Validation of an Electronic Health Record-Based Suicide Risk Prediction Modeling Approach Across Multiple Health Care Systems.

Importance: Suicide is a leading cause of mortality, with suicide-related deaths increasing in recent years. Automated methods for individualized risk prediction have great potential to address this growing public health threat. To facilitate their adoption, they must first be validated across diverse health care settings. Objective: To evaluate the generalizability and cross-site performance of a risk prediction method using readily available structured data from electronic health records in predicting incident suicide attempts across multiple, independent, US health care systems. Design, Setting, and Participants: For this prognostic study, data were extracted from longitudinal electronic health record data comprising International Classification of Diseases, Ninth Revision diagnoses, laboratory test results, procedures codes, and medications for more than 3.7 million patients from 5 independent health care systems participating in the Accessible Research Commons for Health network. Across sites, 6 to 17 years' worth of data were available, up to 2018. Outcomes were defined by International Classification of Diseases, Ninth Revision codes reflecting incident suicide attempts (with positive predictive value >0.70 according to expert clinician medical record review). Models were trained using naive Bayes classifiers in each of the 5 systems. Models were cross-validated in independent data sets at each site, and performance metrics were calculated. Data analysis was performed from November 2017 to August 2019. Main Outcomes and Measures: The primary outcome was suicide attempt as defined by a previously validated case definition using International Classification of Diseases, Ninth Revision codes. The accuracy and timeliness of the prediction were measured at each site. Results: Across the 5 health care systems, of the 3 714 105 patients (2 130 454 female [57.2%]) included in the analysis, 39 162 cases (1.1%) were identified. Predictive features varied by site but, as expected, the most common predictors reflected mental health conditions (eg, borderline personality disorder, with odds ratios of 8.1-12.9, and bipolar disorder, with odds ratios of 0.9-9.1) and substance use disorders (eg, drug withdrawal syndrome, with odds ratios of 7.0-12.9). Despite variation in geographical location, demographic characteristics, and population health characteristics, model performance was similar across sites, with areas under the curve ranging from 0.71 (95% CI, 0.70-0.72) to 0.76 (95% CI, 0.75-0.77). Across sites, at a specificity of 90%, the models detected a mean of 38% of cases a mean of 2.1 years in advance. Conclusions and Relevance: Across 5 diverse health care systems, a computationally efficient approach leveraging the full spectrum of structured electronic health record data was able to detect the risk of suicidal behavior in unselected patients. This approach could facilitate the development of clinical decision support tools that inform risk reduction interventions.

Interest in bariatric surgery among obese patients with obstructive sleep apnea.

BACKGROUND: Standard obstructive sleep apnea (OSA) therapies are poorly tolerated. Bariatric surgery is a potential alternative but the level of interest in this intervention among OSA patients is unknown. OBJECTIVES: Determine the proportion of OSA patients who would be interested in bariatric surgery. SETTING: Sleep clinics, United States. METHODS: Consecutive adult patients with untreated severe OSA and a body mass index of 35-45 kg/m(2) were approached. Patients at low perioperative risk and no urgent indication for OSA treatment were invited to a separate informational visit about bariatric surgery as primary treatment for OSA. RESULTS: Of 767 eligible patients, 230 (30.0%) were not at low perioperative risk, 49 (6.4%) had drowsy driving, and 16 (2.1%) had no insurance coverage for bariatric surgery. Of the remaining 482 patients, over one third (35.5%) were interested in bariatric surgery. Surgical interest was 47.2% in women versus 27.6% in men (P<0.01) and 67.3% in diabetics versus 31.0% in nondiabetics (P<0.01). In multivariable adjusted models, female gender (odds ratio 1.89, 95% CI [1.10-3.25]) and diabetes (odds ratio 3.97, 95% CI [1.97-8.01]) remained highly predictive of bariatric surgery interest. CONCLUSIONS: Nearly two thirds of obese patients with severe OSA are good candidates for bariatric surgery. Among candidates, over one third are interested in this treatment. Interest rates are highest among women and diabetics, indicating that metabolic improvements continue to be a major driver of surgery even in patients with severe OSA. Given patient interest, the role of bariatric surgery should be routinely discussed with obese OSA patients.

Reproducibility of a Standardized Actigraphy Scoring Algorithm for Sleep in a US Hispanic/Latino Population.

