Tardive dyskinesia (TD) is a common debilitating side effect of antipsychotic use. Characterized most notably by involuntary facial movements such as grimacing, involuntary lip, mouth, and tongue movements, and eye blinking, TD is difficult to treat and potentially irreversible. Psychiatrists and other mental health professionals are acutely aware of the impairment and disability experienced by patients who develop TD. Early detection of TD is critical so that appropriate interventions can be instituted. Unfortunately, despite professionals? best efforts, it is often too late in the process and the involuntary movements are permanent. Antipsychotic prescriptions exceeded 50 million in 2011 and the reported incidence of TD is between 13% and 24%. Risk grows with advancing age, off-label uses, and chronic exposure to antipsychotics. Therefore, prevention and early detection are key to managing TD. However, current methods for monitoring patients require observation of patients at infrequent in-person visits or self-reporting by vigilant patients and their families. Therefore strong market potential exists for an automated detection system. This Phase I project proposes to leverage existing telepsychiatry and video interview data gathering technologies available commercially to efficiently collect and analyze two hundred 5-minute video interviews with individuals taking anti-psychotic medications. Half of the interviews will be with individuals living with diagnosed TD and the other without a diagnosis of TD. The participants in the study will be recruited to ensure an equal distribution of females and males as well as an ethnically and racially representative sample. The proposed data gathering strategy will provide the source material necessary to create a powerful supervised machine learning derived video and audio analysis tool to detect TD. The detection tool will be created using 80% of the collected video data as a training set and validated on the remaining 20% reserved as the control set. Based on industry experience with other supervised machine learning training sets and the amount of data to be collected, we set a goal of a 90% success rate in identifying TD positive and TD negative participants in the control set. Once the detection tool is complete the project will conclude by incorporating access to the tool into an existing smartphone app, iRxReminder, that is used for data gathering and monitoring of clinical trials. The iRxReminder system links patients directly to researchers and their electronic records. The modified app will be tested in the laboratory to ensure the interface can be easily used. In Phase II the iRxReminder system will be validated for use in supporting the self-management and symptom monitoring of medication taking by individuals living with chronic mental illnesses. Once feasibility is established, we propose a year-long RCT where participants will be monitored for early detection of TD along with goals for high adherence, improved control of symptoms and side effects, and more aggressive and frequent treatment responses by the healthcare team.
A recent study reported that TD rates among newly treated elderly ranged from 7.2% for those taking Risperidone to 11.1% for those taking olanzapine after 2 years of treatment. Earlier meta-analyses estimate TD frequency in women to be 26.6% and in men 21.6%. Ethnically Chinese and Malaysian mental health patients were studied in Singapore and patients taking anti-psychotic medications were found to have TD in 40% and 29% of cases respectively. Regardless of prevalence, TD is a threat to patient adherence and quality of life. TD only remits in a minority of cases and can be permanent. With 50 million prescriptions for anti-psychotics written annually, more than 10 million persons living with a chronic mental illness are at risk of developing TD. There are likely over 6 million patients living with TD and the number of patients with TD is expected to grow with the aging population and increasing off- label use of antipsychotics.