Characterizing suicidal ideation, suicidal behaviors, and service utilization among unhoused individuals using a health information exchange.

INTRODUCTION: Unhoused individuals have high rates of suicidal ideation (SI) and suicidal behaviors (SB), but few have studied the relative timing of homelessness and SI/SB. Our study examines the potential to use state-wide electronic health record data from Rhode Island's health information exchange (HIE) to identify temporal relationships, service utilization, and associations of SI/SB among unhoused individuals. METHODS: We use timestamped HIE data for 5368 unhoused patients to analyze service utilization and the relative timing of homelessness versus SI/SB onset. Multivariable models identified associations of SI/SB, hospitalization, and repeat acute care utilization within 30 days from clinical features representing 10,000+ diagnoses captured within the HIE. RESULTS: The onset of SI typically precedes homelessness onset, while the onset of SB typically follows. Weekly rates of suicide-related service utilization increased over 25 times the baseline rate during the week before and after homelessness onset. Over 50% of encounters involving SI/SB result in hospitalization. Of those engaging in acute care for suicide-related reasons, we found high rates of repeat acute care encounters. CONCLUSION: HIEs are a particularly valuable resource for understudied populations. Our study demonstrates how longitudinal, multi-institutional data from an HIE can be used to characterize temporal associations, service utilization, and clinical associations of SI and behaviors among a vulnerable population at scale. Increasing access to services that address co-occurring SI/SB, mental health, and substance use is needed.

Characterizing Autism Spectrum Disorder and Predicting Suicide Risk for Pediatric Psychiatric Emergency Services Encounters.

Individuals diagnosed with autism spectrum disorder (ASD) are at a higher risk for mental health concerns including suicidal thoughts and behaviors (STB). Limited studies have focused on suicidal risk factors that are more prevalent or unique to the population with ASD. This study sought to characterize and classify youth presenting to the psychiatric emergency department (ED) for a chief complaint of STB. The results of this study validated that a high number of patients with ASD present to the ED with STB. There were important differences in clinical characteristics to those with ASD versus those without. Clinical features that showed important impact in predicting high suicide risk in the ASD cases include elements of the mental status exam such as affect, trauma symptoms, abuse history, and auditory hallucinations. Focused attention is needed on these unique differences in ASD cases so that suicide risk level can be appropriately and promptly addressed.

The role of H3K9 acetylation and gene expression in different brain regions of Alzheimer's disease patients.

Aims: To evaluate H3K9 acetylation and gene expression profiles in three brain regions of Alzheimer's disease (AD) patients and elderly controls, and to identify AD region-specific abnormalities. Methods: Brain samples of auditory cortex, hippocampus and cerebellum from AD patients and controls underwent chromatin immunoprecipitation sequencing, RNA sequencing and network analyses. Results: We found a hyperacetylation of AD cerebellum and a slight hypoacetylation of AD hippocampus. The transcriptome revealed differentially expressed genes in the hippocampus and auditory cortex. Network analysis revealed Rho GTPase-mediated mechanisms. Conclusions: These findings suggest that some crucial mechanisms, such as Rho GTPase activity and cytoskeletal organization, are differentially dysregulated in brain regions of AD patients at the epigenetic and transcriptomic levels, and might contribute toward future research on AD pathogenesis.

Alzheimer's disease (AD) is the most common form of dementia affecting the elderly population. The onset and progression of AD are influenced by environmental factors, which are able to promote epigenetic changes on the DNA and/or the DNA-associated proteins called histones. We investigated a specific epigenetic modification of histones (H3K9 acetylation) in three brain regions of AD patients and compared them with elderly controls. We found increased levels of H3K9 acetylation in the cerebellum of AD patients, as well as a slight decrease of this modification in the hippocampus of the same patients. These brain tissues from AD patients showed abnormal gene expression patterns when compared with elderly controls. These findings contribute to understanding the molecular changes that occur in AD, and provide a basis for future research or drug development for AD treatment.

The effect of levetiracetam treatment on survival in patients with glioblastoma: a systematic review and meta-analysis.

