Evaluation of the Safer Use of Antipsychotics in Youth Study on Population Level Antipsychotic Initiation: An Interrupted Time Series Analysis.

Background: Antipsychotics carry a higher-risk profile than other psychotropic medications and may be prescribed for youth with conditions in which other first-line treatments are more appropriate. This study aimed to evaluate the population-level effect of the Safer Use of Antipsychotics in Youth (SUAY) trial, which aimed to reduce person-days of antipsychotic use among participants. Methods: We conducted an interrupted time series analysis using segmented regression to measure changes in prescribing trends of antipsychotic initiation rates pre-SUAY and post-SUAY trial at four U.S. health systems between 2013 and 2020. Results: In our overall model, adjusted for age and insurance type, antipsychotic initiation rates decreased by 0.73 (95% confidence interval [CI]: 0.30, 1.16, p = 0.002) prescriptions per 10,000 person-months before the SUAY trial. In the first quarter following the start of the trial, there was an immediate decrease in the rate of antipsychotic initiations of 6.57 (95% CI: 0.99, 12.15) prescriptions per 10,000 person-months. When comparing the posttrial period to the pretrial period, there was an increase of 1.09 (95% CI: 0.32, 1.85) prescriptions per 10,000 person-months, but the increasing rate in the posttrial period alone was not statistically significant (0.36 prescriptions per 10,000 person-months, 95% CI: -0.27, 0.99). Conclusion: The declining trend of antipsychotic initiation seen between 2013 and 2018 (pre-SUAY trial) may have naturally reached a level at which prescribing was clinically warranted and appropriate, resulting in a floor effect. The COVID-19 pandemic, which began in the final three quarters of the posttrial period, may also be related to increased antipsychotic medication initiation.

Suicide Screening, Risk Assessment, and Lethal Means Counseling During Zero Suicide Implementation.

OBJECTIVE: The authors measured implementation of Zero Suicide (ZS) clinical practices that support identification of suicide risk and risk mitigation, including screening, risk assessment, and lethal means counseling, across mental health specialty and primary care settings. METHODS: Six health care systems in California, Colorado, Michigan, Oregon, and Washington participated. The sample included members ages ≥13 years from 2010 to 2019 (N=7,820,524 patients). The proportions of patients with suicidal ideation screening, suicide risk assessment, and lethal means counseling were estimated. RESULTS: In 2019, patients were screened for suicidal ideation in 27.1% (range 5.0%-85.0%) of mental health visits and 2.5% (range 0.1%-35.0%) of primary care visits among a racially and ethnically diverse sample (44.9% White, 27.2% Hispanic, 13.4% Asian, and 7.7% Black). More patients screened positive for suicidal ideation in the mental health setting (10.2%) than in the primary care setting (3.8%). Of the patients screening positive for suicidal ideation in the mental health setting, 76.8% received a risk assessment, and 82.4% of those identified as being at high risk received lethal means counseling, compared with 43.2% and 82.4%, respectively, in primary care. CONCLUSIONS: Six health systems that implemented ZS showed a high level of variation in the proportions of patients receiving suicide screening and risk assessment and lethal means counseling. Two opportunities emerged for further study to increase frequency of these practices: expanding screening beyond patients with regular health care visits and implementing risk assessment with lethal means counseling in the primary care setting directly after a positive suicidal ideation screening.

Adolescents Who Do Not Endorse Risk via the Patient Health Questionnaire Before Self-Harm or Suicide.

