Predictive modeling of initiation and delayed mental health contact for depression.

BACKGROUND: Depression is prevalent among Operation Enduring Freedom and Operation Iraqi Freedom (OEF/OIF) Veterans, yet rates of Veteran mental health care utilization remain modest. The current study examined: factors in electronic health records (EHR) associated with lack of treatment initiation and treatment delay; the accuracy of regression and machine learning models to predict initiation of treatment. METHODS: We obtained data from the VA Corporate Data Warehouse (CDW). EHR data were extracted for 127,423 Veterans who deployed to Iraq/Afghanistan after 9/11 with a positive depression screen and a first depression diagnosis between 2001 and 2021. We also obtained 12-month pre-diagnosis and post-diagnosis patient data. Retrospective cohort analysis was employed to test if predictors can reliably differentiate patients who initiated, delayed, or received no mental health treatment associated with their depression diagnosis. RESULTS: 108,457 Veterans with depression, initiated depression-related care (55,492 Veterans delayed treatment beyond one month). Those who were male, without VA disability benefits, with a mild depression diagnosis, and had a history of psychotherapy were less likely to initiate treatment. Among those who initiated care, those with single and mild depression episodes at baseline, with either PTSD or who lacked comorbidities were more likely to delay treatment for depression. A history of mental health treatment, of an anxiety disorder, and a positive depression screen were each related to faster treatment initiation. Classification of patients was modest (ROC AUC = 0.59 95%CI = 0.586-0.602; machine learning F-measure = 0.46). CONCLUSIONS: Having VA disability benefits was the strongest predictor of treatment initiation after a depression diagnosis and a history of mental health treatment was the strongest predictor of delayed initiation of treatment. The complexity of the relationship between VA benefits and history of mental health care with treatment initiation after a depression diagnosis is further discussed. Modest classification accuracy with currently known predictors suggests the need to identify additional predictors of successful depression management.

Mental health treatment utilization patterns among 108,457 Afghanistan and Iraq veterans with depression.

People with depression often underutilize mental health care. This study was conceived as a first step toward a clinical decision support tool that helps identify patients who are at higher risk of underutilizing care. The primary goals were to (a) describe treatment utilization patterns, early termination, and return to care; (b) identify factors associated with early termination of treatment; and (c) evaluate the accuracy of regression models to predict early termination. These goals were evaluated in a retrospective cohort analysis of 108,457 U.S. veterans who received care from the Veterans Health Administration between 2001 and 2021. Our final sample was 16.5% female with an average age of 34.5. Veterans were included if they had a depression diagnosis, a positive depression screen, and received general health care services at least a year before and after their depression diagnosis. Using treatment quality guidelines, the threshold for treatment underutilization was defined as receiving fewer than four psychotherapy sessions or less than 84 days of antidepressants. Over one fifth of veterans (21.6%) received less than the minimally recommended care for depression. The odds of underutilizing treatment increased with lack of Veterans Administration benefits, male gender, racial/ethnic minority status, and having received mental health treatment in the past (adjusted OR > 1.1). Posttraumatic stress disorder comorbidity correlated with increased depression treatment utilization (adjusted OR < .9). Models with demographic and clinical information from medical records performed modestly in classifying patients who underutilized depression treatment (area under the curve = 0.595, 95% CI [0.588, 0.603]). Most veterans in this cohort received at least the minimum recommended treatment for depression. To improve the prediction of underutilization, patient factors associated with treatment underutilization likely need to be supplemented by additional clinical information. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

The Value of Extracting Clinician-Recorded Affect for Advancing Clinical Research on Depression: Proof-of-Concept Study Applying Natural Language Processing to Electronic Health Records.

BACKGROUND: Affective characteristics are associated with depression severity, course, and prognosis. Patients' affect captured by clinicians during sessions may provide a rich source of information that more naturally aligns with the depression course and patient-desired depression outcomes. OBJECTIVE: In this paper, we propose an information extraction vocabulary used to pilot the feasibility and reliability of identifying clinician-recorded patient affective states in clinical notes from electronic health records. METHODS: Affect and mood were annotated in 147 clinical notes of 109 patients by 2 independent coders across 3 pilots. Intercoder discrepancies were settled by a third coder. This reference annotation set was used to test a proof-of-concept natural language processing (NLP) system using a named entity recognition approach. RESULTS: Concepts were frequently addressed in templated format and free text in clinical notes. Annotated data demonstrated that affective characteristics were identified in 87.8% (129/147) of the notes, while mood was identified in 97.3% (143/147) of the notes. The intercoder reliability was consistently good across the pilots (interannotator agreement [IAA] >70%). The final NLP system showed good reliability with the final reference annotation set (mood IAA=85.8%; affect IAA=80.9%). CONCLUSIONS: Affect and mood can be reliably identified in clinician reports and are good targets for NLP. We discuss several next steps to expand on this proof of concept and the value of this research for depression clinical research.