BACKGROUND: Levetiracetam (LEV) is an anti-epileptic drug (AED) that sensitizes glioblastoma (GBM) to temozolomide (TMZ) chemotherapy by inhibiting O6-methylguanine-DNA methyltransferase (MGMT) expression. Adding LEV to the standard of care (SOC) for GBM may improve TMZ efficacy. This study aimed to pool the existing evidence in the literature to quantify LEV's effect on GBM survival and characterize its safety profile to determine whether incorporating LEV into the SOC is warranted. METHOD: A search of CINAHL, Embase, PubMed, and Web of Science from inception to May 2021 was performed to identify relevant articles. Hazard ratios (HR), median overall survival, and adverse events were pooled using random-effect models. Meta-regression, funnel plots, and the Newcastle-Ottawa Scale were utilized to identify sources of heterogeneity, bias, and statistical influence. RESULTS: From 20 included studies, 5804 GBM patients underwent meta-analysis, of which 1923 (33%) were treated with LEV. Administration of LEV did not significantly improve survival in the entire patient population (HR 0.89, p = 0.094). Significant heterogeneity was observed during pooling of HRs (I2 = 75%, p < 0.01). Meta-regression determined that LEV treatment effect decreased with greater rates of MGMT methylation (RC = 0.03, p = 0.02) and increased with greater proportions of female patients (RC = - 0.05, p = 0.002). Concurrent LEV with the SOC for GBM did not increase odds of adverse events relative to other AEDs. CONCLUSIONS: Levetiracetam treatment may not be effective for all GBM patients. Instead, LEV may be better suited for treating specific molecular profiles of GBM. Further studies are necessary to identify optimal GBM candidates for LEV.

An Unsupervised Cluster Analysis of Post-COVID-19 Mental Health Outcomes and Associated Comorbidities.

The COVID-19 pandemic continues to be widespread, and little is known about mental health impacts from dealing with the disease itself. This retrospective study used a deidentified health information exchange (HIE) dataset of electronic health record data from the state of Rhode Island and characterized different subgroups of the positive COVID-19 population. Three different clustering methods were explored to identify patterns of condition groupings in this population. Increased incidence of mental health conditions was seen post-COVID-19 diagnosis, and these individuals exhibited higher prevalence of comorbidities compared to the negative control group. A self-organizing map cluster analysis showed patterns of mental health conditions in half of the clusters. One mental health cluster revealed a higher comorbidity index and higher severity of COVID-19 disease. The clinical features identified in this study motivate the need for more in-depth analysis to predict and identify individuals at high risk for developing mental illness post-COVID-19 diagnosis.

Predicting open wound mortality in the ICU using machine learning.

BACKGROUND: Open wounds have a significant impact on the health of patients causing pain, loss of function, and death. Labeled as a comorbid condition, open wounds represent a "silent epidemic" that affect a large portion of the US population. Due to their burden of care, open wound patients face an increased risk of ICU stay and mortality. There is a dearth of studies that investigate mortality among wound patients in the ICU. We sought to develop a model that predicts the risk of mortality among wound patients in the ICU. METHODS: Random forest and binomial logistic regression models were developed to predict the risk of mortality among open wound patients in the Medical Information Mart for Intensive Care III (MIMIC-III) database. MIMIC-III includes de-identified data for patients who stayed in critical care units of the Beth Israel Deaconess Medical Center between 2001 and 2012. Six variables were used to develop the model (wound location, gender, age, admission type, minimum platelet count and hyperphosphatemia). The Charlson Comorbidity Index (CCI) and Elixhauser Comorbidity Index were used to assess model strength. RESULTS: A total of 3,937 patients were included with a mean age of 76.57. Of those, 3,372 (85%) survived and 565 (15%) died during their ICU stay. The random forest model achieved an area under the curve (AUC) of 0.924. The CCI and Elixhauser models resulted in AUC of 0.528 and 0.565, respectively. CONCLUSIONS: Machine learning models may allow clinicians to provide better care and management to open wound patients in the ICU.

Clinical Note Section Detection Using a Hidden Markov Model of Unified Medical Language System Semantic Types.

