Modeling an Expert System for Diagnosis of Gestational Diabetes Mellitus Based On Risk Factors

Lakshmi, K

doi:10.9790/0661-0832932

Cited by 7 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Expert systems are computer systems designed to imitate the decision-making ability of a person who has expert knowledge and experience and they usually incorporate a knowledge base containing accumulated experience and an inference or rules engine [23]. An increasing number of expert systems has been proposed to manage diabetes care and to build DSTs, including diabetes diagnosis, therapy adjustment and support to patient self-management [24][25][26][27]. The complexity of diabetes care which is affected by multiple variables and the lack of a gold standard affect the formalization of knowledge when building expert systems in diabetes.…”

Section: Introductionmentioning

confidence: 99%

A web-based clinical decision support system for gestational diabetes: Automatic diet prescription and detection of insulin needs

Caballero-Ruiz

García-Sáez

Rigla

et al. 2017

International Journal of Medical Informatics

120

143

View full text Add to dashboard Cite

Background:The growth of diabetes prevalence is causing an increasing demand in health care services which affects the clinicians' workload as medical resources do not grow at the same rate as the diabetic population. Decision support tools can help clinicians with the inspection of monitoring data, providing a preliminary analysis to ease their interpretation and reduce the evaluation time per patient. This paper presents Sinedie, a clinical decision support system designed to manage the treatment of patients with gestational diabetes. Sinedie aims to improve access to specialized healthcare assistance, to prevent patients from unnecessary displacements, to reduce the evaluation time per patient and to avoid gestational diabetes adverse outcomes. Methods: A web-based telemedicine platform was designed to remotely evaluate patients allowing them to upload their glycaemia data at home directly from their glucose meter, as well as report other monitoring variables like ketonuria and compliance to dietary treatment. Glycaemia values, not tagged by patients, are automatically labelled with their associated meal by a classifier based on the Expectation Maximization clustering algorithm and a C4.5 decision tree learning algorithm. Two finite automata are combined to determine the patient's metabolic condition, which is analysed by a rule-based knowledge base to generate therapy adjustment recommendations. Diet recommendations are automatically prescribed and notified to the patients, whereas recommendations about insulin requirements are notified also to the physicians, who will decide if insulin needs to be prescribed. The system provides clinicians with a view where patients are prioritized according to their metabolic condition. A randomized controlled clinical trial was designed to evaluate the effectiveness and safety oí Sinedie interventions versus standard care and its impact in the professionals' workload in terms of the clinician's time required per patient; number of face-to-face visits; frequency and duration of telematics reviews; patients' compliance to self-monitoring; and patients' satisfaction. Results: Sinedie was clinically evaluated at "Pare Tauli University Hospital" in Spain during 17 months with the participation of 90 patients with gestational diabetes. Sinedie detected all situations that required a therapy adjustment and all the generated recommendations were safe. The time devoted by clinicians to patients' evaluation was reduced by 27.389% and face-to-face visits per patient were reduced by 88.556%. Patients reported to be highly satisfied with the system, considering it useful and trusting in being well controlled. There was no monitoring loss and, in average, patients measured their glycaemia 3.890 times per day and sent their monitoring data every 3.477 days. Conclusions: Sinedie generates safe advice about therapy adjustments, reduces the clinicians' workload and helps physicians to identify which patients need a more urgent or more exhaustive examination and those who present g...

show abstract

Section: Introductionmentioning

confidence: 99%

A web-based clinical decision support system for gestational diabetes: Automatic diet prescription and detection of insulin needs

Caballero-Ruiz

García-Sáez

Rigla

et al. 2017

International Journal of Medical Informatics

120

143

View full text Add to dashboard Cite

show abstract

“…A systematic review and meta-analysis on telemedicine technologies for diabetes in pregnancy conducted by our team in 2016 showed that telemedicine technologies can streamline clinical care delivery and improve maternal satisfaction [ 17 ]. We also evaluated the current state of GDM diagnosis programs by searching Scopus, Web of Science, PubMed, and Embase for studies published in English from inception up to November 17, 2019, using the keywords “gestational diabetes mellitus,” “GDM,” “GDM screening,” “GDM detection,” “GDM diagnosis,” “machine learning,” “artificial intelligence (AI),” and “deep learning.” Although some papers applied AI on screening or early diagnosis of GDM [ 18 , 19 ], they only used the expert system or risk score model instead of up-to-date AI algorithms such as random forest. Recently, a team from Israel applied top 20 contributing features such as baseline risk score and glucose challenge test results of previous pregnancy.…”

Section: Introductionmentioning

confidence: 99%

An Innovative Artificial Intelligence–Based App for the Diagnosis of Gestational Diabetes Mellitus (GDM-AI): Development Study