STUDY OBJECTIVES: While actigraphy is considered objective, the process of setting rest intervals to calculate sleep variables is subjective. We sought to evaluate the reproducibility of actigraphy-derived measures of sleep using a standardized algorithm for setting rest intervals. DESIGN: Observational study. SETTING: Community-based. PARTICIPANTS: A random sample of 50 adults aged 18-64 years free of severe sleep apnea participating in the Sueño sleep ancillary study to the Hispanic Community Health Study/Study of Latinos. INTERVENTIONS: N/A. MEASUREMENTS AND RESULTS: Participants underwent 7 days of continuous wrist actigraphy and completed daily sleep diaries. Studies were scored twice by each of two scorers. Rest intervals were set using a standardized hierarchical approach based on event marker, diary, light, and activity data. Sleep/wake status was then determined for each 30-sec epoch using a validated algorithm, and this was used to generate 11 variables: mean nightly sleep duration, nap duration, 24-h sleep duration, sleep latency, sleep maintenance efficiency, sleep fragmentation index, sleep onset time, sleep offset time, sleep midpoint time, standard deviation of sleep duration, and standard deviation of sleep midpoint. Intra-scorer intraclass correlation coefficients (ICCs) were high, ranging from 0.911 to 0.995 across all 11 variables. Similarly, inter-scorer ICCs were high, also ranging from 0.911 to 0.995, and mean inter-scorer differences were small. Bland-Altman plots did not reveal any systematic disagreement in scoring. CONCLUSIONS: With use of a standardized algorithm to set rest intervals, scoring of actigraphy for the purpose of generating a wide array of sleep variables is highly reproducible.

Does mechanism of injury play a role in recovery from concussion?

BACKGROUND: High school football and soccer are 2 of the leading causes of concussion injuries. However, concussions also occur from mechanisms of injury such as motor vehicle accidents (MVAs), assault, and work-related accidents. PURPOSE: Determine if recovery from concussion could be related to the mechanism of injury. SETTING: Berkshire Medical Center Concussion Clinic. PARTICIPANTS: Patients aged 13 to 21 years suffering concussion from football (n = 31), soccer (n = 9), or MVAs (n = 20). OUTCOME MEASUREMENTS: ImPACT (Immediate Post Concussion Assessment Tool) test scores including symptom inventory; number of days sick; length of time to recovery. RESULTS: Most commonly reported symptom at the time of injury was headache. Patients were seen in clinic an average of 16 (football), 14 (soccer), and 21 (MVA) days postinjury. Groups differed significantly on ImPACT Visual Memory and Visual Motor Speed scores (P < .05). MVA patients had a longer median number of days sick (97 days) than football players (32 days; P < .05). CONCLUSION: This study suggests that concussion from an MVA may be a more serious injury than a typical concussion sustained during sports. Data suggest that MVA patients take longer to present to clinic, have lower Visual Memory and Visual Motor Speed scores on ImPACT, and take longer to recover. Further studies are needed to better understand how the mechanism of injury of concussion may relate to prognosis.

Treatment of obstructive sleep apnea alters cancer-associated transcriptional signatures in circulating leukocytes.

RATIONALE: Obstructive sleep apnea (OSA) has been associated with a number of chronic disorders that may improve with effective therapy. However, the molecular pathways affected by continuous positive airway pressure (CPAP) treatment are largely unknown. We sought to assess the system-wide consequences of CPAP therapy by transcriptionally profiling peripheral blood leukocytes (PBLs). METHODS: Subjects in whom severe OSA was diagnosed were treated with CPAP, and whole-genome expression measurement of PBLs was performed at baseline and following therapy. We used gene set enrichment analysis (GSEA) to identify pathways that were differentially enriched. Network analysis was then applied to highlight key drivers of processes influenced by CPAP. RESULTS: Eighteen subjects with significant OSA underwent CPAP therapy and microarray analysis of their PBLs. Treatment with CPAP improved apnea-hypopnea index (AHI), daytime sleepiness, and blood pressure, but did not affect anthropometric measures. GSEA revealed a number of enriched gene sets, many of which were involved in neoplastic processes and displayed downregulated expression patterns in response to CPAP. Network analysis identified several densely connected genes that are important modulators of cancer and tumor growth. CONCLUSIONS: Effective therapy of OSA with CPAP is associated with alterations in circulating leukocyte gene expression. Functional enrichment and network analyses highlighted transcriptional suppression in cancer-related pathways, suggesting potentially novel mechanisms linking OSA with neoplastic signatures.

Memory for the 2008 presidential election in healthy ageing and mild cognitive impairment.

The present study examined memory accuracy and confidence for personal and public event details of the 2008 presidential election in healthy older adults and those with mild cognitive impairment (MCI). Participants completed phone interviews within a week after the election and after a 10-month delay. MCI patients and healthy older adults had comparable emotional reactions to learning the outcome of the election, with most people finding it to be a positive experience. After the delay period, details about the election were better remembered by all participants than a less emotionally arousing comparison event. However, MCI patients had more difficulty than healthy older adults correctly recalling details of public information about the election, although often the MCI patients could recognise the correct details. This is the first study to show that MCI patients' memory can benefit from emotionally arousing positive events, complementing the literature demonstrating similar effects for negative events.