Importance: Given that the Patient Health Questionnaire (PHQ) item 9 is commonly used to screen for risk of self-harm and suicide, it is important that clinicians recognize circumstances when at-risk adolescents may go undetected. Objective: To understand characteristics of adolescents with a history of depression who do not endorse the PHQ item 9 before a near-term intentional self-harm event or suicide. Design, Setting, and Participants: This was a retrospective cohort study design using electronic health record and claims data from January 2009 through September 2017. Settings included primary care and mental health specialty clinics across 7 integrated US health care systems. Included in the study were adolescents aged 13 to 17 years with history of depression who completed the PHQ item 9 within 30 or 90 days before self-harm or suicide. Study data were analyzed September 2022 to April 2023. Exposures: Demographic, diagnostic, treatment, and health care utilization characteristics. Main Outcome(s) and Measure(s): Responded "not at all" (score = 0) to PHQ item 9 regarding thoughts of death or self-harm within 30 or 90 days before self-harm or suicide. Results: The study included 691 adolescents (mean [SD] age, 15.3 [1.3] years; 541 female [78.3%]) in the 30-day cohort and 1024 adolescents (mean [SD] age, 15.3 [1.3] years; 791 female [77.2%]) in the 90-day cohort. A total of 197 of 691 adolescents (29%) and 330 of 1024 adolescents (32%), respectively, scored 0 before self-harm or suicide on the PHQ item 9 in the 30- and 90-day cohorts. Adolescents seen in primary care (odds ratio [OR], 1.5; 95% CI, 1.0-2.1; P = .03) and older adolescents (OR, 1.2; 95% CI, 1.0-1.3; P = .02) had increased odds of scoring 0 within 90 days of a self-harm event or suicide, and adolescents with a history of inpatient hospitalization and a mental health diagnosis had twice the odds (OR, 2.0; 95% CI, 1.3-3.0; P = .001) of scoring 0 within 30 days. Conversely, adolescents with diagnoses of eating disorders were significantly less likely to score 0 on item 9 (OR, 0.4; 95% CI, 0.2-0.8; P = .007) within 90 days. Conclusions and Relevance: Study results suggest that older age, history of an inpatient mental health encounter, or being screened in primary care were associated with at-risk adolescents being less likely to endorse having thoughts of death and self-harm on the PHQ item 9 before a self-harm event or suicide death. As use of the PHQ becomes more widespread in practice, additional research is needed for understanding reasons why many at-risk adolescents do not endorse thoughts of death and self-harm.

Patient Characteristics and Telemedicine Use in the US, 2022.

Importance: Telemedicine use was common during the COVID-19 pandemic, expanding many patients' approaches to accessing health care. Of concern is whether telemedicine access was poorer among higher-needs and disadvantaged populations. Objective: To assess patient characteristics associated with telemedicine use and telemedicine mode and describe telemedicine visit experiences by telemedicine mode. Design, Setting, and Participants: This cross-sectional study included data from the 2022 Health Information National Trends Survey and included US adults with a health care visit. Data were analyzed from May to September 2023. Exposure: Patient characteristics. Main Outcomes and Measures: Any telemedicine visits vs in-person visits only; telemedicine mode (video vs audio-only). Multivariable logistic models assessed patient characteristics associated with telemedicine visits and mode. Bivariate analyses compared telemedicine experiences by mode. Results: The study included 5437 adult patients (mean [SE] age, 49.4 [0.23] years; 3136 females [53.4%]; 1928 males [46.6%]). In 2022, 2384 patients (43%) had a telemedicine visit; 1565 (70%) had a video visit while 819 (30%) had an audio-only visit. In multivariable models, older age (≥75 years: adjusted odds ratio [aOR], 0.63; 95% CI, 0.42-0.94), no internet use (aOR, 0.62; 95% CI, 0.48-0.81), and living in the Midwest (aOR, 0.50; 95% CI, 0.35-0.70) were negatively associated with having telemedicine visits. Female sex (aOR, 1.43; 95% CI, 1.12-1.83), having chronic conditions (aOR, 2.13; 95% CI, 1.66-2.73), and multiple health care visits (2-4 visits: aOR, 1.77; 95% CI, 1.23-2.54; ≥5 visits: aOR, 3.29; 95% CI, 2.20-4.92) were positively associated. Among individuals who used telemedicine, older age (65-74 years: aOR, 2.13; 95% CI, 1.09-4.14; ≥75 years: aOR, 3.58; 95% CI, 1.60-8.00), no health insurance (aOR, 2.84; 95% CI, 1.42-5.67), and no internet use (aOR, 2.11; 95% CI, 1.18-3.78) were positively associated with having audio-only visits. We observed no significant differences in telemedicine use or mode by education, race and ethnicity, or income. Patients' experiences using telemedicine were generally similar for video and audio-only except more individuals who used audio-only had privacy concerns (20% vs 12%, P = .02). Conclusions and Relevance: In this cross-sectional study of adults with health care visits, many patients, including those with the greatest care needs, chose telemedicine even after in-person visits were available. These findings support continuing this care delivery approach as an option valued by patients. Differences were not observed by most common measures of socioeconomic status. Continued monitoring of telemedicine use is needed to ensure equitable access to health care innovations.

