The project for objective measures using computational psychiatry technology (PROMPT): Rationale, design, and methodology

Taishiro Kishimoto; Akihiro Takamiya; Kuo-Ching Liang; Kei Funaki; Takanori Fujita; Momoko Kitazawa; Michitaka Yoshimura; Yuki Tazawa; Toshiro Horigome; Yoko Eguchi; Toshiaki Kikuchi; Masayuki Tomita; Shogyoku Bun; Junichi Murakami; Brian Sumali; Tifani Warnita; Aiko Kishi; Mizuki Yotsui; Hiroyoshi Toyoshiba; Yasue Mitsukura; Koichi Shinoda; Yasubumi Sakakibara; Masaru Mimura; PROMPT collaborators

doi:10.1016/j.conctc.2020.100649

The project for objective measures using computational psychiatry technology (PROMPT): Rationale, design, and methodology

Contemp Clin Trials Commun. 2020 Aug 18:19:100649. doi: 10.1016/j.conctc.2020.100649. eCollection 2020 Sep.

Authors

Taishiro Kishimoto¹, Akihiro Takamiya¹, Kuo-Ching Liang¹, Kei Funaki¹, Takanori Fujita², Momoko Kitazawa¹, Michitaka Yoshimura¹, Yuki Tazawa¹, Toshiro Horigome¹, Yoko Eguchi¹, Toshiaki Kikuchi¹, Masayuki Tomita³, Shogyoku Bun⁴, Junichi Murakami⁵, Brian Sumali⁶, Tifani Warnita⁷, Aiko Kishi⁶, Mizuki Yotsui⁸, Hiroyoshi Toyoshiba^{9

10}, Yasue Mitsukura⁶, Koichi Shinoda⁷, Yasubumi Sakakibara⁸, Masaru Mimura¹; PROMPT collaborators

Affiliations

¹ Department of Neuropsychiatry, Keio University School of Medicine, 35 Shinanomachi, Shinjuku, Tokyo, 160-8582, Japan.
² Department of Health Policy and Management, Keio University, 35 Shinanomachi, Shinjuku, Tokyo, 160-8582, Japan.
³ Oizumi Hospital, 6-9-1 Oizumi-gakuencho, Nerimaku, Tokyo, 178-0061, Japan.
⁴ Sato Hospital, 948-1 Kunugutsuka, Nanyo, Yamagata, 999-2221, Japan.
⁵ Biwako Hospital, 1-8-5 Sakamoto, Otsu, Shiga, 520-0113, Japan.
⁶ Department of System Design Engineering, Keio University, 3-14-1 Hiyoshi, Minato-kita, Yokohama, Kanagawa, 223-0061, Japan.
⁷ Department of Computer Science, School of Computing, Tokyo Institute of Technology, 4259 Nagatsuda, Yokohama, Kanagawa, 226-8503, Japan.
⁸ Department of Biosciences and Informatics, Keio University, 3-14-1 Hiyoshi, Minato-kita, Yokohama, Kanagawa, 223-0061, Japan.
⁹ Center for Systems Medicine, Keio University, 35 Shinanomachi, Shinjuku, Tokyo, 160-8582, Japan.
¹⁰ FRONTEO, Inc., 2-12-23 Minato-Minami, Minato, Tokyo, 108-0075, Japan.

Abstract

Introduction: Depressive and neurocognitive disorders are debilitating conditions that account for the leading causes of years lived with disability worldwide. However, there are no biomarkers that are objective or easy-to-obtain in daily clinical practice, which leads to difficulties in assessing treatment response and developing new drugs. New technology allows quantification of features that clinicians perceive as reflective of disorder severity, such as facial expressions, phonic/speech information, body motion, daily activity, and sleep.

Methods: Major depressive disorder, bipolar disorder, and major and minor neurocognitive disorders as well as healthy controls are recruited for the study. A psychiatrist/psychologist conducts conversational 10-min interviews with participants ≤10 times within up to five years of follow-up. Interviews are recorded using RGB and infrared cameras, and an array microphone. As an option, participants are asked to wear wrist-band type devices during the observational period. Various software is used to process the raw video, voice, infrared, and wearable device data. A machine learning approach is used to predict the presence of symptoms, severity, and the improvement/deterioration of symptoms.

Discussion: The overall goal of this proposed study, the Project for Objective Measures Using Computational Psychiatry Technology (PROMPT), is to develop objective, noninvasive, and easy-to-use biomarkers for assessing the severity of depressive and neurocognitive disorders in the hopes of guiding decision-making in clinical settings as well as reducing the risk of clinical trial failure. Challenges may include the large variability of samples, which makes it difficult to extract the features that commonly reflect disorder severity.

Trial registration: UMIN000021396, University Hospital Medical Information Network (UMIN).

Keywords: AMED, Japan Agency for Medical Research and Development; Adabag, Adaptive Bagging; Adaboost, Adaptive Boosting; BD, Bipolar disorder; BDI-II, Beck Depression Inventory, Second Edition; BNN, Bayesian Neural Networks; CDR, Clinical Dementia Rating; CDT, Clock Drawing Test; CNN, Convolutional Neural Networks; CPP, cepstral peak prominence; DSM-5, Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition; Depression; F0, fundamental frequency; F1, F2, F3, first, second, and third formant frequencies; FedRAMP, Federal Risk and Authorization Management Program; GCNN, Gated Convolutional Neural Networks; GDS, Geriatric Depression Scale; HAM-D, Hamilton Depression Rating Scale; IEC, International Electrotechnical Commission; ISO, International Organization for Standardization; LM, Wechsler Memory Scale-Revised Logical Memory; LSTM, Long Short-Term Memory Networks; M.I.N.I., Mini-International Neuropsychiatric Interview; MADRS, Montgomery-Asberg Depression Rating Scale; MARS, Motor Agitation and Retardation Scale; MCI, mild cognitive impairment; MDD, Major depressive disorder; MFCC, mel-frequency cepstrum coefficients; MMSE, Mini-Mental State Examination; MRI, magnetic resonance imaging; Machine learning; MoCA, Montreal Cognitive Assessment; NPI, Neuropsychiatric Inventory; Natural language processing; Neurocognitive disorder; PET, positron emission tomography; PROMPT, Project for Objective Measures Using Computational Psychiatry Technology; PSQI, Pittsburgh Sleep Quality Index; RF, Random Forest; RGB, red, green, blue; SCID, Structural Clinical Interview for DSM-5; SVM, Support Vector Machine; SVR, Support Vector Regression; Screening; UI, uncertainty interval; UMIN, University Hospital Medical Information Network; UV, ultraviolet; YLDs, years lived with disability; YMRS, Young Mania Rating Scale.