Clozapine utilization at the United States Veterans Health Administration: a descriptive report of prescribing patterns and patient characteristics among Operation Enduring Freedom/Operation Iraqi Freedom Veterans.

To identify the clozapine utilization rate at Veterans Health Administration, as well as patient characteristics, and correlates of use to garner a better understanding of the Veterans Health Administration-treated clozapine population. A longitudinal retrospective cohort analysis was conducted on all Operation Enduring Freedom/Operation Iraqi Freedom Veterans treated with clozapine prescriptions through Veterans Health Administration from 2006 to 2016. Descriptive and inferential analyses were conducted. The sample of 1.3 million veterans had 15 416 with schizophrenia-spectrum disorders, however; only 197 filled outpatient clozapine prescriptions through Veterans Health Administration, a clozapine utilization rate of 1.28%. Median days on clozapine were 305. Median number of antipsychotic medications was 12, with a median rank of clozapine being the eighth antipsychotic trialed. 59.90% of individuals had at least one period of maintenance clozapine treatment. The median number of psychiatric hospitalizations was four, and Clozapine rank was strongly associated with number of hospitalizations. There were no associations between acute versus maintenance clozapine use and either hospitalizations or mortality. Clozapine utilization was very low relative to recommended prescribing rates. Delayed initiation of clozapine was noted and was associated with increased number of hospitalizations. Lack of observed differences in mortality may be explained by low number of mortalities.

Antidepressant Augmentation: A Review of the Literature and a Review of the Pharmacoeconomic Considerations.

PURPOSE: Antidepressant augmentation strategies for treatment-resistant depression (TRD) are discussed here with an analysis of patient out-of-pocket costs for various medications. The choice of agent ranges from newer atypical antipsychotics (aripiprazole, brexpiprazole, quetiapine) to older agents including buspirone, liothyronine (T3), and lithium. We sought to better understand the differences among these agents to aid in clinical decision making. METHODS: We conducted a focused review of the support for each of the aforementioned agents in antidepressant augmentation. We then compared the approximate out-of-pocket cost for each medication during a typical augmentation trial using the typical prescription costs on ClinCalc.com derived from the Medical Expenditure Panel Survey. We calculated the cost to achieve response for one patient with TRD based on the number needed to treat (NNT). FINDINGS: We observed significant variance in cost to achieve response based on the NNT derived from our review of each of the medications. For example, the overall out-of-pocket cost for one patient to achieve response with aripiprazole (the costliest generic agent) could cover lithium prescriptions for 4 to 5 patients with TRD to achieve response. Although brexpiprazole was estimated separately because of its brand name cost, we estimated that 324 patients receiving lithium could achieve response for same cost of single patient receiving brexpiprazole. IMPLICATIONS: These findings suggest that among augmentation agents, there are differences in cost that may be highly important in clinical decision making. Other issues of medication monitoring may incur additional costs, and brand name medications offer significantly greater complexity and potential out-of-pocket costs to patients. The use of lithium as a first-line agent for TRD should be considered based on low cost, lowest NNT, and data in support of its efficacy.

Comparison of T1Rho MRI, Glucose Metabolism, and Amyloid Burden Across the Cognitive Spectrum: A Pilot Study.

