Dataset Information

Clinical state tracking in serious mental illness through computational analysis of speech.

ABSTRACT: Individuals with serious mental illness experience changes in their clinical states over time that are difficult to assess and that result in increased disease burden and care utilization. It is not known if features derived from speech can serve as a transdiagnostic marker of these clinical states. This study evaluates the feasibility of collecting speech samples from people with serious mental illness and explores the potential utility for tracking changes in clinical state over time. Patients (n = 47) were recruited from a community-based mental health clinic with diagnoses of bipolar disorder, major depressive disorder, schizophrenia or schizoaffective disorder. Patients used an interactive voice response system for at least 4 months to provide speech samples. Clinic providers (n = 13) reviewed responses and provided global assessment ratings. We computed features of speech and used machine learning to create models of outcome measures trained using either population data or an individual's own data over time. The system was feasible to use, recording 1101 phone calls and 117 hours of speech. Most (92%) of the patients agreed that it was easy to use. The individually-trained models demonstrated the highest correlation with provider ratings (rho = 0.78, p<0.001). Population-level models demonstrated statistically significant correlations with provider global assessment ratings (rho = 0.44, p<0.001), future provider ratings (rho = 0.33, p<0.05), BASIS-24 summary score, depression sub score, and self-harm sub score (rho = 0.25,0.25, and 0.28 respectively; p<0.05), and the SF-12 mental health sub score (rho = 0.25, p<0.05), but not with other BASIS-24 or SF-12 sub scores. This study brings together longitudinal collection of objective behavioral markers along with a transdiagnostic, personalized approach for tracking of mental health clinical state in a community-based clinical setting.

SUBMITTER: Arevian AC

PROVIDER: S-EPMC6961853 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Clinical state tracking in serious mental illness through computational analysis of speech.

Arevian Armen C AC Bone Daniel D Malandrakis Nikolaos N Martinez Victor R VR Wells Kenneth B KB Miklowitz David J DJ Narayanan Shrikanth S

PloS one 20200115 1

Individuals with serious mental illness experience changes in their clinical states over time that are difficult to assess and that result in increased disease burden and care utilization. It is not known if features derived from speech can serve as a transdiagnostic marker of these clinical states. This study evaluates the feasibility of collecting speech samples from people with serious mental illness and explores the potential utility for tracking changes in clinical state over time. Patients ...[more]

PMID: 31940347

Similar Datasets

Project description:BackgroundAvoiding interruptions and dropout in outpatient care can prevent mental illness symptom exacerbation and costly crisis services, such as emergency room visits and inpatient psychiatric hospitalization. During the COVID-19 pandemic, to attempt to maintain care continuity, telemedicine services were increasingly utilized, despite the lack of data on efficacy in patients with serious mental illness. Patients with serious mental illness are challenging to enroll and sustain in randomized controlled trials over time due to fluctuations in disease exacerbation. However, capturing and examining utilization and efficacy data in community mental health center (CMHC) patients with serious mental illness during the pandemic is a unique opportunity to inform future clinical and policy decision-making.ObjectiveWe aimed to identify and describe the characteristics of CMHC patients with serious mental illness who experienced treatment interruptions and who utilized telemedicine during the pandemic.MethodsWe conducted a retrospective observational study of treatment interruptions and telemedicine use during the period from December 2019 to June 2020 (compared to the period from December 2018 to June 2019) in New Hampshire CMHC patients. The study population included all Medicaid beneficiaries with serious mental illness engaged in treatment 3 months prior to the declaration of a state of emergency in response to the COVID-19 pandemic. We used chi-square tests of independence and logistic regression to explore associations between treatment interruptions and variables (gender, age, rurality, and diagnosis). Telemedicine utilization was categorized as low (<25%), medium (25%-75%), or high (>75%) use.ResultsA total of 16,030 patients were identified. New Hampshire CMHCs demonstrated only a 4.9% increase in treatment interruptions compared with the year prior. Patients who were male (odds ratio [OR] 1.27, 95% CI 1.17-1.38; P<.001), under the age of 18 years (ages 0-12 years: OR 1.37, 95% CI 0.62-0.86, P<.001; aged 13-17 years: OR 1.49, 95% CI 0.57-0.79, P<.001), or among milder diagnostic categories, such as anxiety disorders (OR 3.77, 95% CI 3.04-4.68; P<.001) and posttraumatic stress disorder (OR 3.69, 95% CI 2.96-4.61; P<.001), were most likely to experience treatment interruptions. Patients who were female (OR 0.89, CI 0.65-0.74), 18 to 34 years old (OR 0.74, CI 0.70-0.79), or among milder diagnostic categories, such as anxiety disorder (OR 0.69, CI 0.65-0.74) or posttraumatic stress disorder (OR 0.77, CI 0.72-0.83), and with major depressive disorder (OR 0.73, CI 0.68-0.78) were less likely to be in the low telemedicine utilization group.ConclusionsThe integration of telemedicine supported care continuity for most CMHC patients; yet, retention varied by subpopulation, as did telemedicine utilization. The development of policies and clinical practice guidelines requires empirical evidence on the effectiveness and limitations of telemedicine in patients with serious mental illness.

