Validation of a Probabilistic Prediction Model for Patients with Type 1 Diabetes Using Compositional Data Analysis

被引:1
|
作者
Cabrera, Alvis [1 ]
Biagi, Lyvia [2 ]
Beneyto, Aleix [1 ]
Estremera, Ernesto [1 ]
Contreras, Ivan [1 ]
Gimenez, Marga [3 ,4 ]
Conget, Ignacio [3 ,4 ]
Bondia, Jorge [4 ,5 ]
Martin-Fernandez, Josep Antoni [6 ]
Vehi, Josep [1 ,4 ]
机构
[1] Univ Girona, Dept Elect Elect & Automat Engn, Girona 17003, Spain
[2] Fed Univ Technol Parana UTFPR, Campus Guarapuava, BR-85053525 Guarapuava, Brazil
[3] Hosp Clin Barcelona, Endocrinol & Nutr Dept, Diabet Unit, Barcelona 08036, Spain
[4] Inst Salud Carlos III, Ctr Invest Biomed Red Diabet & Enfermedades Metab, Madrid 28029, Spain
[5] Univ Politecn Valencia, Inst Univ Automat Informat Ind, Valencia 46022, Spain
[6] Univ Girona, Dept Comp Sci Appl Math & Stat, Girona 17003, Spain
关键词
compositional data; continuous glucose monitoring; prediction model; time in range; type; 1; diabetes;
D O I
10.3390/math11051241
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
Glycemia assessment in people with type 1 diabetes (T1D) has focused on the time spent in different glucose ranges. As this time reflects the relative contributions to the finite duration of a day, it should be treated as compositional data (CoDa) that can be applied to T1D data. Previous works presented a tool for the individual categorization of days and proposed a probabilistic transition model between categories, although validation has hitherto not been presented. In this study, we consider data from eight real adult patients with T1D obtained from continuous glucose monitoring (CGM) sensors and introduce a methodology based on compositional methods to validate the previously presented probability transition model. We conducted 5-fold cross-validation, with both the training and validation data being CoDa vectors, which requires developing new performance metrics. We design new accuracy and precision measures based on statistical error calculations. The results show that the precision for the entire model is higher than 95% in all patients. The use of a probabilistic transition model can help doctors and patients in diabetes treatment management and decision-making. Although the proposed method was tested with CoDa applied to T1D data obtained from CGM, the newly developed accuracy and precision measures apply to any other data or validation based on CoDa.
引用
收藏
页数:17
相关论文
共 50 条
  • [21] Machine Learning Models for Nocturnal Hypoglycemia Prediction in Hospitalized Patients with Type 1 Diabetes
    Berikov, Vladimir B.
    Kutnenko, Olga A.
    Semenova, Julia F.
    Klimontov, Vadim V.
    JOURNAL OF PERSONALIZED MEDICINE, 2022, 12 (08):
  • [22] Towards Prediction of Type 1 Diabetes Patients Who Fail to Achieve Glycemic Target
    Jensen, Morten Hasselstrom
    Cichosz, Simon
    Hejlesen, Ole
    Hirsch, Irl B.
    Vestergaard, Peter
    DIGITAL PERSONALIZED HEALTH AND MEDICINE, 2020, 270 : 1413 - 1414
  • [23] Prediction of type 2 diabetes mellitus based on nutrition data
    Katsimpris, Andreas
    Brahim, Aboulmaouahib
    Rathmann, Wolfgang
    Peters, Anette
    Strauch, Konstantin
    Flaquer, Antonia
    JOURNAL OF NUTRITIONAL SCIENCE, 2021, 10
  • [24] Development and validation of risk prediction models for stroke and mortality among patients with type 2 diabetes in northern China
    Shao, X.
    Liu, H.
    Hou, F.
    Bai, Y.
    Cui, Z.
    Lin, Y.
    Jiang, X.
    Bai, P.
    Wang, Y.
    Zhang, Y.
    Lu, C.
    Zhou, S.
    Yu, P.
    JOURNAL OF ENDOCRINOLOGICAL INVESTIGATION, 2023, 46 (02) : 271 - 283
  • [25] Development of a coronary heart disease risk prediction model for type 1 diabetes: The Pittsburgh CHD in Type 1 Diabetes Risk Model
    Zgibor, Janice C.
    Ruppert, Kristine
    Orchard, Trevor J.
    Soedamah-Muthu, Sabita S.
    Fuller, John
    Chaturvedi, Nish
    Roberts, Mark S.
    DIABETES RESEARCH AND CLINICAL PRACTICE, 2010, 88 (03) : 314 - 321
  • [26] Delayed treatment of diabetic foot ulcer in patients with type 2 diabetes and its prediction model
    Chen, Hui
    Xi, Ying
    WORLD JOURNAL OF DIABETES, 2024, 15 (10)
  • [27] New Prediction Model for Incidence of Dementia in Patients with Type 2 Diabetes
    Phan Thanh Phuc
    Phung Anh Nguyen
    Hsu, Jason C.
    MEDINFO 2023 - THE FUTURE IS ACCESSIBLE, 2024, 310 : 1354 - 1355
  • [28] Forecasting glucose values for patients with type 1 diabetes using heart rate data
    Giancotti, Raffaele
    Bosoni, Pietro
    Vizza, Patrizia
    Tradigo, Giuseppe
    Gnasso, Agostino
    Guzzi, Pietro Hiram
    Bellazzi, Riccardo
    Irace, Concetta
    Veltri, Pierangelo
    COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2024, 257
  • [29] Individual categorisation of glucose profiles using compositional data analysis
    Biagi, Lyvia
    Bertachi, Arthur
    Gimenez, Marga
    Conget, Ignacio
    Bondia, Jorge
    Antoni Martin-Fernandez, Josep
    Vehi, Josep
    STATISTICAL METHODS IN MEDICAL RESEARCH, 2019, 28 (12) : 3550 - 3567
  • [30] Development and Validation of a Machine Learning Model to Predict Weekly Risk of Hypoglycemia in Patients with Type 1 Diabetes Based on Continuous Glucose Monitoring
    Cichosz, Simon Lebech
    Jensen, Morten Hasselstrom
    Olesen, Soren Schou
    DIABETES TECHNOLOGY & THERAPEUTICS, 2024, 26 (07) : 457 - 466