Large Language Models for Social Determinants of Health Information Extraction from Clinical Notes - A Generalizable Approach across Institutions.

The consistent and persuasive evidence illustrating the influence of social determinants on health has prompted a growing realization throughout the health care sector that enhancing health and health equity will likely depend, at least to some extent, on addressing detrimental social determinants. However, detailed social determinants of health (SDoH) information is often buried within clinical narrative text in electronic health records (EHRs), necessitating natural language processing (NLP) methods to automatically extract these details. Most current NLP efforts for SDoH extraction have been limited, investigating on limited types of SDoH elements, deriving data from a single institution, focusing on specific patient cohorts or note types, with reduced focus on generalizability. This study aims to address these issues by creating cross-institutional corpora spanning different note types and healthcare systems, and developing and evaluating the generalizability of classification models, including novel large language models (LLMs), for detecting SDoH factors from diverse types of notes from four institutions: Harris County Psychiatric Center, University of Texas Physician Practice, Beth Israel Deaconess Medical Center, and Mayo Clinic. Four corpora of deidentified clinical notes were annotated with 21 SDoH factors at two levels: level 1 with SDoH factor types only and level 2 with SDoH factors along with associated values. Three traditional classification algorithms (XGBoost, TextCNN, Sentence BERT) and an instruction tuned LLM-based approach (LLaMA) were developed to identify multiple SDoH factors. Substantial variation was noted in SDoH documentation practices and label distributions based on patient cohorts, note types, and hospitals. The LLM achieved top performance with micro-averaged F1 scores over 0.9 on level 1 annotated corpora and an F1 over 0.84 on level 2 annotated corpora. While models performed well when trained and tested on individual datasets, cross-dataset generalization highlighted remaining obstacles. To foster collaboration, access to partial annotated corpora and models trained by merging all annotated datasets will be made available on the PhysioNet repository.

Lipids and lipoproteins may play a role in the neuropathology of Alzheimer's disease.

Alzheimer's disease (AD) and other classes of dementia are important public health problems with overwhelming social, physical, and financial effects for patients, society, and their families and caregivers. The pathophysiology of AD is poorly understood despite the extensive number of clinical and experimental studies. The brain's lipid-rich composition is linked to disturbances in lipid homeostasis, often associated with glucose and lipid abnormalities in various neurodegenerative diseases, including AD. Moreover, elevated low-density lipoprotein (LDL) cholesterol levels may be related to a higher probability of AD. Here, we hypothesize that lipids, and electronegative LDL (L5) in particular, may be involved in the pathophysiology of AD. Although changes in cholesterol, triglyceride, LDL, and glucose levels are seen in AD, the cause remains unknown. We believe that L5-the most electronegative subfraction of LDL-may be a crucial factor in understanding the involvement of lipids in AD pathology. LDL and L5 are internalized by cells through different receptors and mechanisms that trigger separate intracellular pathways. One of the receptors involved in L5 internalization, LOX-1, triggers apoptotic pathways. Aging is associated with dysregulation of lipid homeostasis, and it is believed that alterations in lipid metabolism contribute to the pathogenesis of AD. Proposed mechanisms of lipid dysregulation in AD include mitochondrial dysfunction, blood-brain barrier disease, neuronal signaling, inflammation, and oxidative stress, all of which lead ultimately to memory loss through deficiency of synaptic integration. Several lipid species and their receptors have essential functions in AD pathogenesis and may be potential biomarkers.

Patient and Provider Perspectives on Medication Non-adherence Among Patients with Depression and/or Diabetes in Diverse Community Settings - A Qualitative Analysis.