On- and Off-Label Atypical Antipsychotic Prescription Trends Across a Nine-Year Period Among Adolescents Pre- to Post-COVID-19.

OBJECTIVE: This study examined atypical antipsychotic prescribing by Food and Drug Administration (FDA) approved-use (on-label) status for adolescents before and during the COVID-19 pandemic. METHODS: Retrospective data were collected from electronic health records (EHRs) of adolescents aged 10-17 years in Kaiser Permanente Northern California. New outpatient atypical antipsychotic prescription orders during 2013-2021 were evaluated. Prescriptions were categorized as on-label if linked in EHRs to autism, psychosis, bipolar disorder, or Tourette's diagnoses; otherwise, they were potentially off-label (herein, off-label). Trend analysis of monthly prescribing rates assessed slope change at pandemic onset for the cohort and by sex and age groups. RESULTS: Among 5828 patients, 74.5% of new antipsychotic orders were off-label in 2021. Overall prescribing decreased significantly until early 2020 (slope = -0.045, P < .01) but then significantly increased through 2021 (post-March 2020 slope change = 0.211, P = .01). Off-label prescriptions increased at a similar rate during the COVID-19 time period, but on-label prescriptions did not change significantly. Males and younger adolescents (ages 10-14 years) showed significant decreases until early 2020, while females and older adolescents (ages 15-17 years) did not. Females and younger adolescents exhibited significant increases in overall and off-label prescribing rates following pandemic onset; older adolescents exhibited increases in overall prescriptions while males had no detectable changes. CONCLUSIONS: Antipsychotic prescribing declined slightly but then increased significantly following COVID-19 onset for overall and off-label prescriptions. Pandemic onset differentially impacted antipsychotic prescribing by sex and age, with overall and off-label prescribing driven by increases among female and younger adolescents.

Short report: Transition to International Classification of Diseases, 10th Revision and the prevalence of autism in a cohort of healthcare systems.

LAY ABSTRACT: Currently, the prevalence of autism spectrum disorder (henceforth "autism") is 1 in 36, an increasing trend from previous estimates. In 2015, the United States adopted a new version (International Classification of Diseases, 10th Revision) of the World Health Organization coding system, a standard for classifying medical conditions. Our goal was to examine how the transition to this new coding system impacted autism diagnoses in 10 healthcare systems. We obtained information from electronic medical records and insurance claims data from July 2014 through December 2016 for each healthcare system. We used member enrollment data for 30 consecutive months to observe changes 15 months before and after adoption of the new coding system. Overall, the rates of autism per 1000 enrolled members was increasing for 0- to 5-year-olds before transition to International Classification of Diseases, 10th Revision and did not substantively change after the new coding was in place. There was variation observed in autism diagnoses before and after transition to International Classification of Diseases, 10th Revision for other age groups. The change to the new coding system did not meaningfully affect autism rates at the participating healthcare systems. The increase observed among 0- to 5-year-olds is likely indicative of an ongoing trend related to increases in screening for autism rather than a shift associated with the new coding.

Pilot Evaluation of the Family Bridge Program: A Communication- and Culture-Focused Inpatient Patient Navigation Program.

