The Role of Machine Learning in Diagnosing Bipolar Disorder: Scoping Review

Abstract

Background Bipolar disorder (BD) is the 10th most common cause of frailty in young individuals and has triggered morbidity and mortality worldwide. Patients with BD have a life expectancy 9 to 17 years lower than that of normal people. BD is a predominant mental disorder, but it can be misdiagnosed as depressive disorder, which leads to difficulties in treating affected patients. Approximately 60% of patients with BD are treated for depression. However, machine learning provides advanced skills and techniques for better diagnosis of BD. Objective This review aims to explore the machine learning algorithms used for the detection and diagnosis of bipolar disorder and its subtypes. Methods The study protocol adopted the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. We explored 3 databases, namely Google Scholar, ScienceDirect, and PubMed. To enhance the search, we performed backward screening of all the references of the included studies. Based on the predefined selection criteria, 2 levels of screening were performed: title and abstract review, and full review of the articles that met the inclusion criteria. Data extraction was performed independently by all investigators. To synthesize the extracted data, a narrative synthesis approach was followed. Results We retrieved 573 potential articles were from the 3 databases. After preprocessing and screening, only 33 articles that met our inclusion criteria were identified. The most commonly used data belonged to the clinical category (19, 58%). We identified different machine learning models used in the selected studies, including classification models (18, 55%), regression models (5, 16%), model-based clustering methods (2, 6%), natural language processing (1, 3%), clustering algorithms (1, 3%), and deep learning–based models (3, 9%). Magnetic resonance imaging data were most commonly used for classifying bipolar patients compared to other groups (11, 34%), whereas microarray expression data sets and genomic data were the least commonly used. The maximum ratio of accuracy was 98%, whereas the minimum accuracy range was 64%. Conclusions This scoping review provides an overview of recent studies based on machine learning models used to diagnose patients with BD regardless of their demographics or if they were compared to patients with psychiatric diagnoses. Further research can be conducted to provide clinical decision support in the health industry.

The process of stigma experience in the families of people living with bipolar disorder: a grounded theory study

“…The prevalence of type 1 bipolar disorder in the general population is 1.5-2.1% and in the intensive care unit (ICU) is 21-26% [5][6][7][8]. The aggregate lifetime prevalence of all types of bipolar disorder was reported to be 5% [9].…”

Natural Language Processing: from Bedside to Everywhere

“…In psychiatry, NLP can be used for IE from unstructured EHR and speech analysis on patient speech data [63,64]. NLP can help in the screening, early diagnosis, or severity estimation of various diseases such as depression [63], bipolar disorder [65], dementia [66][67][68], psychosis [69,70], and schizophrenia [71]. Dai…”

Natural language processing in clinical neuroscience and psychiatry: A review

“…Due to their nature, they were not categorized into any of the three topics presented in Section "Results." Some of these reviews are extremely focused on a specific argument (6)(7)(8)(9)(10); this makes them good candidates for topic-specific analysis, but they lack a general vision. Other reviews do not present the breakthroughs of the last 4-5 years (attention mechanism, transformers, BERTmodels, etc.…”

“…In recent years, researchers have recognized that social medias can also be a source of text for these experiments. This is the case of Low et al ( 67 70) exploited data from Reachout.com, 7 an online mental health service for young people and their parents in Australia, benchmarking multiple methods of text feature representation for social media posts and comparing their downstream use with automated ML tools. Yu et al (71) used data from the John Tung Foundation 8 to build a framework for discovering linguistic association patterns, and showed that they are promising features for classification tasks.…”