Background: Diabetes and depression affect a significant percentage of the world's total population, and the management of these conditions is critical for reducing the global burden of disease. Medication adherence is crucial for improving diabetes and depression outcomes, and research is needed to elucidate barriers to medication adherence, including the intentionality of non-adherence, to intervene effectively. The purpose of this study was to explore the perspectives of patients and health care providers on intentional and unintentional medication adherence among patients with depression and diabetes through a series of focus groups conducted across clinical settings in a large urban area. Methods: This qualitative study utilized a grounded theory approach to thematically analyze qualitative data using the framework method. Four focus groups in total were conducted, two with patients and two with providers, over a one-year period using a semi-structured facilitation instrument containing open-ended questions about experiences, perceptions and beliefs about medication adherence. Results: Across the focus groups, communication difficulties between patients and providers resulting in medication non-adherence was a primary theme that emerged. Concerns about medication side effects and beliefs about medication effectiveness were identified as perceptual barriers related to intentional medication non-adherence. Practical barriers to medication adherence, including medication costs, forgetting to take medications and polypharmacy, emerged as themes related to unintentional medication non-adherence. Conclusion: The study findings contribute to a growing body of research suggesting health system changes are needed to improve provider education and implement multicomponent interventions to improve medication adherence among patients with depression and/or diabetes, both chronic illnesses accounting for significant disease burden globally.

National Network of Depression Centers' Recommendations on Harmonizing Clinical Documentation of Electroconvulsive Therapy.

ABSTRACT: Electroconvulsive therapy (ECT) is a highly therapeutic and cost-effective treatment for severe and/or treatment-resistant major depression. However, because of the varied clinical practices, there is a great deal of heterogeneity in how ECT is delivered and documented. This represents both an opportunity to study how differences in implementation influence clinical outcomes and a challenge for carrying out coordinated quality improvement and research efforts across multiple ECT centers. The National Network of Depression Centers, a consortium of 26+ US academic medical centers of excellence providing care for patients with mood disorders, formed a task group with the goals of promoting best clinical practices for the delivery of ECT and to facilitate large-scale, multisite quality improvement and research to advance more effective and safe use of this treatment modality. The National Network of Depression Centers Task Group on ECT set out to define best practices for harmonizing the clinical documentation of ECT across treatment centers to promote clinical interoperability and facilitate a nationwide collaboration that would enable multisite quality improvement and longitudinal research in real-world settings. This article reports on the work of this effort. It focuses on the use of ECT for major depressive disorder, which accounts for the majority of ECT referrals in most countries. However, most of the recommendations on clinical documentation proposed herein will be applicable to the use of ECT for any of its indications.

Artificial Intelligence and Chatbots in Psychiatry.

The utilization of artificial intelligence (AI) in psychiatry has risen over the past several years to meet the growing need for improved access to mental health solutions. Additionally, shortages of mental health providers during the COVID-19 pandemic have continued to exacerbate the burden of mental illness worldwide. AI applications already in existence include those enabled to assist with psychiatric diagnoses, symptom tracking, disease course prediction, and psychoeducation. Modalities of AI mental health care delivery include availability through the internet, smartphone applications, and digital gaming. Here we review emerging AI-based interventions in the form of chat and therapy bots, specifically conversational applications that teach the user emotional coping mechanisms and provide support for people with communication difficulties, computer generated images of faces that form the basis of avatar therapy, and intelligent animal-like robots with new advances in digital psychiatry. We discuss the implications of incorporating AI chatbots into clinical practice and offer perspectives on how these AI-based interventions will further impact the field of psychiatry.

Current knowledge and attitudes of psychiatric nurses toward electroconvulsive therapy.

PURPOSE: This study assessed the current knowledge and attitudes of psychiatric nurses toward electroconvulsive therapy (ECT). DESIGN AND METHODS: A quantitative, nonexperimental study was conducted at a large psychiatric hospital in the United States. The Questionnaire on Attitudes and Knowledge (QuAKE) Scale was used to conduct the assessment among a convenient sample of 158 psychiatric nurses. FINDINGS: Participants' responses to questions that elicited knowledge of ECT ranged from 45% to 99% and positive attitudes ranged from 21% to 96%, revealing increased levels when compared with the low to average knowledge and positive attitudes noted in previous studies. PRACTICE IMPLICATIONS: Targeted ECT education is needed among psychiatric nurses with limited knowledge and negative attitudes toward ECT.