OBJECTIVE: Children with low income and minority race and ethnicity have worse hospital outcomes due partly to systemic and interpersonal racism causing communication and system barriers. We tested the feasibility and acceptability of a novel inpatient communication-focused navigation program. METHODS: Multilingual design workshops with parents, providers, and staff created the Family Bridge Program. Delivered by a trained navigator, it included 1) hospital orientation; 2) social needs screening and response; 3) communication preference assessment; 4) communication coaching; 5) emotional support; and 6) a post-discharge phone call. We enrolled families of hospitalized children with public or no insurance, minority race or ethnicity, and preferred language of English, Spanish, or Somali in a single-arm trial. We surveyed parents at enrollment and 2 to 4 weeks post-discharge, and providers 2 to 3 days post-discharge. Survey measures were analyzed with paired t tests. RESULTS: Of 60 families enrolled, 57 (95%) completed the follow-up survey. Most parents were born outside the United States (60%) with a high school degree or less (60%). Also, 63% preferred English, 33% Spanish, and 3% Somali. The program was feasible: families received an average of 5.3 of 6 components; all received >2. Most caregivers (92%) and providers (81% [30/37]) were "very satisfied." Parent-reported system navigation improved from enrollment to follow-up (+8.2 [95% confidence interval 2.9, 13.6], P = .003; scale 0-100). Spanish-speaking parents reported decreased skills-related barriers (-18.4 [95% confidence interval -1.8, -34.9], P = .03; scale 0-100). CONCLUSIONS: The Family Bridge Program was feasible, acceptable, and may have potential for overcoming barriers for hospitalized children at risk for disparities.

Psychotherapy Disruption Before and After the Transition to Virtual Mental Health Care Induced by the COVID-19 Pandemic.

OBJECTIVE: This study aimed to examine population-level disruption in psychotherapy before and after the rapid shift to virtual mental health care induced by the onset of the COVID-19 pandemic in the United States. METHODS: This retrospective study used electronic health record and insurance claims data from three U.S. health systems. The sample included 110,089 patients with mental health conditions who were members of the health systems' affiliated health plans and attended at least two psychotherapy visits from June 14, 2019, through December 15, 2020. Data were subdivided into two 9-month periods (before vs. after COVID-19 onset, defined in this study as March 14, 2020). Psychotherapy visits were measured via health records and categorized as in person or virtual. Disruption was defined as a gap of >45 days between visits. RESULTS: Visits in the preonset period were almost exclusively in person (97%), whereas over half of visits in the postonset period were virtual (52%). Approximately 35% of psychotherapy visits were followed by a disruption in the preonset period, compared with 18% in the postonset period. Disruption continued to be less common (adjusted OR=0.45) during the postonset period after adjustment for visit, mental health, and sociodemographic factors. The magnitude of the difference in disruption between periods was homogeneous across sociodemographic characteristics but heterogeneous across psychiatric diagnoses. CONCLUSIONS: This study found fewer population-level disruptions in psychotherapy receipt after rapid transition to virtual mental health care following COVID-19 onset. These data support the continued availability of virtual psychotherapy.

Improving Diabetes Control in a Medicaid Managed Care Population With Complex Needs.

INTRODUCTION: People enrolled in Medicaid managed care who struggle with diabetes control often have complex medical, behavioral, and social needs. Here the authors report the results of a program designed to partner with primary care teams to address those needs. METHODS: A nonprofit organization partnered with a Medicaid managed care plan and a Federally Qualified Health Center in California to enroll people with A1cs >9% in a 12-month program. The program team included a community health worker, certified diabetes care and education specialist/registered dietitian, behavioral health counselor, and registered nurse. They developed patient-led action plans, connected patients to community resources, and supported behavior changes to improve diabetes control. Baseline assessments of behavioral health conditions and social needs were collected. Monthly A1c values were tracked for participants and a comparison group. RESULTS: Of the 51 people enrolled, 83% had at least 1 behavioral health condition. More than 90% reported at least 1 unmet social need. The average monthly A1c among program participants was 0.699 lower than the comparison group post-enrollment (P = .0008), and the disparity in A1c between Hispanic and non-Hispanic White participants at enrollment declined. DISCUSSION: Participants had high levels of unmet medical, behavioral, and social needs. Addressing these needs resulted in a rapid and sustained improvement in A1c control compared to non-enrollees and a reduction in disparity of control among Hispanic participants. CONCLUSION: By partnering with a primary care team, a program external to Federally Qualified Health Center primary care can improve clinical outcomes for people with complex needs living with diabetes.

Predicting risk of suicidal behavior from insurance claims data vs. linked data from insurance claims and electronic health records.

