PMID- 35330368
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20220329
IS  - 2075-4426 (Print)
IS  - 2075-4426 (Electronic)
IS  - 2075-4426 (Linking)
VI  - 12
IP  - 3
DP  - 2022 Feb 28
TI  - Extracting New Temporal Features to Improve the Interpretability of Undiagnosed 
      Type 2 Diabetes Mellitus Prediction Models.
LID - 10.3390/jpm12030368 [doi]
LID - 368
AB  - Type 2 diabetes mellitus (T2DM) often results in high morbidity and mortality. In 
      addition, T2DM presents a substantial financial burden for individuals and their 
      families, health systems, and societies. According to studies and reports, 
      globally, the incidence and prevalence of T2DM are increasing rapidly. Several 
      models have been built to predict T2DM onset in the future or detect undiagnosed 
      T2DM in patients. Additional to the performance of such models, their 
      interpretability is crucial for health experts, especially in personalized 
      clinical prediction models. Data collected over 42 months from health check-up 
      examinations and prescribed drugs data repositories of four primary healthcare 
      providers were used in this study. We propose a framework consisting of 
      LogicRegression based feature extraction and Least Absolute Shrinkage and 
      Selection operator based prediction modeling for undiagnosed T2DM prediction. 
      Performance of the models was measured using Area under the ROC curve (AUC) with 
      corresponding confidence intervals. Results show that using LogicRegression based 
      feature extraction resulted in simpler models, which are easier for healthcare 
      experts to interpret, especially in cases with many binary features. Models 
      developed using the proposed framework resulted in an AUC of 0.818 (95% 
      Confidence Interval (CI): 0.812-0.823) that was comparable to more complex models 
      (i.e., models with a larger number of features), where all features were included 
      in prediction model development with the AUC of 0.816 (95% CI: 0.810-0.822). 
      However, the difference in the number of used features was significant. This 
      study proposes a framework for building interpretable models in healthcare that 
      can contribute to higher trust in prediction models from healthcare experts.
FAU - Kocbek, Simon
AU  - Kocbek S
AD  - Institute of Informatics, Faculty of Electrical Engineering and Computer Science, 
      University of Maribor, 2000 Maribor, Slovenia.
FAU - Kocbek, Primoz
AU  - Kocbek P
AUID- ORCID: 0000-0002-9064-5085
AD  - Faculty of Health Sciences, University of Maribor, 2000 Maribor, Slovenia.
FAU - Gosak, Lucija
AU  - Gosak L
AUID- ORCID: 0000-0002-8742-6594
AD  - Faculty of Health Sciences, University of Maribor, 2000 Maribor, Slovenia.
FAU - Fijacko, Nino
AU  - Fijacko N
AUID- ORCID: 0000-0003-2722-0049
AD  - Faculty of Health Sciences, University of Maribor, 2000 Maribor, Slovenia.
FAU - Stiglic, Gregor
AU  - Stiglic G
AUID- ORCID: 0000-0002-0183-8679
AD  - Institute of Informatics, Faculty of Electrical Engineering and Computer Science, 
      University of Maribor, 2000 Maribor, Slovenia.
AD  - Faculty of Health Sciences, University of Maribor, 2000 Maribor, Slovenia.
AD  - Usher Institute, University of Edinburgh, Edinburgh EH8 9YL, UK.
LA  - eng
GR  - ARRS N2-0101 and ARRS P2-0057/Slovenian Research Agency/
GR  - 830927/European Union/
PT  - Journal Article
DEP - 20220228
PL  - Switzerland
TA  - J Pers Med
JT  - Journal of personalized medicine
JID - 101602269
PMC - PMC8950921
OTO - NOTNLM
OT  - LogicRegression
OT  - diabetes mellitus type 2
OT  - interpretability
OT  - prediction model
COIS- The authors declare no conflict of interest.
EDAT- 2022/03/26 06:00
MHDA- 2022/03/26 06:01
PMCR- 2022/02/28
CRDT- 2022/03/25 01:12
PHST- 2021/12/06 00:00 [received]
PHST- 2022/02/13 00:00 [revised]
PHST- 2022/02/25 00:00 [accepted]
PHST- 2022/03/25 01:12 [entrez]
PHST- 2022/03/26 06:00 [pubmed]
PHST- 2022/03/26 06:01 [medline]
PHST- 2022/02/28 00:00 [pmc-release]
AID - jpm12030368 [pii]
AID - jpm-12-00368 [pii]
AID - 10.3390/jpm12030368 [doi]
PST - epublish
SO  - J Pers Med. 2022 Feb 28;12(3):368. doi: 10.3390/jpm12030368.