A Novel Refractory Mood Disorders and Electroconvulsive Therapy Elective for Medical Students: Fighting Stigma through Experience.

Treatment resistant mood disorders (TRMD) have a significant impact on patients and society. Electroconvulsive therapy (ECT) has been shown to be effective for treatment resistant depression (TRD). Despite the effectiveness and safety of ECT, there remains significant stigma surrounding its use. Studies worldwide have shown that many medical students receive their knowledge from the media, which often portrays ECT in a negative light, and very few have exposure to ECT prior to their psychiatric clinical rotations. In this article we highlight the importance of medical education and introduce a novel approach in helping to fight the stigma of ECT through educational intervention for medical trainees that combines active, longitudinal and theoretical learning. By ensuring that trainees have a robust education in this arena, we can help them educate patients about treatment options, improve confidence in prescribing and administering these therapies, and ultimately improve patient and societal outcomes.

Cross-cultural Comparison of Perceptions and Knowledge About Electroconvulsive Therapy Among Adults Who Screened Positive for Depression in the United States, India, and China.

OBJECTIVE: Despite the established efficacy of electroconvulsive therapy (ECT), negative perceptions and inaccurate knowledge about ECT in the United States and other countries persist. This study examined ECT perceptions and knowledge in the 3 most populous countries in the world. METHODS: We recruited participants who screened positive for depression on the Patient Health Questionnaire 9 (PHQ-9) in the United States (n = 1643), India (n = 1469), and China (n = 328) and compared responses on the ECT-Perception and Knowledge Scale. RESULTS: Although the US sample had significantly higher PHQ-9 scores than the India and China samples, the US sample was less likely to have been offered ECT or to have ever received ECT. Moreover, the US sample scored lower on the ECT Perception and Knowledge subscales than the other samples indicating more negative perceptions and inaccurate knowledge about ECT. Across samples, there were moderate fears about ECT being painful or causing brain damage, and misconceptions about ECT being outdated and adverse effects of induced seizures. Higher PHQ-9 scores were correlated with more negative perceptions. CONCLUSIONS: Greater public education is needed about ECT, particularly in the United States. Misperceptions and lack of knowledge may hinder utilization of ECT in India, China, and the United States.

Birth Seasonality of Schizophrenia and Bipolar Disorder? A Review of Inpatient Records.

BACKGROUND: Numerous studies on seasonality of birth for mood disorders and schizophrenia have been published but findings are inconsistent 1. We aim to test the hypothesis of lack of seasonal birth differences in hospitalized Bipolar Disorder and Schizophrenia patients. METHODS: 15969 inpatient records in UTHealth Harris County Psychiatric Center between 2012-2014 were enrolled (HSC-MS-14-0274). Patients birth months that were diagnosed as Schizophrenia (n=4178) and Bipolar Disorder (n=5303) according to the DSM IV Criteria were tabulated including admitting diagnosis. Texas Birth statistics between 1903-1997 were obtained as control group (n= 17096471). RESULTS: There was no significant difference for winter births between schizophrenia patients and control group (P=0.738) and there was no significant difference for winter births between bipolar patients and control group either (P= 0.862). Mann Kendall Trend Analysis showed no significant trends of birth months for schizophrenia, bipolar and control groups. LIMITATIONS: The study limitations include being a retrospective study, inability to control for environmental factors, and recruiting from a single location. CONCLUSIONS: Our large sample showed no association between birth season or months with schizophrenia or bipolar disorder. Severe schizophrenia that requires admission may not be related with birth seasonality.

Melatonin Receptor Gene Polymorphism in Bipolar-I Disorder.