OBJECTIVE: The pathological cascades associated with the development of Alzheimer's disease (AD) have a common element: acidosis. T1rho MRI is a pH-sensitive measure, with higher values associated with greater neuropathological burden. The authors investigated the relationship between T1rho imaging and AD-associated pathologies as determined by available diagnostic imaging techniques. METHODS: Twenty-seven participants (men, N=13, women, N=14; ages 55-90) across the cognitive spectrum (healthy control subjects [HCs] with normal cognition, N=17; participants with mild cognitive impairment [MCI], N=7; participants with mild AD, N=3) underwent neuropsychological testing, MRI (T1-weighted and T1rho [spin-lattice relaxation time in the rotating frame]), and positron emission tomography imaging ([11C]Pittsburg compound B for amyloid burden [N=26] and [18F]fluorodeoxyglucose for cerebral glucose metabolism [N=12]). The relationships between global T1rho values and neuropsychological, demographic, and imaging measures were explored. RESULTS: Global mean and median T1rho were positively associated with age. After controlling for age, higher global T1rho was associated with poorer cognitive function, poorer memory function (immediate and delayed memory scores), higher amyloid burden, and more abnormal cerebral glucose metabolism. Regional T1rho values, when controlling for age, significantly differed between HCs and participants with MCI or AD in select frontal, cingulate, and parietal regions. CONCLUSIONS: Higher T1rho values were associated with greater cognitive impairment and pathological burden. T1rho, a biomarker that varies according to a feature common to each cascade rather than one that is unique to a particular pathology, has the potential to serve as a metric of neuropathology, theoretically providing a measure for assessing pathological status and for monitoring the neurodegeneration trajectory.

Palliative Care for Dementia: 2020 Update.

Dementia management is complicated by neuropsychiatric symptoms such that the longitudinal care of a psychiatrist or other mental health provider is often an essential part of patient care and a major source of family support. Given the importance of end-of-life continuity of care, the involvement of psychiatry in palliative and hospice services affords an important opportunity for growth. Common challenges involve sharing prognostic information with patients and families to aid in advance planning, and management of persistent pain and nutritional issues. Future research will yield important new insights and guidelines for care.

Mortality and Associated Risk Factors in Community-Dwelling Persons With Early Dementia.

OBJECTIVE: Examine mortality and associations with baseline characteristics among Veterans with early dementia. METHODS: Participants included dyads of community-based Veterans with early dementia and their caregivers (N=143) enrolled in a previous longitudinal study. Department of Veterans Health Affairs' electronic records were used to retrospectively collect Veteran mortality outcomes, over a 6-year period. Measures included baseline: demographics, dementia-related factors, other comorbid conditions, functioning, and medication use. Associations with baseline characteristics and mortality were examined with bivariate analyses and a series of Cox proportional hazard models. RESULTS: Over 6 years of study follow-up, 53.1% of participants died. The mean time to death was 3.09 years, with a range of 54 days to 5.91 years. Female sex, better cognition, and higher scores on the Tinetti Gait and Balance scale were protective factors in the final multivariable model, adjusting for other characteristics. CONCLUSIONS: While newly diagnosed with early dementia, over half of our sample died in the 6-year follow-up period, with the average death occurring only 3 years after initial diagnosis. The finding of lower mortality associated with better performance on gait/balance testing indicates an important opportunity for focused interventions and early detection of gait and balance changes early during cognitive decline.

American Association for Geriatric Psychiatry-Strategic Thinking.

Never has there been a more pressing time for the American Association for Geriatric Psychiatry (AAGP) to articulate a unified strategy to meet the challenges of our aging world. To this end, this report summarizes an AAGP leadership meeting that reviewed the results from a recent membership survey and launched a strategic planning process on behalf of AAGP members and stakeholders. This meeting was the first step in drafting a blueprint for the future that may serve as our guide in the context of finite resources to meet the infinitely complex and growing need for education, research, public advocacy, and clinical practice support. The following report serves to invite our valued colleagues to provide feedback and actively participate in defining our mission. Among the outcomes of the planning session, the following aspirations were identified by the participants 1) assert the AAGP as the "go to" organization for all things related to geriatric mental health, 2) prioritize activities that enhance the inclusivity/diversity of membership, and 3) collaborate across disciplines focused on geriatric mental health. From this initial framework, the group developed four general themes to guide AAGP's strategic future: 1) collaboration, 2) advocacy, 3) inclusivity, 4) high purpose. Inclusivity was further defined as encompassing growth, return on investment, and workforce development. Higher purpose was further defined as encompassing engagement, purpose, branding, communication, and expertise. The AAGP affirmed its commitment to serving the needs of its members and widening its scope of impact in view of staggering demands for better access to geriatric mental healthcare.

Early Phase PIB-PET as a Surrogate for Global and Regional Cerebral Blood Flow Measures.

BACKGROUND AND PURPOSE: To explore the potential for simplified measures of [11 C]PIB uptake to serve as a surrogate for cerebral blood flow (CBF) measures, thereby, providing both pathological and functional information in the same scan. METHODS: Participants (N = 24, 16 M, 8 F, 57-87 years) underwent quantitative [15 O]water imaging and dynamic [11 C]PIB imaging. Time-activity curves were created for each participant's regional [11 C]PIB data scaled in standardized uptake values (SUVs). The frame in which maximal uptake occurred was defined for each subject (ie, "peak"). The concentration (SUV) for each region at the individual's peak, during the 3.5-4 minute time interval and for the initial 6 minute sum, was determined. R1 (ie, relative delivery using cerebellum as reference tissue) from the simplified reference tissue model 2 was determined for each region. PIB SUVs were compared to the absolute CBF global and regional values (in mL/minute/100 mL) and the R1 values were compared to the cerebellar-normalized rCBF. RESULTS: Significant linear relationships were found for all SUV measures with measures of absolute global and regional CBF that were comparable to the relationship between normalized CBF and R1. The individual SUVpeak exhibited the strongest relationship both regionally and globally. All individuals and all regions had highly significant regression slopes. Age, gender, or amyloid burden did not influence the relationship. CONCLUSION: Early PIB uptake has the potential to effectively serve as a surrogate for global and regional CBF measures. The simple and readily obtainable individual's SUVpeak value was the strongest predictor regionally and globally of CBF.

Machine learning for psychiatric patient triaging: an investigation of cascading classifiers.

Objective: Develop an approach, One-class-at-a-time, for triaging psychiatric patients using machine learning on textual patient records. Our approach aims to automate the triaging process and reduce expert effort while providing high classification reliability. Materials and Methods: The One-class-at-a-time approach is a multistage cascading classification technique that achieves higher triage classification accuracy compared to traditional multiclass classifiers through 1) classifying one class at a time (or stage), and 2) identification and application of the highest accuracy classifier at each stage. The approach was evaluated using a unique dataset of 433 psychiatric patient records with a triage class label provided by "I2B2 challenge," a recent competition in the medical informatics community. Results: The One-class-at-a-time cascading classifier outperformed state-of-the-art classification techniques with overall classification accuracy of 77% among 4 classes, exceeding accuracies of existing multiclass classifiers. The approach also enabled highly accurate classification of individual classes-the severe and mild with 85% accuracy, moderate with 64% accuracy, and absent with 60% accuracy. Discussion: The triaging of psychiatric cases is a challenging problem due to the lack of clear guidelines and protocols. Our work presents a machine learning approach using psychiatric records for triaging patients based on their severity condition. Conclusion: The One-class-at-a-time cascading classifier can be used as a decision aid to reduce triaging effort of physicians and nurses, while providing a unique opportunity to involve experts at each stage to reduce false positive and further improve the system's accuracy.

Multi-Parametric Classification of Vascular Cognitive Impairment and Dementia: The Impact of Diverse Cerebrovascular Injury Biomarkers.

Vascular cognitive impairment and dementia (VCID) is a diagnostic term applied to cognitively impaired individuals with heterogeneous cerebrovascular conditions affecting large and/or small vessels. Individual biomarkers have been identified as instrumental in relating VCID to specific underlying pathologies to better characterize this syndrome. Emerging research to refine panels of biomarkers will increase classification sensitivity and specificity. Refined VCID clustering based on the severity and pathology of vascular injury will permit the development of optimal prevention and treatment strategies. Here, we review recently reported data concerning the diversity of VCID-related pathology and attempts for VCID clustering based on biomarkers obtained from different sets of measurements. We discuss three major sets of biomarkers: 1) neuroimaging biomarkers, 2) neuropsychological performance measures, and 3) biochemical markers in current VCID clustering. Finally, we highlight the effect of blood-brain barrier health on cerebrovascular disease trajectory.

Palliative Care for Dementia.

With the growing care needs for the older population at the end of their lives, there has been a substantial increase in attention to the management of the patient with dementia in hospice and palliative care services. This article reviews issues in access to care and the optimal management of the patient with dementia, particularly in the context of neuropsychiatric complexities. Special issues such as delirium, cachexia, behavioral symptoms, and pain management are addressed. Future challenges in research such as the development of better prognostic models are noted as well as the importance of attention to access to care.