Clinical notes are a rich source of biomedical data for natural language processing (NLP). The identification of note sections represents a first step in creating portable NLP tools. Here, a system that used a heterogeneous hidden Markov model (HMM) was designed to identify seven note sections: (1) Medical History, (2) Medications, (3) Family and Social History, (4) Physical Exam, (5) Labs and Imaging, (6) Assessment and Plan, and (7) Review of Systems. Unified Medical Language System (UMLS) concepts were identified using MetaMap, and UMLS semantic type distributions for each section type were empirically determined. The UMLS semantic type distributions were used to train the HMM for identifying clinical note sections. The system was evaluated relative to a template boundary model using manually annotated notes from the Medical Information Mart for Intensive Care III. The results show promise for an approach to segment clinical notes into sections for subsequent NLP tasks.

Applying FAIR Principles to Improve Data Searchability of Emergency Department Datasets: A Case Study for HCUP-SEDD.

BACKGROUND: There is a recognized need to improve how scholarly data are managed and accessed. The scientific community has proposed the findable, accessible, interoperable, and reusable (FAIR) data principles to address this issue. OBJECTIVE: The objective of this case study was to develop a system for improving the FAIRness of Healthcare Cost and Utilization Project's State Emergency Department Databases (HCUP's SEDD) within the context of data catalog availability. METHODS: A search tool, EDCat (Emergency Department Catalog), was designed to improve the "FAIRness" of electronic health databases and tested on datasets from HCUP-SEDD. ElasticSearch was used as a database for EDCat's search engine. Datasets were curated and defined. Searchable data dictionary-related elements and unified medical language system (UMLS) concepts were included in the curated metadata. Functionality to standardize search terms using UMLS concepts was added to the user interface. RESULTS: The EDCat system improved the overall FAIRness of HCUP-SEDD by improving the findability of individual datasets and increasing the efficacy of searches for specific data elements and data types. DISCUSSION: The databases considered for this case study were limited in number as few data distributors make the data dictionaries of datasets available. The publication of data dictionaries should be encouraged through the FAIR principles, and further efforts should be made to improve the specificity and measurability of the FAIR principles. CONCLUSION: In this case study, the distribution of datasets from HCUP-SEDD was made more FAIR through the development of a search tool, EDCat. EDCat will be evaluated and developed further to include datasets from other sources.

Machine Learning Offers Exciting Potential for Predicting Postprocedural Outcomes: A Framework for Developing Random Forest Models in IR.

PURPOSE: To demonstrate that random forest models trained on a large national sample can accurately predict relevant outcomes and may ultimately contribute to future clinical decision support tools in IR. MATERIALS AND METHODS: Patient data from years 2012-2014 of the National Inpatient Sample were used to develop random forest machine learning models to predict iatrogenic pneumothorax after computed tomography-guided transthoracic biopsy (TTB), in-hospital mortality after transjugular intrahepatic portosystemic shunt (TIPS), and length of stay > 3 days after uterine artery embolization (UAE). Model performance was evaluated with area under the receiver operating characteristic curve (AUROC) and maximum F1 score. The threshold for AUROC significance was set at 0.75. RESULTS: AUROC was 0.913 for the TTB model, 0.788 for the TIPS model, and 0.879 for the UAE model. Maximum F1 score was 0.532 for the TTB model, 0.357 for the TIPS model, and 0.700 for the UAE model. The TTB model had the highest AUROC, while the UAE model had the highest F1 score. All models met the criteria for AUROC significance. CONCLUSIONS: This study demonstrates that machine learning models may suitably predict a variety of different clinically relevant outcomes, including procedure-specific complications, mortality, and length of stay. Performance of these models will improve as more high-quality IR data become available.

Characterization of Cerebellum-Specific Ribosomal DNA Epigenetic Modifications in Alzheimer's Disease: Should the Cerebellum Serve as a Control Tissue After All?

