PMID- 29862384
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20201001
IS  - 2575-2626 (Print)
IS  - 2575-2626 (Linking)
VI  - 2017
DP  - 2017 Aug
TI  - Estimating Disease Onset Time by Modeling Lab Result Trajectories via Bayes 
      Networks.
PG  - 374-379
LID - 10.1109/ICHI.2017.41 [doi]
AB  - The true onset time of a disease, particularly slow-onset diseases like Type 2 
      diabetes mellitus (T2DM), is rarely observable in electronic health records 
      (EHRs). However, it is critical for analysis of time to events and for studying 
      sequences of diseases. The aim of this study is to demonstrate a method for 
      estimating the onset time of such diseases from intermittently observable 
      laboratory results in the specific context of T2DM. A retrospective observational 
      study design is used. A cohort of 5,874 non-diabetic patients from a large 
      healthcare system in the Upper Midwest United States was constructed with a 
      three-year follow-up period. The HbA1c level of each patient was collected from 
      earliest and the latest follow-up. We modeled the patients' HbA1c trajectories 
      through Bayesian networks to estimate the onset time of diabetes. Due to 
      non-random censoring and interventions unobservable from EHR data (such as 
      lifestyle changes), naive modeling of HbA1c through linear regression or modeling 
      time-to-event through proportional hazard model leads to a clinically infeasible 
      model with no or limited ability to predict the onset time of diabetes. Our model 
      is consistent with clinical knowledge and estimated the onset of diabetes with 
      less than a six-month error for almost half the patients for whom the onset time 
      could be clinically ascertained. To our knowledge, this is the first study of 
      modeling long-term HbA1c progression in non-diabetic patients and estimating the 
      onset time of diabetes.
FAU - Oh, Wonsuk
AU  - Oh W
AD  - Institute for Health Informatics, University of Minnesota.
FAU - Yadav, Pranjul
AU  - Yadav P
AD  - Department of Computer Science and Engineering, University of Minnesota.
FAU - Kumar, Vipin
AU  - Kumar V
AD  - Department of Computer Science and Engineering, University of Minnesota.
FAU - Caraballo, Pedro J
AU  - Caraballo PJ
AD  - Division of General Internal Medicine, Mayo Clinic.
FAU - Castro, M Regina
AU  - Castro MR
AD  - Division of Endocrinology, Diabetes, Metabolism & Nutrition, Mayo Clinic.
FAU - Steinbach, Michael S
AU  - Steinbach MS
AD  - Department of Computer Science and Engineering, University of Minnesota.
FAU - Simon, Gyorgy J
AU  - Simon GJ
AD  - Institute for Health Informatics, University of Minnesota.
AD  - Department of Medicine, University of Minnesota.
LA  - eng
GR  - R01 LM011972/LM/NLM NIH HHS/United States
PT  - Journal Article
DEP - 20170914
PL  - United States
TA  - IEEE Int Conf Healthc Inform
JT  - IEEE International Conference on Healthcare Informatics. IEEE International 
      Conference on Healthcare Informatics
JID - 101683411
PMC - PMC5975351
MID - NIHMS968577
EDAT- 2018/06/05 06:00
MHDA- 2018/06/05 06:01
PMCR- 2018/05/30
CRDT- 2018/06/05 06:00
PHST- 2018/06/05 06:00 [entrez]
PHST- 2018/06/05 06:00 [pubmed]
PHST- 2018/06/05 06:01 [medline]
PHST- 2018/05/30 00:00 [pmc-release]
AID - 10.1109/ICHI.2017.41 [doi]
PST - ppublish
SO  - IEEE Int Conf Healthc Inform. 2017 Aug;2017:374-379. doi: 10.1109/ICHI.2017.41. 
      Epub 2017 Sep 14.