PURPOSE: Observational studies assessing effects of medical products on suicidal behavior often rely on health record data to account for pre-existing risk. We assess whether high-dimensional models predicting suicide risk using data derived from insurance claims and electronic health records (EHRs) are superior to models using data from insurance claims alone. METHODS: Data were from seven large health systems identified outpatient mental health visits by patients aged 11 or older between 1/1/2009 and 9/30/2017. Data for the 5 years prior to each visit identified potential predictors of suicidal behavior typically available from insurance claims (e.g., mental health diagnoses, procedure codes, medication dispensings) and additional potential predictors available from EHRs (self-reported race and ethnicity, responses to Patient Health Questionnaire or PHQ-9 depression questionnaires). Nonfatal self-harm events following each visit were identified from insurance claims data and fatal self-harm events were identified by linkage to state mortality records. Random forest models predicting nonfatal or fatal self-harm over 90 days following each visit were developed in a 70% random sample of visits and validated in a held-out sample of 30%. Performance of models using linked claims and EHR data was compared to models using claims data only. RESULTS: Among 15 845 047 encounters by 1 574 612 patients, 99 098 (0.6%) were followed by a self-harm event within 90 days. Overall classification performance did not differ between the best-fitting model using all data (area under the receiver operating curve or AUC = 0.846, 95% CI 0.839-0.854) and the best-fitting model limited to data available from insurance claims (AUC = 0.846, 95% CI 0.838-0.853). Competing models showed similar classification performance across a range of cut-points and similar calibration performance across a range of risk strata. Results were similar when the sample was limited to health systems and time periods where PHQ-9 depression questionnaires were recorded more frequently. CONCLUSION: Investigators using health record data to account for pre-existing risk in observational studies of suicidal behavior need not limit that research to databases including linked EHR data.

The rapid shift to virtual mental health care: Examining psychotherapy disruption by rurality status.

BACKGROUND: Given the low usage of virtual health care prior to the COVID-19 pandemic, it was unclear whether those living in rural locations would benefit from increased availability of virtual mental health care. The rapid transition to virtual services during the COVID-19 pandemic allowed for a unique opportunity to examine how the transition to virtual mental health care impacted psychotherapy disruption (i.e., 45+ days between appointments) among individuals living in rural locations compared with those living in nonrural locations. METHODS: Electronic health record and insurance claims data were collected from three health care systems in the United States including rurality status and psychotherapy disruption. Psychotherapy disruption was measured before and after the COVID-19 pandemic onset. RESULTS: Both the nonrural and rural cohorts had significant decreases in the rates of psychotherapy disruption from pre- to post-COVID-19 onset (32.5-16.0% and 44.7-24.8%, respectively, p < 0.001). The nonrural cohort had a greater reduction of in-person visits compared with the rural cohort (96.6-45.0 vs. 98.0-66.2%, respectively, p < 0.001). Among the rural cohort, those who were younger and those with lower education had greater reductions in psychotherapy disruption rates from pre- to post-COVID-19 onset. Several mental health disorders were associated with experiencing psychotherapy disruption. CONCLUSIONS: Though the rapid transition to virtual mental health care decreased the rate of psychotherapy disruption for those living in rural locations, the reduction was less compared with nonrural locations. Other strategies are needed to improve psychotherapy disruption, especially among rural locations (i.e., telephone visits).

Beyond clinical outcomes: Case control study of the role of race in disruptive life events for people with serious mental illness.

OBJECTIVE: To understand how race and serious mental illness (SMI) interact for disruptive life events defined as financial (bankruptcy and judgement filings), and non-financial (arrests). METHODS: Patients were adults with schizophrenia (SCZ; N = 16,159) or bipolar I disorder (BPI; N = 30,008) matched 1:1 to patients without SMI (non-SMI) from health systems in Michigan and Southern California during 1/1/2007 through 12/31/2018. The main exposure was self-reported race, and the outcome was disruptive life events aggregated by Transunion. We hypothesized that Black patients with SCZ or BPI would be the most likely to experience a disruptive life event when compared to Black patients without SMI, and all White or Asian patients regardless of mental illness. RESULTS: Black patients with SCZ had the least likelihood (37% lower) and Asian patients with BPI had the greatest likelihood (2.25 times higher) of experiencing a financial disruptive life event among all patients in the study. There was no interaction of race with either SCZ or BPI for experiencing an arrest. The findings did not support our hypotheses for patients with SCZ and partially supported them for patients with BPI. CONCLUSIONS: Clinical initiatives to assess social determinants of health should consider a focus on Asian patients with BPI.