BACKGROUND AND AIM: In patients with Bipolar-I Disorder (BD-I), circadian rhythm and sleep disorders are frequently observed. Melatonin is a main regulatory hormone for the circadian rhythm. Certain studies have shown the relationship of melatonin receptor gene polymorphism with psychiatric diseases. In this study, it was aimed to investigate the relationship between BD-I and -184T>C (rs2119882) polymorphism in melatonin receptor 1A (MTNR1A) gene and -1193C>T (rs4753426) polymorphism in melatonin receptor 1B (MTNR1B) gene. METHODS: The study included 108 patients diagnosed with BD-I and 95 healthy people as the control group. Real-time PCR (RT-PCR) method was used to evaluate the polymorphism of MTNR1A gene-184T>C. Genotyping of MTNR1B gene-1193C>T polymorphism was done by polymerase chain reaction-restriction fragment length polymorphism (PCR-RFLP). RESULTS: In terms of MTNR1B gene-1193C>T polymorphism, homozygous CC genotype was found to be increased in BD-I patient group compared to the control group (p <0.05). Similarly, a statistically significant difference was found between the patients and the control group in terms of allele frequencies too (p <0.05). However, no relation between BD-I and MTNR1A gene-184T>C polymorphism was found (p >0.05). CONCLUSION: The results of the study revealed that MTNR1B gene-1193C>T polymorphism may play a role in BD-I genetic etiology and may be among the causes of sleep disorder and circadian rhythm disorder seen in these patients.

A case of mirror image agnosia and mirrored self-misidentification syndrome in schizophrenia without dementia or structural abnormalities.

Delusional misidentification syndrome (DMS) is an umbrella term encompassing a variety of disorders. One rare form of DMS is the delusional misidentification of one's own reflection, known as "mirrored self-misidentification syndrome". In "mirror image agnosia", the ability to identify the image of self and/or others in the mirror is lost, while the ability to identify the mirror itself is preserved. To our knowledge, mirror image agnosia has never been described in a patient with schizophrenia. Herein we present a case of a patient with schizophrenia with severe delusions of both mirrored self-misidentification and mirror image agnosia without any structural abnormalities or dementia.

Image of Electroconvulsive Therapy in YouTube Videos.

OBJECTIVES: Image of electroconvulsive therapy (ECT) in TV shows and movies have been studied before. However, there is no study about image of ECT on YouTube as one of the most commonly used social media platforms for disseminating health information. Our study aims to study the image of ECT in YouTube videos. METHODS: Key word "Electroconvulsive therapy and ECT" were used to search on Youtube.com and only videos over 50,000 view counts and in English were selected. Above videos were reviewed by an ECT physician and were classified into neutral, negative, and positive groups based on the image of ECT. RESULTS: There were 41 YouTube videos selected based on the criteria as stated above, among which 14 were unrelated with ECT treatment, 8 were neutral, 9 were positive, and 10 were reflecting negative image about ECT. There was no significant difference among view counts of the positive, negative and neutral videos (χ = 2.746, P = 0.253). Furthermore, the most viewed 3 videos showed negative image of ECT. Additionally, only 6 videos showed the modified ECT and one showed both modified and nonmodified ECT. CONCLUSIONS: This is the first study conducted on image of ECT in YouTube videos. We found the stigma against ECT may persist in digital video platforms, such as YouTube.

Ontological representation-oriented term normalization and standardization of the Research Domain Criteria.

The Research Domain Criteria, launched by the National Institute of Mental Health, is a new dimensional and interdisciplinary research framework for mental disorders. The Research Domain Criteria matrix is its core part. Since an ontology has the strengths of supporting semantic inferencing and automatic data processing, we would like to transform the Research Domain Criteria matrix into an ontological structure. In terms of data normalization, which is the essential part of an ontology representation, the Research Domain Criteria elements (mainly in the Units of Analysis) have some limitations. In this article, we propose a series of solutions to improve data normalization of the Research Domain Criteria elements in the Units of Analysis, including leveraging standard terminologies (i.e. the Unified Medical Language System Metathesaurus), context-combining queries, and domain expertise. The evaluation results show the positive (Yes) percentage is more than 80 percent, indicating our work is favorably received by the mental health professionals, and we have formed a good data foundation for the Research Domain Criteria ontological representation in the future work.

MicroRNA dysregulation in manic and euthymic patients with bipolar disorder.