Project description:BackgroundSerious mental illnesses (SMI) are common, disabling, and challenging to treat, requiring years of monitoring and treatment adjustments. Stress or reduced medication adherence can lead to rapid worsening of symptoms and behaviors. Illness exacerbations and relapses generally occur with little or no clinician awareness in real time, leaving limited opportunity to modify treatments. Previous research suggests that passive mobile sensing may be beneficial for individuals with SMI by helping them monitor mental health status and behaviors, and quickly detect worsening mental health for prompt assessment and intervention. However, there is too little research on its feasibility and acceptability and the extent to which passive data can predict changes in behaviors or symptoms.ObjectiveThe aim of this research is to study the feasibility, acceptability, and safety of passive mobile sensing for tracking behaviors and symptoms of patients in treatment for SMI, as well as developing analytics that use passive data to predict changes in behaviors and symptoms.MethodsA mobile app monitors and transmits passive mobile sensor and phone utilization data, which is used to track activity, sociability, and sleep in patients with SMI. The study consists of a user-centered design phase and a mobile sensing phase. In the design phase, focus groups, interviews, and usability testing inform further app development. In the mobile sensing phase, passive mobile sensing occurs with participants engaging in weekly assessments for 9 months. Three- and nine-month interviews study the perceptions of passive mobile sensing and ease of app use. Clinician interviews before and after the mobile sensing phase study the usefulness and feasibility of app utilization in clinical care. Predictive analytic models are built, trained, and selected, and make use of machine learning methods. Models use sensor and phone utilization data to predict behavioral changes and symptoms.ResultsThe study started in October 2020. It has received institutional review board approval. The user-centered design phase, consisting of focus groups, usability testing, and preintervention clinician interviews, was completed in June 2021. Recruitment and enrollment for the mobile sensing phase began in October 2021.ConclusionsFindings may inform the development of passive sensing apps and self-tracking in patients with SMI, and integration into care to improve assessment, treatment, and patient outcomes.Trial registrationClinicalTrials.gov NCT05023252; https://clinicaltrials.gov/ct2/show/NCT05023252.International registered report identifier (irrid)DERR1-10.2196/39010.

Project description:BackgroundPeople with a serious mental illness are more likely to smoke more and to be more dependent smokers than the general population. This may be due to a wide range of factors that could include a common aetiology to both smoking and the illness, self medication, smoking to alleviate adverse effects of medications, boredom in the existing environment, or a combination of these factors. It is important to undertake this review to facilitate improvements in both the health and safety of people with serious mental illness who smoke, and to reduce the overall burden of costs (both financial and health) to the smoker and, eventually, to the taxpayer.ObjectivesTo review the effects of smoking cessation advice for people with serious mental illness.Search methodsWe searched the Cochrane Schizophrenia Group Specialized Trials Register up to 2 April 2015, which is based on regular searches of CENTRAL, BIOSIS, PubMed, MEDLINE, EMBASE, CINAHL, PsycINFO, and trial registries. We also undertook unsystematic searches of a sample of the component databases (BNI, CINHAL, EMBASE, MEDLINE, and PsycINFO), up to 2 April 2015, and searched references of all identified studiesSelection criteriaWe planned to include all randomised controlled trials (RCTs) that focussed on smoking cessation advice versus standard care or comparing smoking cessation advice with other more focussed methods of delivering care or information.Data collection and analysisThe review authors (PK, AC, and DB) independently screened search results but did not identify any trials that fulfilled the inclusion criteria of this review.Main resultsWe did not identify any RCTs that evaluated advice regarding smoking cessation for people with serious mental illness. The excluded studies illustrate that randomisation of packages of care relevant to smokers with serious mental illness is possible.Authors' conclusionsPeople with serious mental illness are more likely to smoke than the general population. Yet we could not find any high quality evidence to guide the smoking cessation advice healthcare professionals pass onto service users. This is an area where trials are possible and needed.

Dataset Information

Clinical state tracking in serious mental illness through computational analysis of speech.

Publications

Clinical state tracking in serious mental illness through computational analysis of speech.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets