Classification of Depression Through Resting-State Electroencephalogram as a Novel Practice in Psychiatry: Review

Background Machine learning applications in health care have increased considerably in the recent past, and this review focuses on an important application in psychiatry related to the detection of depression. Since the advent of computational psychiatry, research based on functional magnetic resonance imaging has yielded remarkable results, but these tools tend to be too expensive for everyday clinical use. Objective This review focuses on an affordable data-driven approach based on electroencephalographic recordings. Web-based applications via public or private cloud-based platforms would be a logical next step. We aim to compare several different approaches to the detection of depression from electroencephalographic recordings using various features and machine learning models. Methods To detect depression, we reviewed published detection studies based on resting-state electroencephalogram with final machine learning, and to predict therapy outcomes, we reviewed a set of interventional studies using some form of stimulation in their methodology. Results We reviewed 14 detection studies and 12 interventional studies published between 2008 and 2019. As direct comparison was not possible due to the large diversity of theoretical approaches and methods used, we compared them based on the steps in analysis and accuracies yielded. In addition, we compared possible drawbacks in terms of sample size, feature extraction, feature selection, classification, internal and external validation, and possible unwarranted optimism and reproducibility. In addition, we suggested desirable practices to avoid misinterpretation of results and optimism. Conclusions This review shows the need for larger data sets and more systematic procedures to improve the use of the solution for clinical diagnostics. Therefore, regulation of the pipeline and standard requirements for methodology used should become mandatory to increase the reliability and accuracy of the complete methodology for it to be translated to modern psychiatry.

Classification of Depression Through Resting-State Electroencephalogram as a Novel Practice in Psychiatry: Review (Preprint)

BACKGROUND Machine learning applications in health care have increased considerably in the recent past, and this review focuses on an important application in psychiatry related to the detection of depression. Since the advent of computational psychiatry, research based on functional magnetic resonance imaging has yielded remarkable results, but these tools tend to be too expensive for everyday clinical use. OBJECTIVE This review focuses on an affordable data-driven approach based on electroencephalographic recordings. Web-based applications via public or private cloud-based platforms would be a logical next step. We aim to compare several different approaches to the detection of depression from electroencephalographic recordings using various features and machine learning models. METHODS To detect depression, we reviewed published detection studies based on resting-state electroencephalogram with final machine learning, and to predict therapy outcomes, we reviewed a set of interventional studies using some form of stimulation in their methodology. RESULTS We reviewed 14 detection studies and 12 interventional studies published between 2008 and 2019. As direct comparison was not possible due to the large diversity of theoretical approaches and methods used, we compared them based on the steps in analysis and accuracies yielded. In addition, we compared possible drawbacks in terms of sample size, feature extraction, feature selection, classification, internal and external validation, and possible unwarranted optimism and reproducibility. In addition, we suggested desirable practices to avoid misinterpretation of results and optimism. CONCLUSIONS This review shows the need for larger data sets and more systematic procedures to improve the use of the solution for clinical diagnostics. Therefore, regulation of the pipeline and standard requirements for methodology used should become mandatory to increase the reliability and accuracy of the complete methodology for it to be translated to modern psychiatry. CLINICALTRIAL

EAT-PAD: Educating about psychiatric advance directives in India

Background: With India enacting the Mental Health Care Act (MHCA; No. 10 of 2017a), Psychiatric Advance Directives (PADs) have been legalised and have become binding orders for psychiatrists treating patients. There is a paucity of research into acceptability of PADs in Indian mental health care, likely due to a lack of awareness. There are no educational measures about PADs provided for in this Act. Facilitators and facilitation methods have not been elaborated upon as well. Aim: The aim of this study is (a) to develop/evaluate the effectiveness of a structured Education-cum-Assessment Tool (EAT) in providing information regarding PADs and (b) to evaluate modes of facilitation required by patients to complete PADs. Methods: A tool was developed as per provisions regarding PADs in the Mental Health Care Bill of 2013. This tool was administered to patients ( n = 100), purposively sampled from the adult psychiatry review out-patient department (OPD). Patients were evaluated on retention of information, completion of PADs, modes of facilitation and time taken to write one. Results: Mean years of education was 8.28 (±5.74) years and mean duration of illness was 8.30 (±7.04) years. In all, 65% had Below-Poverty Line (BPL) status. All participants completed valid PADs in an average of 15 minutes. About 93% required facilitation via assistance in writing and reminding. The mean EAT scores implied above 70% retention but did not relate to types of facilitation. Conclusions: EAT scores can be used as an approximate measure of the patient’s ability to understand and retain information which is a part of decisional capacity. Types of facilitation can help in understanding patient’s ability to communicate their choices. Service providers may find EAT a time-effective tool for uniformly educating service users regarding PADs and indirectly assessing competence.

Symptoms of Poststroke Depression among Stroke Survivors: An Appraisal of Psychiatry Needs and Care during Physiotherapy Rehabilitation

Purpose. To identify stroke survivors with symptoms of poststroke depression and the extent of psychiatry needs and care they have received while on physiotherapy rehabilitation.Participants. Fifty stroke survivors (22 females and 28 males) at the outpatient unit of Physiotherapy Department, University of Nigeria Teaching Hospital, Enugu, who gave their informed consent, were randomly selected. Their age range and mean age were 26–66 years and54.76±8.79years, respectively.Method. A multiple case study of 50 stroke survivors for symptoms of poststroke depression was done with Beck’s Depression Inventory, mini mental status examination tool, and Modified Motor Assessment Scale. The tests were performed independently by the participants except otherwise stated and scored on a scale of 0–6. Data were analyzed usingZ-test for proportional significance and chi-square test for determining relationship between variables, atp<0.05.Results. Twenty-one (42.0%) stroke survivors had symptoms of PSD, which was significantly dependent on duration of stroke (χ2= 21.680, df = 6, andp=0.001), yet none of the participants had a psychiatry review.Conclusions. Symptoms of PSD may be common in cold compared to new cases of stroke and may need psychiatry care while on physiotherapy rehabilitation.