BACKGROUND: Bipolar disorder (BPD) is a major psychiatric disorder with an unclear pathophysiology. Peripheral blood samples are easily drawn, making them are good candidates for diagnosing diseases. MicroRNAs are small non-coding RNA transcripts that regulate gene expression by binding to the 3'- UTR of mRNAs and directing their degradation. The aim of this study was to use blood plasma to investigate microRNA dysregulations in bipolar manic and euthymic patients. SUBJECTS AND METHODS: Blood samples were collected from 58 patients with bipolar I disorder (19 manic, 39 euthymic) and 51 healthy controls. RESULTS: Four microRNAs (miR-29a-3p, p = 0.035; miR-106b-5p, p = 0.014; miR-107, p = 0.011; and miR-125a-3p, p = 0.014) were upregulated in the entire bipolar group, compared to the healthy controls. Seven microRNAs (miR-9-5p, p = 0.032; miR-29a-3p, p = 0.001; miR-106a-5p, p = 0.034; miR-106b-5p, p = 0.003; miR-107, p < 0.001; miR-125a-3p, p = 0.016; and miR-125b-5p, p = 0.004) were more upregulated in bipolar manic patients compared to the healthy controls, and two microRNAs (miR-106a-5p, p = 0.013, and miR-107, p = 0.021) showed statistically significant upregulation in the manic patients compared to the euthymic patients. CONCLUSIONS: Our results showed greater miRNA dysregulation in the manic patients than in the euthymic patients. Two microRNAs could be more selective for bipolar manic episodes. Future studies should include depressive patients along with euthymic and manic patients.

Brain-Derived Neurotrophic Factor and Oxidative Stress in Cannabis Dependence.

INTRODUCTION: Neurotrophin levels and oxidative stress markers such as ceruloplasmin and free thiols have been shown to contribute to pathophysiology in several psychiatric disorders. OBJECTIVE: Our aim is to evaluate whether those markers are altered in cannabis dependence. METHODS: Forty-five cannabis-dependent patients diagnosed according to the DSM-IV criteria and 45 healthy controls matched according to sex, age, BMI, and smoking status were enrolled. Brain-derived neurotrophic factor (BDNF), ceruloplasmin, lipid hydroperoxide, and total free thiols were measured in both groups. Those who had psychiatric comorbidities were excluded before sampling. RESULTS: We found significantly increased BDNF, ceruloplasmin, and lipid hydroperoxide, and decreased free thiol levels in patients with cannabis dependence. There is also a positive correlation between BDNF and lipid hydroperoxide (n = r = 0.472, p < 0.001) and a negative correlation between BDNF and total thiols (n = r = -0.412, p = 0.001). CONCLUSIONS: Increased BDNF might be a sign of impaired neuronal plasticity that is crucial for memory formation and adaptive response to drug addiction. Neuronal plasticity in the ventral tegmental area dopaminergic neurons was implied to play a role in substance addiction disorders, and these adaptations can be secondary to oxidative stress. Our findings, including increased lipid hydroperoxide, ceruloplasmin, and decreased free thiols, might support this hypothesis. In conclusion, cannabis dependency alters BDNF levels and increases oxidative stress.

Cannabis use: A co-existing condition in first-episode bipolar mania patients.

BACKGROUND: An association between first-episode presentation of bipolar mania and concurrent cannabis use disorder has been well established in the current literature (Bally et al., 2014, Baethge et al., 2008). Previous studies have shown that 30-70% of patients admitted for a first manic episode had concurrent cannabis use (Bally et al., 2014). The exact mechanism of this association has yet to be confirmed. AIMS: We aim to evaluate the prevalence of cannabis use in patients with bipolar disorder (BD) admitted to UTHealth Harris County Psychiatric Center (HCPC) for a first manic episode. METHODS: In this retrospective cohort study, 15,969 inpatient records of patients admitted to HCPC between 2012-2013 were examined to identify patients admitted with a first manic episode according to ICD-9 criteria (single episode mania). The prevalence of multiple sociodemographic and clinical variables including cannabis positivity in urine drug screening (UDS) were examined. RESULTS: Twenty patients were admitted for a first manic episode. Half of the patients were females; mean age was 28.65 ± 10.56 years and mean length of stay (LOS) was 7.15 ± 3.72 days. Fifteen patients received a UDS. Of these fifteen, seven were positive for cannabinoids (47%). One patient was positive for phencyclidine (in addition to cannabis) and one patient was positive for amphetamine (but not cannabis). CONCLUSIONS: The prevalence of cannabis use was higher in first-episode mania patients compared to the general population. The influence of cannabis on the first episode of mania requires additional study.