Cost of Implementing an Evidence-Based Intervention to Support Safer Use of Antipsychotics in Youth.

To estimate the cost of implementing a clinical program designed to support safer use of antipsychotics in children and adolescents (youth) age 3-17 years at the time of initiating an antipsychotic medication. We calculate the costs of implementing a psychiatric consultation and navigation program for youth prescribed antipsychotic medications across 4 health systems, which included an electronic health record (EHR) decision support tool, consultation with a child and adolescent psychiatrist, and up to 6 months of behavioral health care navigation, as well as telemental health for patients (n = 348). Cost data were collected for both start-up and ongoing intervention phases and are estimated over a 1-year period. Data sources included study records and time-in-motion reports, analyzed from a health system perspective. Costs included both labor and nonlabor costs (2019 US dollars). The average total start-up and ongoing costs per health system were $34,007 and $185,174, respectively. The average total cost per patient was $2,128. The highest average ongoing labor cost components were telemental health ($901 per patient), followed by child and adolescent psychiatrist consultation ($659), and the lowest cost component was primary care/behavioral health provider time to review/respond to the EHR decision support tool and case consultation ($24). For health systems considering programs to promote safer and targeted use of antipsychotics among youth, this study provides estimates of the full start-up and ongoing costs of an EHR decision support tool, psychiatric consultation service, and psychotherapeutic services for patients and families.Trial registration: Clinicaltrials.gov, NCT03448575.

Assessment of Disruptive Life Events for Individuals Diagnosed With Schizophrenia or Bipolar I Disorder Using Data From a Consumer Credit Reporting Agency.

Importance: There is a dearth of population-level data on major disruptive life events (defined here as arrests by a legal authority, address changes, bankruptcy, lien, and judgment filings) for patients with bipolar I disorder (BPI) or schizophrenia, which has limited studies on mental health and treatment outcomes. Objective: To conduct a population-level study on disruptive life events by using publicly available data on disruptive life events, aggregated by a consumer credit reporting agency in conjunction with electronic health record (EHR) data. Design, Setting, and Participants: This study used EHR data from 2 large, integrated health care systems, Kaiser Permanente Southern California and Henry Ford Health. Cohorts of patients diagnosed from 2007 to 2019 with BPI or schizophrenia were matched 1:1 by age at analysis, age at diagnosis (if applicable), sex, race and ethnicity, and Medicaid status to (1) an active comparison group with diagnoses of major depressive disorder (MDD) and (2) a general health (GH) cohort without diagnoses of BPI, schizophrenia, or MDD. Patients with diagnoses of BPI or schizophrenia and their respective comparison cohorts were matched to public records data aggregated by a consumer credit reporting agency (98% match rate). Analysis took place between November 2020 and December 2022. Main Outcomes and Measures: The differences in the occurrence of disruptive life events among patients with BPI or schizophrenia and their comparison groups. Results: Of 46 167 patients, 30 008 (65%) had BPI (mean [SD] age, 42.6 [14.2] years) and 16 159 (35%) had schizophrenia (mean [SD], 41.4 [15.1] years). The majoriy of patients were White (30 167 [65%]). In addition, 18 500 patients with BPI (62%) and 6552 patients with schizophrenia (41%) were female. Patients with BPI were more likely to change addresses than patients in either comparison cohort (with the incidence ratio being as high as 1.25 [95% CI, 1.23-1.28]) when compared with GH cohort. Patients with BPI were also more likely to experience any of the financial disruptive life events with odds ratio ranging from 1.15 [95% CI, 1.07-1.24] to 1.50 [95% CI, 1.42-1.58]). The largest differences in disruptive life events were seen in arrests of patients with either BPI or schizophrenia compared with GH peers (3.27 [95% CI, 2.84-3.78] and 3.04 [95% CI, 2.57-3.59], respectively). Patients with schizophrenia had fewer address changes and were less likely to experience a financial event than their matched comparison cohorts. Conclusions and Relevance: This study demonstrated that data aggregated by a consumer credit reporting agency can support population-level studies on disruptive life events among patients with BPI or schizophrenia.

