AutoML과 라이프로그를 활용한 인지기능 장애 예측모형
Cognitive Impairment Prediction Model Using AutoML and Lifelog
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
본 연구는 고령층의 치매 예방을 위한 선별검사 수단으로 자동화된 기계학습(AutoML)을 활용하여인지기능 장애 예측모형을 개발하였다. 연구 데이터는 한국지능정보사회진흥원의 ‘치매 고위험군 웨어러블 라이프로그 데이터’를 활용하였다. 분석은 구글 코랩 환경에서 PyCaret 3.0.0이 사용하여 우수한분류성능을 보여주는 5개의 모형을 선정하고 앙상블 학습을 진행하여 모형을 통합한 뒤, 최종 성능평가를 진행하였다. 연구결과, Voting Classifier, Gradient Boosting Classifier, Extreme Gradient Boosting, Light Gradient Boosting Machine, Extra Trees Classifier, Random Forest Classifier 모형 순으로 높은 예측성능을보이는 것으로 나타났다. 특히 ‘수면 중 분당 평균 호흡수’와 ‘수면 중 분당 평균 심박수’가 가장 중요한특성변수(feature)로 확인되었다. 본 연구의 결과는 고령층의 인지기능 장애를 보다 효과적으로 관리하고예방하기 위한 수단으로 기계학습과 라이프로그의 활용 가능성에 대한 고려를 시사한다.
Abstract
This study developed a cognitive impairment predictive model as one of the screening tests for preventing dementia in the elderly by using Automated Machine Learning(AutoML). We used ‘Wearable lifelog data for high-risk dementia patients’ of National Information Society Agency, then conducted using PyCaret 3.0.0 in the Google Colaboratory environment. This study analysis steps are as follows; first, selecting five models demonstrating excellent classification performance for the model development and lifelog data analysis. Next, using ensemble learning to integrate these models and assess their performance. It was found that Voting Classifier, Gradient Boosting Classifier, Extreme Gradient Boosting, Light Gradient Boosting Machine, Extra Trees Classifier, and Random Forest Classifier model showed high predictive performance in that order. This study findings, furthermore, emphasized on the the crucial importance of 'Average respiration per minute during sleep' and 'Average heart rate per minute during sleep' as the most critical feature variables for accurate predictions. Finally, these study results suggest that consideration of the possibility of using machine learning and lifelog as a means to more effectively manage and prevent cognitive impairment in the elderly.
참고문헌 (40)
- "2022 Statistics of the aged, Statistics Korea Press"[URL]
- "2021 Statistics index of the medical care cost"[URL]
- 백원희, "고령화연구패널조사 자료를 이용한 노인 인지기능의 영향요인: 인구통계학적, 사회·심리적, 신체적, 건강관련행위 특성을 중심으로", Journal of The Korean Data Analysis Society, 24(5), pp.1893~1906 (2022), 한국자료분석학회[DOI]
- 박대우, "경도인지장애 환자군에서 치매 발병 시점에 영향을 미치는 요인에 대한 연구", 보건정보통계학회지, 47(4), pp.307~311 (2022), 한국보건정보통계학회[DOI]
- 오응석, "경도인지장애", 대한신경과학회지, 34(3), pp.167~175 (2016), 대한신경과학회[DOI]
- Ronald C. Petersen, "MILD COGNITIVE IMPAIRMENT", CONTINUUM: Lifelong Learning in Neurology, 10(1), pp.9~28 (2004), Ovid Technologies (Wolters Kluwer Health)[DOI]
- A. So, "Analysis for Development of The Dementia Sorting System using Machine Learning Techniques", The Korean Association Of Computer Education Academic Conference Papers, 19(1), pp.137~140 (2015)
- 장경오, "G시 공무원의 치매인식과 치매두려움이 치매태도에 미치는 영향", Journal of The Korean Data Analysis Society, 24(2), pp.873~886 (2022), 한국자료분석학회[DOI]
- 최호진, "치매국가책임제의 현재와 미래", 대한신경과학회지, 36(3), pp.152~158 (2018), 대한신경과학회[DOI]
- 김태훈, "랜덤 포레스트 모델을 이용한 자살 사고 영향요인 분석", Journal of The Korean Data Analysis Society, 25(3), pp.1121~1132 (2023), 한국자료분석학회[DOI]
- 이태인, "이기종 머신러닝 모델 기반 치매예측 모델", 한국정보통신학회논문지, 25(12), pp.1729~1738 (2021), 한국정보통신학회[DOI]
- 권승원, "이기종 스마트워치의 라이프로그 수집을 위한 관계형데이터베이스 모델", 한국정보기술학회논문지, 16(9), pp.13~21 (2018), 한국정보기술학회[DOI]
- 한건희, "빅데이터에 대한 소개와 활용사례에 관한 연구", Journal of The Korean Data Analysis Society, 16(3), pp.1337~1351 (2014), 한국자료분석학회
- W. Jo, "Lifelog big data-based lifestyle(life pattern)analysis and wellness predictive care service system using IoT", The Journal of The Korean Institute of Communication Sciences, 31(12), pp.17~24 (2014)
- Cees Jonker, "Are memory complaints predictive for dementia? A review of clinical and population-based studies", International Journal of Geriatric Psychiatry, 15(11), pp.983~991 (2000), Wiley[DOI]
- Glenn J. Larrabee, "Estimated Prevalence of Age-Associated Memory Impairment Derived From Standardized Tests of Memory Function", International Psychogeriatrics, 6(1), pp.95~104 (2005), Cambridge University Press (CUP)[DOI]
