주메뉴

홈아이콘  >  이슈

[연구] 우울증-조울증 재발, 스마트폰으로 90% 예측

고대안암병원 이헌정 교수팀 <Journal of Medical Internet Research> 4월 17일자 게재

송보미 기자bmb@healthi.kr 입력 : 2019-05-15 16:02  | 수정 : 2019-05-15 16:02

네이버 페이스북 밴드 구글 트위터 핀터레스트 카카오스토리 카카오링크 인쇄 다운로드 확대 축소

 

[헬스앤라이프 송보미 기자] 스마트폰이나 스마트밴드로 우울증과 조울증 재발을 90% 정확도로 예측할 수 있는 기술이 국내 연구진에 의해 개발됐다. 

 

고대안암병원 정신건강의학과 이헌정 교수.
사진=고려대학교 안암병원

고대안암병원 정신건강의학과 이헌정 교수팀(이헌정·조철현 교수, 성신여대 이택 교수)은 주요우울장애, 1형 양극성장애, 2형 양극성장애 환자 55명에서 스마트밴드와 스마트폰을 이용 실시간으로 수집해증상의 변화와 우울증, 조증, 경조증의 재발양상을 2년간 추적 관찰한 결과를 13일 발표했다.  

 

연구 결과 스마트폰을 통해 얻은 데이터로 활동량, 수면양상, 심박수변화, 빛노출 정도 등 생체리듬의 교란과 연관된 요인들을 기반으로 인공지능으로 학습할 경우, 3일 후의 증상 재발여부를 90%에 달하는 정확도로 예측할 수 있었다. 

 

이번 연구는 환자의 주관적 증상보고 없이도, 객관적인 행동양상과 생체리듬의 교란을 측정해 우울증과 조증 재발을 예측, 진단 가능함을 보여준 최초의 연구란 점에서 의의가 있다.

 

이헌정 교수는 "기분장애환자의 증상발현을 예측할 수 있다는 것은 미리 대응해 증상발현을 조절하거나 완화할 수 있다는 뜻이다. 이는 환자와 가족의 삶의 질을 크게 높이는 효과를 가져올 것"이라고 설명했다.

 

이헌정 교수팀은 이번 연구를 기반으로 울증, 조울증의 재발을 약물치료와 함께 웨어러블기기와 스마트폰의 도움으로 예방하는 기술을 개발하고 있다. 
 

 

*** 아래는 논문 원문 일부 발췌본 (Downloaded from Journal of Medical Internet Research)


Mood Prediction of Patients With Mood Disorders by Machine Learning Using Passive Digital Phenotypes Based on the Circadian Rhythm: Prospective Observational Cohort Study

 

Chul-Hyun Cho1*, MD, PhD; Taek Lee2*, PhD; Min-Gwan Kim3, MS; Hoh Peter In3, PhD; Leen Kim1, MD, PhD;Heon-Jeong Lee1, MD, PhD

 

 

Abstract
 

Background:

Virtually, all organisms on Earth have their own circadian rhythm, and humans are no exception. Circadian rhythms are associated with various human states, especially mood disorders, and disturbance of the circadian rhythm is known to be very closely related. Attempts have also been made to derive clinical implications associated with mood disorders using the vast amounts of digital log that is acquired by digital technologies develop and using computational analysis techniques.

 

Objective:

This study was conducted to evaluate the mood state or episode, activity, sleep, light exposure, and heart rate during a period of about 2 years by acquiring various digital log data through wearable devices and smartphone apps as well as conventional clinical assessments. We investigated a mood prediction algorithm developed with machine learning using passive data phenotypes based on circadian rhythms.

 

Methods:

We performed a prospective observational cohort study on 55 patients with mood disorders (major depressive disorder [MDD] and bipolar disorder type 1 [BD I] and 2 [BD II]) for 2 years. A smartphone app for self-recording daily mood scores and detecting light exposure (using the installed sensor) were provided. From daily worn activity trackers, digital log data of activity, sleep, and heart rate were collected. Passive digital phenotypes were processed into 130 features based on circadian rhythms, and a mood prediction algorithm was developed by random forest.

 

Results:

The mood state prediction accuracies for the next 3 days in all patients, MDD patients, BD I patients, and BD II patients were 65%, 65%, 64%, and 65% with 0.7, 0.69, 0.67, and 0.67 area under the curve (AUC) values, respectively. The accuracies of all patients for no episode (NE), depressive episode (DE), manic episode (ME), and hypomanic episode (HME) were 85.3%, 87%, 94%, and 91.2% with 0.87, 0.87, 0.958, and 0.912 AUC values, respectively. The prediction accuracy in BD II patients was distinctively balanced as high showing 82.6%, 74.4%, and 87.5% of accuracy (with generally good sensitivity and specificity) with 0.919, 0.868, and 0.949 AUC values for NE, DE, and HME, respectively.

 

Conclusions:

On the basis of the theoretical basis of chronobiology, this study proposed a good model for future research by developing a mood prediction algorithm using machine learning by processing and reclassifying digital log data. In addition to academic value, it is expected that this study will be of practical help to improve the prognosis of patients with mood disorders by making it possible to apply actual clinical application owing to the rapid expansion of digital technology.

 

Article Infor.

J Med Internet Res 2019;21(4):e11029

https://www.jmir.org/2019/4/e11029/

 

Figure 2. The performance evaluation of the mood state prediction model. The mood state prediction model outputs one of 2 mood states (ie, biased mood state or neutral mood state) and whether the model outcomes that were correctly matched with the ground truth (ie, the known actual mood states)
was tested. The mood performance was evaluated in terms of the 4 performance evaluation metrics: sensitivity, specificity, accuracy, and area under the curve with the 3 different ground truth labeling criterion: 10%, 30%, and 50% cut-offs in absolute mood score distribution. (A) The performance evaluation result in the case of mood state labeling with 10% cut-off, (B) the performance evaluation result in the case of mood state labeling with 30% cut-off, and (C) the performance evaluation result in the case of mood state labeling with 50% cut-off. MDD: major depressive disorder; BD I: bipolar I disorder; BD II: bipolar II disorder; AUC: area under the curve
출처=Journal of Medical Internet Research 

 

※ 출처  Journal of Medical Internet Research

 


bmb@healthi.kr

 

#고려대안암병원 #정신건강의학과 #이헌정교수 #우울증재발 #조울증예발 #우울증예측 #스마트폰우울증예측 #의료연구성과 #헬스앤라이프