Alzheimer's disease (AD) is a neurodegenerative disease, known as the most common form of dementia. In AD onset, abnormal rRNA expression has been reported to be linked in pathogenesis. Although region-specific expression patterns have previously been reported in AD, it is not until recently that the cerebellum has come under the spotlight. Specifically, it is unclear whether DNA methylation is the mechanism involved in rRNA expression regulation in AD. Hence, we sought to explore the rDNA methylation pattern of two different brain regions - auditory cortex and cerebellum - from AD and age-/sex-matched controls. Our results showed differential hypermethylation at an upstream CpG region to the rDNA promoter when comparing cerebellum controls to auditory cortex controls. This suggests a possible regulatory region from rDNA expression regulation. Moreover, when comparing between AD and control cerebellum samples, we observed hypermethylation of the rDNA promoter region as well as an increase in rDNA content. In addition, we also observed increased rRNA levels in AD compared to control cerebellum. Although still considered a pathology-free brain region, there are growing findings that continue to suggest otherwise. Indeed, cerebellum from AD has been recently described as affected by the disease, presenting a unique pattern of molecular alterations. Given that we observed that increased rDNA promoter methylation did not silence rDNA gene expression, we suggest that rDNA promoter hypermethylation is playing a protective role in rDNA genomic stability and, therefore, increasing rRNA levels in AD cerebellum.

Mental Health Comorbidity Analysis in Pediatric Patients with Autism Spectrum Disorder Using Rhode Island Medical Claims Data.

Identification of comorbidity subgroups linked with Autism Spectrum Disorder (ASD) could provide promising insight into learning more about this disorder. This study sought to use the Rhode Island All-Payer Claims Database to examine mental health conditions linked to ASD. Medical claims data for ASD patients and one or more mental health conditions were analyzed using descriptive statistics, association rule mining (ARM), and sequential pattern mining (SPM). The results indicated that patients with ASD have a higher proportion of mental health diagnoses than the general pediatric population. ARM and SPM methods identified patterns of comorbidities commonly seen among ASD patients. Based on the observed patterns and temporal sequences, suicidal ideation, mood disorders, anxiety, and conduct disorders may need focused attention prospectively. Understanding more about groupings of ASD patients and their comorbidity burden can help bridge gaps in knowledge and make strides toward improved outcomes for patients with ASD.

Selection of Clinical Text Features for Classifying Suicide Attempts.

Research has demonstrated cohort misclassification when studies of suicidal thoughts and behaviors (STBs) rely on ICD-9/10-CM diagnosis codes. Electronic health record (EHR) data are being explored to better identify patients, a process called EHR phenotyping. Most STB phenotyping studies have used structured EHR data, but some are beginning to incorporate unstructured clinical text. In this study, we used a publicly-accessible natural language processing (NLP) program for biomedical text (MetaMap) and iterative elastic net regression to extract and select predictive text features from the discharge summaries of 810 inpatient admissions of interest. Initial sets of 5,866 and 2,709 text features were reduced to 18 and 11, respectively. The two models fit with these features obtained an area under the receiver operating characteristic curve of 0.866-0.895 and an area under the precision-recall curve of 0.800-0.838, demonstrating the approach's potential to identify textual features to incorporate in phenotyping models.

Extracting Angina Symptoms from Clinical Notes Using Pre-Trained Transformer Architectures.

Anginal symptoms can connote increased cardiac risk and a need for change in cardiovascular management. In this study, a pre-trained transformer architecture was used to automatically detect and characterize anginal symptoms from within the history of present illness sections of 459 primary care physician notes. Consecutive patients referred for cardiac testing were included. Notes were annotated for positive and negative mentions of chest pain and shortness of breath characterization. The results demonstrate high sensitivity and specificity for the detection of chest pain or discomfort, substernal chest pain, shortness of breath, and dyspnea on exertion. Model performance extracting factors related to provocation and palliation of chest pain were limited by small sample size. Overall, this study shows that pre-trained transformer architectures have promise in automating the extraction of anginal symptoms from clinical texts.

Coding Free-Text Chief Complaints from a Health Information Exchange: A Preliminary Study.

Chief complaints are important textual data that can serve to enrich diagnosis and symptom data in electronic health record (EHR) systems. In this study, a method is presented to preprocess chief complaints and assign corresponding ICD-10-CM codes using the MetaMap natural language processing (NLP) system and Unified Medical Language System (UMLS) Metathesaurus. An exploratory analysis was conducted using a set of 7,942 unique chief complaints from the statewide health information exchange containing EHR data from hospitals across Rhode Island. An evaluation of the proposed method was then performed using a set of 123,086 chief complaints with corresponding ICD-10-CM encounter diagnoses. With 87.82% of MetaMap-extracted concepts correctly assigned, the preliminary findings support the potential use of the method explored in this study for improving upon existing NLP techniques for enabling use of data captured within chief complaints to support clinical care, research, and public health surveillance.

