaches offer advantages, although additional replication studies are warranted.

Personal and family history of suicidal thoughts and behaviors (PSH and FSH, respectively) are significant risk factors associated with suicides. Research is limited in automatic identification of such data from clinical notes in Electronic Health Records. This study developed deep learning (DL) tools utilizing transformer models (Bio_ClinicalBERT and GatorTron) to detect PSH and FSH in clinical notes derived from three academic medical centers, and compared their performance with a rule-based natural language processing tool. For detecting PSH, the rule-based approach obtained an F1-score of 0.75 ± 0.07, while the Bio_ClinicalBERT and GatorTron DL tools scored 0.83 ± 0.09 and 0.84 ± 0.07, respectively. For detecting FSH, the rule-based approach achieved an F1-score of 0.69 ± 0.11, compared to 0.89 ± 0.10 for Bio_ClinicalBERT and 0.92 ± 0.07 for GatorTron. Across sites, the DL tools identified more than 80% of patients at elevated risk for suicide who remain undiagnosed and untreated.

A scholarly recommendation system is an important tool for identifying prior and related resources such as literature, datasets, grants, and collaborators. A well-designed scholarly recommender significantly saves the time of researchers and can provide information that would not otherwise be considered. The usefulness of scholarly recommendations, especially literature recommendations, has been established by the widespread acceptance of web search engines such as CiteSeerX, Google Scholar, and Semantic Scholar. This article discusses different aspects and developments of scholarly recommendation systems. We searched the ACM Digital Library, DBLP, IEEE Explorer, and Scopus for publications in the domain of scholarly recommendations for literature, collaborators, reviewers, conferences and journals, datasets, and grant funding. In total, 225 publications were identified in these areas. We discuss methodologies used to develop scholarly recommender systems. Content-based filtering is the most commonly applied technique, whereas collaborative filtering is more popular among conference recommenders. The implementation of deep learning algorithms in scholarly recommendation systems is rare among the screened publications. We found fewer publications in the areas of the dataset and grant funding recommenders than in other areas. Furthermore, studies analyzing users’ feedback to improve scholarly recommendation systems are rare for recommenders. This survey provides background knowledge regarding existing research on scholarly recommenders and aids in developing future recommendation systems in this domain.

BACKGROUND Creating credible and engaging health communication materials is knowledge- and labor-intensive. OBJECTIVE We propose a low-cost alternative by classifying lay health articles by relevance and topic using natural language processing (NLP). METHODS With postpartum depression as a case study, we conducted a manual review of online lay articles to classify articles on their relevance to pregnancy and topics. To scale the classification process on relevance and topics, we built models using Bidirectional Encoder Representations from Transformers (BERT), Generative Pre-trained Transformer model (ChatGPT), and Random Forest. RESULTS The gold standard corpus included 392 articles. A BERT-based model performed best (F1= 0.974) in an end-to-end classification of relevance and topics. In a two-step approach, given articles already classified as related to pregnancy, ChatGPT was best (F1 = 0.972) in classifying topics. CONCLUSIONS With NLP, we may repurpose lay reading materials as low-cost and easily accessible health education and communication sources.

Research grants are important for researchers to sustain a good position in academia. There are many grant opportunities available from different funding agencies. However, finding relevant grant announcements is challenging and time-consuming for researchers. To resolve the problem, we proposed a grant announcements recommendation system for the National Institute of Health (NIH) grants using researchers’ publications. We formulated the recommendation as a classification problem and proposed a recommender using state-of-the-art deep learning techniques: i.e. Bidirectional Encoder Representations from Transformers (BERT), to capture intrinsic, non-linear relationship between researchers’ publications and grants announcements. Internal and external evaluations were conducted to assess the system’s usefulness. During internal evaluations, the grant citations were used to establish grant-publication ground truth, and results were evaluated against Recall@k, Precision@k, Mean reciprocal rank (MRR) and Area under the Receiver Operating Characteristic curve (ROC-AUC). During external evaluations, researchers’ publications were clustered using Dirichlet Process Mixture Model (DPMM), recommended grants by our model were then aggregated per cluster through Recency Weight, and finally researchers were invited to provide ratings to recommendations to calculate Precision@k. For comparison, baseline recommenders using Okapi Best Matching (BM25), Term-Frequency Inverse Document Frequency (TF-IDF), doc2vec, and Naïve Bayes (NB) were also developed. Both internal and external evaluations (all metrics) revealed favorable performances of our proposed BERT-based recommender.

Public health and epidemiologic research have established that social connectedness promotes overall health. Yet there have been no recent reviews of findings from research examining social connectedness as a determinant of mental health. The goal of this review was to evaluate recent longitudinal research probing the effects of social connectedness on depression and anxiety symptoms and diagnoses in the general population. A scoping review was performed of PubMed and PsychInfo databases from January 2015 to December 2021 following PRISMA-ScR guidelines using a defined search strategy. The search yielded 66 unique studies. In research with other than pregnant women, 83% (19 of 23) studies reported that social support benefited symptoms of depression with the remaining 17% (5 of 23) reporting minimal or no evidence that lower levels of social support predict depression at follow-up. In research with pregnant women, 83% (24 of 29 studies) found that low social support increased postpartum depressive symptoms. Among 8 of 9 studies that focused on loneliness, feeling lonely at baseline was related to adverse outcomes at follow-up including higher risks of major depressive disorder, depressive symptom severity, generalized anxiety disorder, and lower levels of physical activity. In 5 of 8 reports, smaller social network size predicted depressive symptoms or disorder at follow-up. In summary, most recent relevant longitudinal studies have demonstrated that social connectedness protects adults in the general population from depressive symptoms and disorders. The results, which were largely consistent across settings, exposure measures, and populations, support efforts to improve clinical detection of high-risk patients, including adults with low social support and elevated loneliness.

Objective: Social determinants of health (SDoH) are nonclinical dispositions that impact patient health risks and clinical outcomes. Leveraging SDoH in clinical decision-making can potentially improve diagnosis, treatment planning, and patient outcomes. Despite increased interest in capturing SDoH in electronic health records (EHRs), such information is typically locked in unstructured clinical notes. Natural language processing (NLP) is the key technology to extract SDoH information from clinical text and expand its utility in patient care and research. This article presents a systematic review of the state-of-the-art NLP approaches and tools that focus on identifying and extracting SDoH data from unstructured clinical text in EHRs. Materials and Methods: A broad literature search was conducted in February 2021 using 3 scholarly databases (ACL Anthology, PubMed, and Scopus) following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A total of 6402 publications were initially identified, and after applying the study inclusion criteria, 82 publications were selected for the final review. Results: Smoking status (n = 27), substance use (n = 21), homelessness (n = 20), and alcohol use (n = 15) are the most frequently studied SDoH categories. Homelessness (n = 7) and other less-studied SDoH (eg, education, financial problems, social isolation and support, family problems) are mostly identified using rule-based approaches. In contrast, machine learning approaches are popular for identifying smoking status (n = 13), substance use (n = 9), and alcohol use (n = 9). Conclusion: NLP offers significant potential to extract SDoH data from narrative clinical notes, which in turn can aid in the development of screening tools, risk prediction models, and clinical decision support systems.