STAR-Caregivers Virtual Training and Follow-up: a cultural adaptation for Latino caregivers of people with dementia.

STAR-Caregivers Virtual Training and Follow-up (STAR-VTF) is an evidence-based intervention that teaches family caregivers how to manage behavioral and psychological symptoms of dementia. The study objective was to identify what adaptations to STAR-VTF are needed to improve cultural relevance for Latino caregivers. A qualitative research study was conducted that interviewed Spanish- and English-speaking caregivers of people with dementia who self-identify as Hispanic/Latino (N = 30) and healthcare and social service providers of older Latino clients and/or Latino family caregivers (N = 14). Thematic analysis methods were applied to code and analyze interview transcripts. The codebook was theory-driven, relying mainly on codes that directly represented components of the Cultural Treatment Adaptation Framework. Based on the content of the excerpts, the codes were sorted into themes that represented opportunities to culturally adapt STAR-VTF. Three themes were identified: (i) there was a need to increase awareness about dementia and decrease stigma; (ii) semantics mattered as certain words and phrases could be stigmatizing, offensive, or culturally inappropriate; and (iii) there was a need to incorporate into program materials the traditional family structure and nature of caregiving in Latino families. Based on findings, adaptations were performed on STAR-VTF that included expanding content to improve understanding of dementia, revising language that was viewed as problematic, and adding cultural examples to reflect the range of family involvement in caring for people living with dementia and multigenerational living. Findings from this qualitative research study advance understanding of the Latino caregiver experience and how to modify programs to better serve their needs.

STAR-Caregivers Virtual Training and Follow-up (STAR-VTF) is an evidence-based intervention that teaches family caregivers how to manage behavioral and psychological symptoms of dementia. The study objective was to identify what adaptations to STAR-VTF are needed to improve cultural relevance for Latino caregivers. Thirty Spanish- and English-speaking caregivers of people living with dementia who self-identify as Hispanic/Latino and 14 providers of healthcare and social services were interviewed. Interview transcripts were analyzed using thematic analysis methods. The Cultural Treatment Adaptation Framework guided data collection and analysis. Three themes were identified: (i) there was a need to increase awareness about dementia and decrease stigma; (ii) semantics mattered as certain words and phrases could be stigmatizing, offensive, or culturally inappropriate; and (iii) there was a need to incorporate into program materials the traditional family structure and nature of caregiving in Latino families. Adaptations were performed on STAR-VTF, including expanding content to improve understanding of dementia, revising language that was viewed as problematic, and adding cultural examples to reflect the range of family involvement in caring for people living with dementia and multigenerational living. Findings from this study advance understanding of the Latino caregiver experience and how to modify programs to better serve their needs.

Complex modeling with detailed temporal predictors does not improve health records-based suicide risk prediction.

Suicide risk prediction models can identify individuals for targeted intervention. Discussions of transparency, explainability, and transportability in machine learning presume complex prediction models with many variables outperform simpler models. We compared random forest, artificial neural network, and ensemble models with 1500 temporally defined predictors to logistic regression models. Data from 25,800,888 mental health visits made by 3,081,420 individuals in 7 health systems were used to train and evaluate suicidal behavior prediction models. Model performance was compared across several measures. All models performed well (area under the receiver operating curve [AUC]: 0.794-0.858). Ensemble models performed best, but improvements over a regression model with 100 predictors were minimal (AUC improvements: 0.006-0.020). Results are consistent across performance metrics and subgroups defined by race, ethnicity, and sex. Our results suggest simpler parametric models, which are easier to implement as part of routine clinical practice, perform comparably to more complex machine learning methods.

Using natural language processing to identify child maltreatment in health systems.

