Predicting the onset of Alzheimer's disease and related dementia using electronic health records: findings from the cache county study on memory in aging (1995-2008)

被引:0
作者
Schliep, Karen C. [1 ]
Thornhill, Jeffrey [1 ]
Tschanz, JoAnn T. [2 ,3 ]
Facelli, Julio C. [4 ]
Ostbye, Truls [5 ]
Sorweid, Michelle K. [6 ]
Smith, Ken R. [7 ]
Varner, Michael [8 ]
Boyce, Richard D. [9 ]
Cliatt Brown, Christine J. [10 ]
Meeks, Huong [11 ]
Abdelrahman, Samir [1 ]
机构
[1] Univ Utah Hlth, Dept Family & Prevent Med, Div Publ Hlth, 375 Chipeta Way, Suite, Salt Lake City, UT 84108 USA
[2] Utah State Univ, Dept Psychol, Logan, UT 84322 USA
[3] Utah State Univ, Alzheimers Dis & Dementia Res Ctr, Logan, UT 84322 USA
[4] Univ Utah Hlth, Dept Biomed Informat, Salt Lake City, UT 84108 USA
[5] Duke Univ, Community & Family Med & Community Hlth, Nursing & Global Hlth, Durham, NC 27710 USA
[6] Univ Utah Hlth, Dept Geriatr, Salt Lake City, UT 84132 USA
[7] Univ Utah, Dept Family & Consumer Studies, Salt Lake City, UT 84112 USA
[8] Univ Utah, Dept Obstet & Gynecol, Salt Lake City, UT 84132 USA
[9] Univ Pittsburgh, Dept Biomed Informat, Pittsburgh, PA 15260 USA
[10] Univ Utah, Dept Neurol, Salt Lake City, UT 84132 USA
[11] Univ Utah, Dept Pediat, Salt Lake City, UT 84108 USA
关键词
Dementia; Diagnosis; Machine learning; Medical records; Prospective cohort; Alzheimer's disease; PREVALENCE; DIAGNOSIS;
D O I
10.1186/s12911-024-02728-4
中图分类号
R-058 [];
学科分类号
摘要
IntroductionClinical notes, biomarkers, and neuroimaging have proven valuable in dementia prediction models. Whether commonly available structured clinical data can predict dementia is an emerging area of research. We aimed to predict gold-standard, research-based diagnoses of dementia including Alzheimer's disease (AD) and/or Alzheimer's disease related dementias (ADRD), in addition to ICD-based AD and/or ADRD diagnoses, in a well-phenotyped, population-based cohort using a machine learning approach.MethodsAdministrative healthcare data (k = 163 diagnostic features), in addition to census/vital record sociodemographic data (k = 6 features), were linked to the Cache County Study (CCS, 1995-2008).ResultsAmong successfully linked UPDB-CCS participants (n = 4206), 522 (12.4%) had incident dementia (AD alone, AD comorbid with ADRD, or ADRD alone) as per the CCS "gold standard" assessments. Random Forest models, with a 1-year prediction window, achieved the best performance with an Area Under the Curve (AUC) of 0.67. Accuracy declined for dementia subtypes: AD/ADRD (AUC = 0.65); ADRD (AUC = 0.49). Accuracy improved when using ICD-based dementia diagnoses (AUC = 0.77).DiscussionCommonly available structured clinical data (without labs, notes, or prescription information) demonstrate modest ability to predict "gold-standard" research-based AD/ADRD diagnoses, corroborated by prior research. Using ICD diagnostic codes to identify dementia as done in the majority of machine learning dementia prediction models, as compared to "gold-standard" dementia diagnoses, can result in higher accuracy, but whether these models are predicting true dementia warrants further research.
引用
收藏
页数:10
相关论文
共 30 条
  • [1] [Anonymous], 2023, 2023 Alzheimer's disease facts and figures
  • [2] Development and Validation of eRADAR: A Tool Using EHR Data to Detect Unrecognized Dementia
    Barnes, Deborah E.
    Zhou, Jing
    Walker, Rod L.
    Larson, Eric B.
    Lee, Sei J.
    Boscardin, W. John
    Marcum, Zachary A.
    Dublin, Sascha
    [J]. JOURNAL OF THE AMERICAN GERIATRICS SOCIETY, 2020, 68 (01) : 103 - 111
  • [3] Predicting dementia with routine care EMR data
    Ben Miled, Zina
    Haas, Kyle
    Black, Christopher M.
    Khandker, Rezaul Karim
    Chandrasekaran, Vasu
    Lipton, Richard
    Boustani, Malaz A.
    [J]. ARTIFICIAL INTELLIGENCE IN MEDICINE, 2020, 102
  • [4] Introduction to Supervised Machine Learning
    Biswas, Aditya
    Saran, Ishan
    Wilson, F. Perry
    [J]. KIDNEY360, 2021, 2 (05): : 878 - 880
  • [5] Missed and Delayed Diagnosis of Dementia in Primary Care Prevalence and Contributing Factors
    Bradford, Andrea
    Kunik, Mark E.
    Schulz, Paul
    Williams, Susan P.
    Singh, Hardeep
    [J]. ALZHEIMER DISEASE & ASSOCIATED DISORDERS, 2009, 23 (04) : 306 - 314
  • [6] APOE-ε4 count predicts age when prevalence of AD increases, then declines -: The Cache County Study
    Breitner, JCS
    Wyse, BW
    Anthony, JC
    Welsh-Bohmer, KA
    Steffens, DC
    Norton, MC
    Tschanz, JT
    Plassman, BL
    Meyer, MR
    Skoog, I
    Khachaturian, A
    [J]. NEUROLOGY, 1999, 53 (02) : 321 - 331
  • [7] Multifactorial 10-Year Prior Diagnosis Prediction Model of Dementia
    Dallora, Ana Luiza
    Minku, Leandro
    Mendes, Emilia
    Rennemark, Mikael
    Anderberg, Peter
    Sanmartin Berglund, Johan
    [J]. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH, 2020, 17 (18) : 1 - 18
  • [8] Automated detection of patients with dementia whose symptoms have been identified in primary care but have no formal diagnosis: a retrospective case-control study using electronic primary care records
    Ford, Elizabeth
    Sheppard, Joanne
    Oliver, Seb
    Rooney, Philip
    Banerjee, Sube
    Cassell, Jackie A.
    [J]. BMJ OPEN, 2021, 11 (01):
  • [9] Alzheimer-type dementia prediction by sparse logistic regression using claim data
    Fukunishi, Hiroaki
    Nishiyama, Mitsuki
    Luo, Yuan
    Kubo, Masahiro
    Kobayashi, Yasuki
    [J]. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2020, 196
  • [10] Hayden K M, 2005, Alzheimers Dement, V1, P19, DOI 10.1016/j.jalz.2005.06.002