Web-Based Visualization of MeSH-Based PubMed/MEDLINE Statistics.

Statistical analysis of Medical Subject Headings (MeSH) descriptors to improve biomedical literature search is an active research area. Existing tools have limited interactive visualizations that are accessible to researchers investigating how their hypotheses compare to trends in the research literature. We present a web application that computes and provides an interactive visualization of basic frequencies and co-occurrence statistics of MeSH descriptors associated with a PubMed query.

Analysis of 8q24.21 miRNA cluster expression and copy number variation in gastric cancer.

Aim: To analyze gene expression and copy number of five miRNAs (miR-1204, miR-1205, miR-1206, miR-1207 and miR-1208) localized in this chromosome region in gastric cancer (GC). Materials & methods: 65 paired neoplastic and non-neoplastic specimens collected from GC patients and 20 non-neoplastic gastric tissues from cancer-free individuals were included in this study. The expression levels of the five miRNAs were accessed by real time qPCR and were correlated. Results: MiR-1207-3p, miR-1205, miR-1207-5p and miR-1208 were upregulated in approximately 50% of GC tumors in relation to those of adjacent non-neoplastic tissues. MiR-1205 expression was associated with gain of gene copies and was upregulated in adjacent non-neoplastic samples relative to external controls. Conclusion: The coexpression of the 8q24 miRNAs indicated the role of miR-1205 in the initiation of gastric cancer development.

Mining Drugs and Indications for Suicide-Related Adverse Events.

There has been a significant increase in suicide rates in the United States (U.S.) over the past two decades. Studies have highlighted the need for further exploration of suicide risk factors, particularly combinations of factors. In this study, a pharmacovigilance analysis was conducted to better understand drugs and indications as risk factors for suicide using data from the U.S. Food and Drug Administration (FDA) Adverse Event Reporting System (FAERS) and Adverse Event Open Learning through Universal Standardization (AEOLUS), a standardized version of FAERS. Association rule mining techniques were applied to 85,071 cases involving suicide-related adverse reactions and demographic subsets of these cases. Preliminary results reveal combinations of drugs and indications that may increase the likelihood of suicide, with certain combinations potentially affecting some demographic groups more than others. Further work is needed to validate the initial findings, explore subpopulations, and determine the broader implications for suicide prevention.

Evaluation of Flowsheet Documentation in the Electronic Health Record for Residence, Living Situation, and Living Conditions.

Social determinants of health (SDOH) are important considerations in diagnosis, prevention, and health outcomes. However, they are often not well documented in the EHR and found primarily in unstructured or semi-structured text. Building upon previous work, we analyzed all flowsheet data in 2013 for information related to the SDOH topic areas of Residence, Living Situation, and Living Conditions. Overall, 91 rows were identified as being related to the topics areas resulting in 604,616 unique observations. Individual rows contained SDOH data often covered multiple concepts especially free-text entries. These data included most often references to the residence, residence details, and with whom the patient lives. Very few contained living condition references. Additionally, there was significant duplication and inconsistency of row labels, as well as variation in value list content for rows collecting the same concepts. Our findings demonstrate significant opportunities to improve and achieve better standardization in documentation around these SDOH.

Predicting Mortality in Diabetic ICU Patients Using Machine Learning and Severity Indices.

Diabetes constitutes a significant health problem that leads to many long term health issues including renal, cardiovascular, and neuropathic complications. Many of these problems can result in increased health care costs, as well risk of ICU stay and mortality. To date, no published study has used predictive modeling to examine the relative influence of diabetes, diabetic health maintenance, and comorbidities on outcomes in ICU patients. Using the MIMIC-III database, machine learning and binomial logistic regression modeling were applied to predict risk of mortality. The final models achieved good fit with AUC values of 0.787 and 0.785 respectively. Additionally, this study demonstrated that robust classification can be done as a combination of five variables (HbA1c, mean glucose during stay, diagnoses upon admission, age, and type of admission) to predict risk as compared with other machine learning models that require nearly 35 variables for similar risk assessment and prediction.