BACKGROUND: Rates of child maltreatment (CM) obtained from electronic health records are much lower than national child welfare prevalence rates indicate. There is a need to understand how CM is documented to improve reporting and surveillance. OBJECTIVES: To examine whether using natural language processing (NLP) in outpatient chart notes can identify cases of CM not documented by ICD diagnosis code, the overlap between the coding of child maltreatment by ICD and NLP, and any differences by age, gender, or race/ethnicity. METHODS: Outpatient chart notes of children age 0-18 years old within Kaiser Permanente Washington (KPWA) 2018-2020 were used to examine a selected set of maltreatment-related terms categorized into concept unique identifiers (CUI). Manual review of text snippets for each CUI was completed to flag for validated cases and retrain the NLP algorithm. RESULTS: The NLP results indicated a crude rate of 1.55 % to 2.36 % (2018-2020) of notes with reference to CM. The rate of CM identified by ICD code was 3.32 per 1000 children, whereas the rate identified by NLP was 37.38 per 1000 children. The groups that increased the most in identification of maltreatment from ICD to NLP were adolescents (13-18 yrs. old), females, Native American children, and those on Medicaid. Of note, all subgroups had substantially higher rates of maltreatment when using NLP. CONCLUSIONS: Use of NLP substantially increased the estimated number of children who have been impacted by CM. Accurately capturing this population will improve identification of vulnerable youth at high risk for mental health symptoms.

Development of a machine learning model to predict mild cognitive impairment using natural language processing in the absence of screening.

BACKGROUND: Patients and their loved ones often report symptoms or complaints of cognitive decline that clinicians note in free clinical text, but no structured screening or diagnostic data are recorded. These symptoms/complaints may be signals that predict who will go on to be diagnosed with mild cognitive impairment (MCI) and ultimately develop Alzheimer's Disease or related dementias. Our objective was to develop a natural language processing system and prediction model for identification of MCI from clinical text in the absence of screening or other structured diagnostic information. METHODS: There were two populations of patients: 1794 participants in the Adult Changes in Thought (ACT) study and 2391 patients in the general population of Kaiser Permanente Washington. All individuals had standardized cognitive assessment scores. We excluded patients with a diagnosis of Alzheimer's Disease, Dementia or use of donepezil. We manually annotated 10,391 clinic notes to train the NLP model. Standard Python code was used to extract phrases from notes and map each phrase to a cognitive functioning concept. Concepts derived from the NLP system were used to predict future MCI. The prediction model was trained on the ACT cohort and 60% of the general population cohort with 40% withheld for validation. We used a least absolute shrinkage and selection operator logistic regression approach (LASSO) to fit a prediction model with MCI as the prediction target. Using the predicted case status from the LASSO model and known MCI from standardized scores, we constructed receiver operating curves to measure model performance. RESULTS: Chart abstraction identified 42 MCI concepts. Prediction model performance in the validation data set was modest with an area under the curve of 0.67. Setting the cutoff for correct classification at 0.60, the classifier yielded sensitivity of 1.7%, specificity of 99.7%, PPV of 70% and NPV of 70.5% in the validation cohort. DISCUSSION AND CONCLUSION: Although the sensitivity of the machine learning model was poor, negative predictive value was high, an important characteristic of models used for population-based screening. While an AUC of 0.67 is generally considered moderate performance, it is also comparable to several tests that are widely used in clinical practice.

Suicide Deaths Before and During the Coronavirus Disease 2019 Pandemic: An Interrupted Time-series Study.

INTRODUCTION: With stressors that are often associated with suicide increasing during the coronavirus disease 2019 (COVID-19) pandemic, there has been concern that suicide mortality rates may also be increasing. Our objective was to determine whether suicide mortality rates increased during the COVID-19 pandemic. METHODS: We conducted an interrupted time-series study using data from January 2019 through December 2020 from 2 large integrated health care systems. The population at risk included all patients or individuals enrolled in a health plan at HealthPartners in Minnesota or Henry Ford Health System in Michigan. The primary outcome was change in suicide mortality rates, expressed as annualized crude rates of suicide death per 100,000 people in 10 months following the start of the pandemic in March 2020 compared with the 14 months prior. RESULTS: There were 6,434,675 people at risk in the sample, with 55% women and a diverse sample across ages, race/ethnicity, and insurance type. From January 2019 through February 2020, there was a slow increase in the suicide mortality rate, with rates then decreasing by 0.45 per 100,000 people per month from March 2020 through December 2020 (SE=0.19, P=0.03). CONCLUSIONS: Overall suicide mortality rates did not increase with the pandemic, and in fact slightly declined from March to December 2020. Our findings should be confirmed across other settings and, when available, using final adjudicated state mortality data.