Detection of Personal and Family History of Suicidal Thoughts and Behaviors using Deep Learning and Natural Language Processing: A Multi-Site Study.

Objective: Personal and family history of suicidal thoughts and behaviors (PSH and FSH, respectively) are significant risk factors associated with future suicide events. These are often captured in narrative clinical notes in electronic health records (EHRs). Collaboratively, Weill Cornell Medicine (WCM), Northwestern Medicine (NM), and the University of Florida (UF) developed and validated deep learning (DL)-based natural language processing (NLP) tools to detect PSH and FSH from such notes. The tool's performance was further benchmarked against a method relying exclusively on ICD-9/10 diagnosis codes. Materials and Methods: We developed DL-based NLP tools utilizing pre-trained transformer models Bio_ClinicalBERT and GatorTron, and compared them with expert-informed, rule-based methods. The tools were initially developed and validated using manually annotated clinical notes at WCM. Their portability and performance were further evaluated using clinical notes at NM and UF. Results: The DL tools outperformed the rule-based NLP tool in identifying PSH and FHS. For detecting PSH, the rule-based system 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 NLP tool's F1-score was 0.69 ± 0.11, compared to 0.89 ± 0.10 for Bio_ClinicalBERT and 0.92 ± 0.07 for GatorTron. For the gold standard corpora across the three sites, only 2.2% (WCM), 9.3% (NM), and 7.8% (UF) of patients reported to have an ICD-9/10 diagnosis code for suicidal thoughts and behaviors prior to the clinical notes report date. The best performing GatorTron DL tool identified 93.0% (WCM), 80.4% (NM), and 89.0% (UF) of patients with documented PSH, and 85.0%(WCM), 89.5%(NM), and 100%(UF) of patients with documented FSH in their notes. Discussion: While PSH and FSH are significant risk factors for future suicide events, little effort has been made previously to identify individuals with these history. To address this, we developed a transformer based DL method and compared with conventional rule-based NLP approach. The varying effectiveness of the rule-based tools across sites suggests a need for improvement in its dictionary-based approach. In contrast, the performances of the DL tools were higher and comparable across sites. Furthermore, DL tools were fine-tuned using only small number of annotated notes at each site, underscores its greater adaptability to local documentation practices and lexical variations. Conclusion: Variations in local documentation practices across health care systems pose challenges to rule-based NLP tools. In contrast, the developed DL tools can effectively extract PSH and FSH information from unstructured clinical notes. These tools will provide clinicians with crucial information for assessing and treating patients at elevated risk for suicide who are rarely been diagnosed.

Identification and assessment of classification criteria attributes for systemic lupus erythematosus in a regional medical record data network.

OBJECTIVE: To assess the application and utility of algorithms designed to detect features of SLE in electronic health record (EHR) data in a multisite, urban data network. METHODS: Using the Chicago Area Patient-Centered Outcomes Research Network (CAPriCORN), a Clinical Data Research Network (CDRN) containing data from multiple healthcare sites, we identified patients with at least one positively identified criterion from three SLE classification criteria sets developed by the American College of Rheumatology (ACR) in 1997, the Systemic Lupus International Collaborating Clinics (SLICC) in 2012, and the European Alliance of Associations for Rheumatology and the ACR in 2019 using EHR-based algorithms. To measure the algorithms' performance in this data setting, we first evaluated whether the number of clinical encounters for SLE was associated with a greater quantity of positively identified criteria domains using Poisson regression. We next quantified the amount of SLE criteria identified at a single healthcare institution versus all sites to assess the amount of SLE-related information gained from implementing the algorithms in a CDRN. RESULTS: Patients with three or more SLE encounters were estimated to have documented 2.77 (2.73 to 2.80) times the number of positive SLE attributes from the 2012 SLICC criteria set than patients without an SLE encounter via Poisson regression. Patients with three or more SLE-related encounters and with documented care from multiple institutions were identified with more SLICC criteria domains when data were included from all CAPriCORN sites compared with a single site (p<0.05). CONCLUSIONS: The positive association observed between amount of SLE-related clinical encounters and the number of criteria domains detected suggests that the algorithms used in this study can be used to help describe SLE features in this data environment. This work also demonstrates the benefit of aggregating data across healthcare institutions for patients with fragmented care.

2-hydroxy-1,4-naphthoquinones with 3-alkyldiarylether groups: synthesis and Plasmodium falciparum inhibitory activity.

Background: In 1948, the synthesis and Plasmodium lophurae activity of 2-hydroxy-1,4-naphthoquinones containing 3-alkyldiarylether side chains was reported. Method/results: The synthesis of five related compounds, designed to be more metabolically stable, was pursued. The compounds were synthesized using a radical alkylation reaction with naphthoquinones. One compound had a lower IC50 value against various strains of Plasmodium falciparum and assay data indicate that it binds to the Qo site of cytochrome bc1. With a low yield for the radical alkylation of the most active compound, a reductive alkylation method with used to improve reaction yields. Conclusion: Further synthetic knowledge was obtained, and the assay data indicate that there are sensitivity differences between avian and human malarial parasites for these molecules.

Malaria is a disease caused by a parasite that affects millions of people each year and results in many deaths. In 1948, 300 structurally related compounds were made and tested for antimalarial activity with the goal of finding a drug to treat the disease. From this work, promising compounds were identified and this work has served as a starting point for further investigations. Based on recent discoveries, this study made variations of promising 1948 compounds to investigate whether antimalarial activity could be improved. These compounds were made using two different methods. One derivative was found to be more potent than the original compound but was not the one expected based on the 1948 work.

Electronic health record data use in the assessment of quality indicators for glucocorticoid osteoporosis screening in systemic lupus erythematosus.

OBJECTIVE: To determine whether electronic health record (EHR) data components could be identified and used to assess bone health quality indicators in patients with systemic lupus erythematosus as a foundation for population health management. METHODS: We identified patients in our EHR system who had diagnosis codes for lupus from 2012 to 2017 and characterized them based on the frequency and dosage of prescribed glucocorticoid medications. The medical records of patients who received repeated high-dose glucocorticoid orders were further reviewed for osteoporosis, osteoporotic fractures, receipt of appropriate preventive screening, and orders for protective medications based on established quality indicators. Descriptive statistics were calculated to summarize results. RESULTS: We identified 617 patients with a lupus diagnosis; 414 received glucocorticoid prescriptions, 189 received chronic, high-dose; and 83 received chronic, low-dose prescription orders. Of those with chronic high-dose glucocorticoid prescriptions, 14% had an osteoporosis diagnosis, 3% had an osteoporotic fracture, 51% received a prescription for calcium/vitamin D, 43% had bone mineral density screening orders, 20% received a spine radiograph order, 29% had a documented T-score, 12% received a prescription for osteoporosis medication, and 6% had a documented osteoporosis screening. We were able to identify data elements in the EHR for all nine components of the osteoporosis management quality indicator. CONCLUSIONS: It is possible to identify data in the EHR for all attributes of the quality indicator for osteoporosis in lupus patients who receive chronic high-dose glucocorticoids. However, missing data and need to extract data from text-based notes may make development of population management tools challenging.