Geographical access to electroconvulsive therapy services in Texas.

AIMS: Electroconvulsive Therapy (ECT) is a well-established and effective treatment in mood disorders but the use of ECT in Texas is much lower than the general average among the United States. Our goal is to explore the geographical accessibility of Electroconvulsive Services in Texas. METHODS: 22 ECT Centers in Texas listed in State's 2016 annual ECT report were enrolled and georeferenced. We used Esri's StreetMap Premium Network release 1 network dataset to generate 1-hour drive time service areas for these ECTs. We estimated populations within these service areas based on US Census Tract level population-weighted centroids; generated from the 2015, American Community Survey (ACS) estimates at the US Census Block Group level. RESULTS: About 75% (19,851,802 of 26,538,614) of Texas total population is within a 1-hour drive time to any ECT Services location. When focusing on population below the poverty level from 2015 Block Group level ACS data: 68% (3,046,141 of 4,472,451) are within a 1-hour drive time. CONCLUSIONS: ECT services are geographically accessible in Texas. Other barriers may contribute to lower use of ECT.

Psychiatric stressor recognition from clinical notes to reveal association with suicide.

Suicide takes the lives of nearly a million people each year and it is a tremendous economic burden globally. One important type of suicide risk factor is psychiatric stress. Prior studies mainly use survey data to investigate the association between suicide and stressors. Very few studies have investigated stressor data in electronic health records, mostly due to the data being recorded in narrative text. This study takes the initiative to automatically extract and classify psychiatric stressors from clinical text using natural language processing-based methods. Suicidal behaviors were also identified by keywords. Then, a statistical association analysis between suicide ideations/attempts and stressors extracted from a clinical corpus is conducted. Experimental results show that our natural language processing method could recognize stressor entities with an F-measure of 89.01 percent. Mentions of suicidal behaviors were identified with an F-measure of 97.3 percent. The top three significant stressors associated with suicide are health, pressure, and death, which are similar to previous studies. This study demonstrates the feasibility of using natural language processing approaches to unlock information from psychiatric notes in electronic health record, to facilitate large-scale studies about associations between suicide and psychiatric stressors.

Evaluation of Oxidant/Antioxidant Status and Cytokine Levels in Patients with Cannabis Use Disorder.

OBJECTIVE: Cannabis is the most commonly used illegal drug in the world and it has several adverse effects such as anxiety, panic reactions and psychotic symptoms. In this study, we aimed to evaluate oxidant, anti-oxidant status and cytokine levels in individuals with cannabis use disorder. METHODS: Thirty-four patients with cannabis use disorder and 34 healthy controls were enrolled to the study. Serum total antioxidant status, total oxidant status and cytokine levels were investigated in patients with cannabis use disorder and healthy controls. RESULTS: We found increased levels of total oxidant status, oxidative stress index and interleukin (IL) 1ß, IL-6, IL-8, and tumor necrosis factor (TNF) α in individuals with cannabis dependency compared to healthy people. When we compared total antioxidant status, IL-12, and interferon (IFN) γ levels, there were no differences in both groups. There was positive correlation between IL-6 and total oxidant status, oxidative stress index levels. CONCLUSION: The oxidative balance of individuals with cannabis use disorder was impaired and they had higher levels of IL-1ß, IL-6, IL-8, and TNF-α, which is a pro-inflammatory cytokine and indicates increased inflammation compared to healthy controls. Thus, these findings suggest that cannabis increased inflammation and impaired the oxidative balance.