- "99 Stories of dementia" (2012)[URL]
- ROBERT L. KAHN, "BRIEF OBJECTIVE MEASURES FOR THE DETERMINATION OF MENTAL STATUS IN THE AGED", American Journal of Psychiatry, 117(4), pp.326~328 (1960), American Psychiatric Association Publishing[DOI]
- M. F. Folstein, "Mini-mental state : a practical method for grading the cognitive state of patients for the clinician", Journal of psychiatric research, 12(3), pp.189~198 (1975)
- 이삼연, "치매선별 검사도구", 생물치료정신의학, 12(2), pp.131~139 (2006), 대한생물치료정신의학회
- Jong‐Han Park, "Modification of the mini‐mental state examination for use in the elderly in a non‐western society. Part 1. Development of korean version of mini‐mental state examination", International Journal of Geriatric Psychiatry, 5(6), pp.381~387 (1990), Wiley[DOI]
- Y. Kang, "A Validity Study on the Korean Mini-Mental State Examination(K-MMSE)in Dementia Patients", J Korean Neurol Assoc, 15(2), pp.300~308 (1997)
- S. H. Choi, "A Short form of the Samsung Dementia Questionnaire(S-SDQ) : development and cross-validation", J Korean Neurol Assoc, 17(2), pp.253~258 (1999)
- D. Galasko, "The Mini-Mental State Examination in the Early Diagnosis of Alzheimer's Disease", Archives of Neurology, 47(1), pp.49~52 (1990), American Medical Association (AMA)[DOI]
- Christopher M. Clark, "Variability in Annual Mini-Mental State Examination Score in Patients With Probable Alzheimer Disease", Archives of Neurology, 56(7), pp.857~862 (1999), American Medical Association (AMA)[DOI]
- Samaneh A. Mofrad, "Cognitive and MRI trajectories for prediction of Alzheimer’s disease", Scientific Reports, 11(1) (2021), Springer Science and Business Media LLC[DOI]
- Ali Haidar Syaifullah, "Machine Learning for Diagnosis of AD and Prediction of MCI Progression From Brain MRI Using Brain Anatomical Analysis Using Diffeomorphic Deformation", Frontiers in Neurology, 11, pp.1~13 (2021), Frontiers Media SA[DOI]
- S. H. Lee, "Lifelog-based classification of mild cognitive impairment using artificial neural networks", 2018 International Conference on Electronics, Information, and Communication (ICEIC), pp.1~2 (2018), IEEE
- T. Nagarajah, "A review on automated machine learning (AutoML) systems", IEEE, pp.1~6 (2019)
- 남경훈, "AutoML을 이용한 산사태 예측 및 변수 중요도 산정", 지질공학, 30(3), pp.315~325 (2020), 대한지질공학회
- M. Graczyk, "Comparison of bagging, boosting and stacking ensembles applied to real estate appraisal", Intelligent Information and Database Systems: Second International Conference, ACIIDS, pp.340~350 (2010), Springer Berlin Heidelberg, Proceedings
- Abdulla Amin Aburomman, "A novel SVM-kNN-PSO ensemble method for intrusion detection system", Applied Soft Computing, 38, pp.360~372 (2016), Elsevier BV[DOI]
- Tianao Wu, "Evaluation of stacking and blending ensemble learning methods for estimating daily reference evapotranspiration", Computers and Electronics in Agriculture, 184, pp.106039~ (2021), Elsevier BV[DOI]
- Saloni Kumari, "An ensemble approach for classification and prediction of diabetes mellitus using soft voting classifier", International Journal of Cognitive Computing in Engineering, 2, pp.40~46 (2021), Elsevier BV[DOI]
- W. Muangpaisan, "Neuropsychiatric symptoms in the community‐based patients with mild cognitive impairment and the influence of demographic factors", International Journal of Geriatric Psychiatry, 23(7), pp.699~703 (2008), Wiley[DOI]
- 정서연, "요양병원에 거주하는 경도인지장애 노인의 수면의 질 관련요인", 노인간호학회지, 24(2), pp.210~217 (2022), 한국노인간호학회[DOI]
- 임찬영, "경도인지장애 환자에서 수면문제와 인지저하의 연관성", 생물치료정신의학, 22(3), pp.187~195 (2016), 대한생물치료정신의학회
- 이경환, "수면과 알츠하이머 치매의 관계", 수면정신생리, 29(1), pp.1~3 (2022), 대한수면의학회[DOI]
- B. H. Choi, "Neurocognitive Function in Obstructive Sleep Apnea Patients. Sleep Medicine and Psychophysiology", Sleep Med Psychophysiol, 3(1), pp.38~46 (1996)
- Takayuki KAGEYAMA, "Self-Reported Sleep Quality, Job Stress, and Daytime Autonomic Activities Assessed in Terms of Short-Term Heart Rate Variability among Male White-Collar Workers.", INDUSTRIAL HEALTH, 36(3), pp.263~272 (1998), National Institute of Industrial Health[DOI]