PMID- 32100174
OWN - NLM
STAT- MEDLINE
DCOM- 20210222
LR  - 20210222
IS  - 1741-0444 (Electronic)
IS  - 0140-0118 (Linking)
VI  - 58
IP  - 5
DP  - 2020 May
TI  - Use of a K-nearest neighbors model to predict the development of type 2 diabetes 
      within 2 years in an obese, hypertensive population.
PG  - 991-1002
LID - 10.1007/s11517-020-02132-w [doi]
AB  - Prediabetes is a type of hyperglycemia in which patients have blood glucose 
      levels above normal but below the threshold for type 2 diabetes mellitus (T2DM). 
      Prediabetic patients are considered to be at high risk for developing T2DM, but 
      not all will eventually do so. Because it is difficult to identify which patients 
      have an increased risk of developing T2DM, we developed a model of several 
      clinical and laboratory features to predict the development of T2DM within a 
      2-year period. We used a supervised machine learning algorithm to identify 
      at-risk patients from among 1647 obese, hypertensive patients. The study period 
      began in 2005 and ended in 2018. We constrained data up to 2 years before the 
      development of T2DM. Then, using a time series analysis with the features of 
      every patient, we calculated one linear regression line and one slope per 
      feature. Features were then included in a K-nearest neighbors classification 
      model. Feature importance was assessed using the random forest algorithm. The 
      K-nearest neighbors model accurately classified patients in 96% of cases, with a 
      sensitivity of 99%, specificity of 78%, positive predictive value of 96%, and 
      negative predictive value of 94%. The random forest algorithm selected the 
      homeostatic model assessment-estimated insulin resistance, insulin levels, and 
      body mass index as the most important factors, which in combination with KNN had 
      an accuracy of 99% with a sensitivity of 99% and specificity of 97%. We built a 
      prognostic model that accurately identified obese, hypertensive patients at risk 
      for developing T2DM within a 2-year period. Clinicians may use machine learning 
      approaches to better assess risk for T2DM and better manage hypertensive 
      patients. Machine learning algorithms may help health care providers make more 
      informed decisions.
FAU - Garcia-Carretero, Rafael
AU  - Garcia-Carretero R
AUID- ORCID: 0000-0001-7532-4585
AD  - Internal Medicine Department, Mostoles University Hospital, Rey Juan Carlos 
      University, Calle Rio Jucar, s/n, 28935, Mostoles (Madrid), Spain. 
      rgcarretero@salud.madrid.org.
FAU - Vigil-Medina, Luis
AU  - Vigil-Medina L
AD  - Internal Medicine Department, Mostoles University Hospital, Rey Juan Carlos 
      University, Calle Rio Jucar, s/n, 28935, Mostoles (Madrid), Spain.
FAU - Mora-Jimenez, Inmaculada
AU  - Mora-Jimenez I
AD  - Department of Signal Theory and Communications and Telematics Systems and 
      Computing, Rey Juan Carlos University, Mostoles, Spain.
FAU - Soguero-Ruiz, Cristina
AU  - Soguero-Ruiz C
AD  - Department of Signal Theory and Communications and Telematics Systems and 
      Computing, Rey Juan Carlos University, Mostoles, Spain.
FAU - Barquero-Perez, Oscar
AU  - Barquero-Perez O
AD  - Department of Signal Theory and Communications and Telematics Systems and 
      Computing, Rey Juan Carlos University, Mostoles, Spain.
FAU - Ramos-Lopez, Javier
AU  - Ramos-Lopez J
AD  - Department of Signal Theory and Communications and Telematics Systems and 
      Computing, Rey Juan Carlos University, Mostoles, Spain.
LA  - eng
GR  - TEC2016-75361-R/Ministry of Science, Innovation and Universities/
GR  - TEC2016-75161-C2-1-R/Ministry of Science, Innovation and Universities/
GR  - DTS17/00158/Instituto de Salud Carlos III/
PT  - Journal Article
DEP - 20200226
PL  - United States
TA  - Med Biol Eng Comput
JT  - Medical & biological engineering & computing
JID - 7704869
SB  - IM
MH  - Adult
MH  - Aged
MH  - Algorithms
MH  - *Diabetes Mellitus, Type 2/complications/diagnosis/epidemiology
MH  - Female
MH  - Humans
MH  - *Hypertension/complications/epidemiology
MH  - Machine Learning
MH  - Male
MH  - Middle Aged
MH  - *Models, Statistical
MH  - *Obesity/complications/epidemiology
MH  - Sensitivity and Specificity
OTO - NOTNLM
OT  - Cardiovascular risk assessment
OT  - K-nearest neighbors
OT  - Random forest
OT  - Type 2 diabetes mellitus
EDAT- 2020/02/27 06:00
MHDA- 2021/02/23 06:00
CRDT- 2020/02/27 06:00
PHST- 2019/04/17 00:00 [received]
PHST- 2020/01/19 00:00 [accepted]
PHST- 2020/02/27 06:00 [pubmed]
PHST- 2021/02/23 06:00 [medline]
PHST- 2020/02/27 06:00 [entrez]
AID - 10.1007/s11517-020-02132-w [pii]
AID - 10.1007/s11517-020-02132-w [doi]
PST - ppublish
SO  - Med Biol Eng Comput. 2020 May;58(5):991-1002. doi: 10.1007/s11517-020-02132-w. 
      Epub 2020 Feb 26.