et al. 2020

View full text Add to dashboard Cite

Background Gestational diabetes mellitus (GDM) can cause adverse consequences to both mothers and their newborns. However, pregnant women living in low- and middle-income areas or countries often fail to receive early clinical interventions at local medical facilities due to restricted availability of GDM diagnosis. The outstanding performance of artificial intelligence (AI) in disease diagnosis in previous studies demonstrates its promising applications in GDM diagnosis. Objective This study aims to investigate the implementation of a well-performing AI algorithm in GDM diagnosis in a setting, which requires fewer medical equipment and staff and to establish an app based on the AI algorithm. This study also explores possible progress if our app is widely used. Methods An AI model that included 9 algorithms was trained on 12,304 pregnant outpatients with their consent who received a test for GDM in the obstetrics and gynecology department of the First Affiliated Hospital of Jinan University, a local hospital in South China, between November 2010 and October 2017. GDM was diagnosed according to American Diabetes Association (ADA) 2011 diagnostic criteria. Age and fasting blood glucose were chosen as critical parameters. For validation, we performed k-fold cross-validation (k=5) for the internal dataset and an external validation dataset that included 1655 cases from the Prince of Wales Hospital, the affiliated teaching hospital of the Chinese University of Hong Kong, a non-local hospital. Accuracy, sensitivity, and other criteria were calculated for each algorithm. Results The areas under the receiver operating characteristic curve (AUROC) of external validation dataset for support vector machine (SVM), random forest, AdaBoost, k-nearest neighbors (kNN), naive Bayes (NB), decision tree, logistic regression (LR), eXtreme gradient boosting (XGBoost), and gradient boosting decision tree (GBDT) were 0.780, 0.657, 0.736, 0.669, 0.774, 0.614, 0.769, 0.742, and 0.757, respectively. SVM also retained high performance in other criteria. The specificity for SVM retained 100% in the external validation set with an accuracy of 88.7%. Conclusions Our prospective and multicenter study is the first clinical study that supports the GDM diagnosis for pregnant women in resource-limited areas, using only fasting blood glucose value, patients’ age, and a smartphone connected to the internet. Our study proved that SVM can achieve accurate diagnosis with less operation cost and higher efficacy. Our study (referred to as GDM-AI study, ie, the study of AI-based diagnosis of GDM) also shows our app has a promising future in improving the quality of maternal health for pregnant women, precision medicine, and long-distance medical care. We recommend future work should expand the dataset scope and replicate the process to validate the performance of the AI algorithms.

show abstract

“…We also evaluated the current state of GDM diagnosis programs by searching Scopus, Web of Science, PubMed, and Embase for studies published in English from inception up to November 17, 2019, using the keywords "gestational diabetes mellitus," "GDM," "GDM screening," "GDM detection," "GDM diagnosis," "machine learning," "artificial intelligence (AI)," and "deep learning." Although some papers applied AI on screening or early diagnosis of GDM [18,19], they only used the expert system or risk score model instead of up-to-date AI algorithms such as random forest. Recently, a team from Israel applied top 20 contributing features such as baseline risk score and glucose challenge test results of previous pregnancy.…”

Section: Introductionmentioning

confidence: 99%

An Innovative Artificial Intelligence–Based App for the Diagnosis of Gestational Diabetes Mellitus (GDM-AI): Development Study (Preprint)

Shen¹,

Chen²,

Zheng³

et al. 2020

Preprint

View full text Add to dashboard Cite

BACKGROUND Gestational diabetes mellitus (GDM) can cause adverse consequences to both mothers and their newborns. However, pregnant women living in low- and middle-income areas or countries often fail to receive early clinical interventions at local medical facilities due to restricted availability of GDM diagnosis. The outstanding performance of artificial intelligence (AI) in disease diagnosis in previous studies demonstrates its promising applications in GDM diagnosis. OBJECTIVE This study aims to investigate the implementation of a well-performing AI algorithm in GDM diagnosis in a setting, which requires fewer medical equipment and staff and to establish an app based on the AI algorithm. This study also explores possible progress if our app is widely used. METHODS An AI model that included 9 algorithms was trained on 12,304 pregnant outpatients with their consent who received a test for GDM in the obstetrics and gynecology department of the First Affiliated Hospital of Jinan University, a local hospital in South China, between November 2010 and October 2017. GDM was diagnosed according to American Diabetes Association (ADA) 2011 diagnostic criteria. Age and fasting blood glucose were chosen as critical parameters. For validation, we performed k-fold cross-validation (k=5) for the internal dataset and an external validation dataset that included 1655 cases from the Prince of Wales Hospital, the affiliated teaching hospital of the Chinese University of Hong Kong, a non-local hospital. Accuracy, sensitivity, and other criteria were calculated for each algorithm. RESULTS The areas under the receiver operating characteristic curve (AUROC) of external validation dataset for support vector machine (SVM), random forest, AdaBoost, k-nearest neighbors (kNN), naive Bayes (NB), decision tree, logistic regression (LR), eXtreme gradient boosting (XGBoost), and gradient boosting decision tree (GBDT) were 0.780, 0.657, 0.736, 0.669, 0.774, 0.614, 0.769, 0.742, and 0.757, respectively. SVM also retained high performance in other criteria. The specificity for SVM retained 100% in the external validation set with an accuracy of 88.7%. CONCLUSIONS Our prospective and multicenter study is the first clinical study that supports the GDM diagnosis for pregnant women in resource-limited areas, using only fasting blood glucose value, patients’ age, and a smartphone connected to the internet. Our study proved that SVM can achieve accurate diagnosis with less operation cost and higher efficacy. Our study (referred to as GDM-AI study, ie, the study of AI-based diagnosis of GDM) also shows our app has a promising future in improving the quality of maternal health for pregnant women, precision medicine, and long-distance medical care. We recommend future work should expand the dataset scope and replicate the process to validate the performance of the AI algorithms.

show abstract

Modeling an Expert System for Diagnosis of Gestational Diabetes Mellitus Based On Risk Factors

Cited by 7 publications

References 7 publications

A web-based clinical decision support system for gestational diabetes: Automatic diet prescription and detection of insulin needs

A web-based clinical decision support system for gestational diabetes: Automatic diet prescription and detection of insulin needs

An Innovative Artificial Intelligence–Based App for the Diagnosis of Gestational Diabetes Mellitus (GDM-AI): Development Study

An Innovative Artificial Intelligence–Based App for the Diagnosis of Gestational Diabetes Mellitus (GDM-AI): Development Study (Preprint)

Contact Info

Product

Resources

About