Predicting 10-Year Risk of End-Organ Complications of Type 2 Diabetes With and Without Metabolic Surgery: A Machine Learning Approach

Machine learning techniques to predict the risk of developing diabetic nephropathy: a literature review

Purpose

Diabetes is a major public health challenge with widespread prevalence, often leading to complications such as Diabetic Nephropathy (DN)-a chronic condition that progressively impairs kidney function. In this context, it is important to evaluate if Machine learning models can exploit the inherent temporal factor in clinical data to predict the risk of developing DN faster and more accurately than current clinical models.

Methods

Three different databases were used for this literature review: Scopus, Web of Science, and PubMed. Only articles written in English and published between January 2015 and December 2022 were included.

Results

We included 11 studies, from which we discuss a number of algorithms capable of extracting knowledge from clinical data, incorporating dynamic aspects in patient assessment, and exploring their evolution over time. We also present a comparison of the different approaches, their performance, advantages, disadvantages, interpretation, and the value that the time factor can bring to a more successful prediction of diabetic nephropathy.

Conclusion

Our analysis showed that some studies ignored the temporal factor, while others partially exploited it. Greater use of the temporal aspect inherent in Electronic Health Records (EHR) data, together with the integration of omics data, could lead to the development of more reliable and powerful predictive models.

Machine Learning Models for Prediction of Diabetic Microvascular Complications

IMPORTANCE AND AIMS

Diabetic microvascular complications significantly impact morbidity and mortality. This review focuses on machine learning/artificial intelligence (ML/AI) in predicting diabetic retinopathy (DR), diabetic kidney disease (DKD), and diabetic neuropathy (DN).

METHODS

A comprehensive PubMed search from 1990 to 2023 identified studies on ML/AI models for diabetic microvascular complications. The review analyzed study design, cohorts, predictors, ML techniques, prediction horizon, and performance metrics.

RESULTS

Among the 74 identified studies, 256 featured internally validated ML models and 124 had externally validated models, with about half being retrospective. Since 2010, there has been a rise in the use of ML for predicting microvascular complications, mainly driven by DKD research across 27 countries. A more modest increase in ML research on DR and DN was observed, with publications from fewer countries. For all microvascular complications, predictive models achieved a mean (standard deviation) c-statistic of 0.79 (0.09) on internal validation and 0.72 (0.12) on external validation. Diabetic kidney disease models had the highest discrimination, with c-statistics of 0.81 (0.09) on internal validation and 0.74 (0.13) on external validation, respectively. Few studies externally validated prediction of DN. The prediction horizon, outcome definitions, number and type of predictors, and ML technique significantly influenced model performance.

CONCLUSIONS AND RELEVANCE

There is growing global interest in using ML for predicting diabetic microvascular complications. Research on DKD is the most advanced in terms of publication volume and overall prediction performance. Both DR and DN require more research. External validation and adherence to recommended guidelines are crucial.

Benefits of metabolic surgery on macrovascular outcomes in adult patients with type 2 diabetes: a systematic review and meta-analysis

Type 2 diabetes (T2D) is a chronic metabolic disorder that affects millions of individuals associated with an increased risk of mortality and macrovascular complications. We aimed to synthesize the benefit of metabolic surgery (MS) on macrovascular outcomes in adult patients with T2D.We included both cohort studies and randomized controlled trials (RCTs) that evaluated MS added to medical therapy compared with medical therapy alone in the treatment of adult patients with T2D. Studies must have evaluated the incidence of any macrovascular complication of the disease for a period of at least 6 months. We performed our search using PubMed, Scopus, EMBASE, Web of Science, and COCHRANE Central database which was performed from inception date until March 2022. The trial protocol was previously registered at PROSPERO (CRD42021243739). A total of 6338 references were screened throughout the selection process from which 16 studies involving 179,246 participants fulfilled inclusion criteria. MS reduced the risk of any cardiovascular event by 44% (relative risk .56 [95% CI, .42-.75]; P = < .001), myocardial infarction by 54% (.46 [95% CI, .26-.83]; P = .009), coronary artery disease by 40% (.60 [95% CI, .42-.85]; P = .004) and heart failure by 71% (.29 [95% CI, .14-.61]; P = .001). It also provided a risk reduction of stroke by 29% (.71 [95% CI, .51-.99]; P = .04) and 38% (.62 [95% CI, .46-.85]; P = .001) for cerebrovascular events. On mortality, MS yields a risk reduction of 55% (.45 [95% CI, .36-.57]; P <.001) in overall mortality and 69% in cardiovascular mortality (relative risk .31 [95% CI, .22-.42]; P < .001). Peripheral vascular disease risk was also reduced. MS in adult patients with T2D can reduce the risk of mortality and of any macrovascular outcomes. However, there is a need for the planning of randomized clinical trials to further analyze and confirm the results.

The Pulse of AI: Implementation of Artificial Intelligence in Healthcare and its Potential Hazards

In this editorial, we explore the existing utilization of artificial intelligence (AI) within the healthcare industry, examining both its scope and potential harms if implemented and relied upon on a broader scale. Collaboration among corporations, government bodies, policymakers, and medical experts is essential to address potential concerns, ensuring smooth AI integration into healthcare systems.

Prognostic models for heart failure in patients with type 2 diabetes: a systematic review and meta-analysis

OBJECTIVE

To provide a systematic review, critical appraisal, assessment of performance and generalisability of all the reported prognostic models for heart failure (HF) in patients with type 2 diabetes (T2D).

METHODS

We performed a literature search in Medline, Embase, Central Register of Controlled Trials, Cochrane Database of Systematic Reviews and Scopus (from inception to July 2022) and grey literature to identify any study developing and/or validating models predicting HF applicable to patients with T2D. We extracted data on study characteristics, modelling methods and measures of performance, and we performed a random-effects meta-analysis to pool discrimination in models with multiple validation studies. We also performed a descriptive synthesis of calibration and we assessed the risk of bias and certainty of evidence (high, moderate, low).

RESULTS

Fifty-five studies reporting on 58 models were identified: (1) models developed in patients with T2D for HF prediction (n=43), (2) models predicting HF developed in non-diabetic cohorts and externally validated in patients with T2D (n=3), and (3) models originally predicting a different outcome and externally validated for HF (n=12). RECODe (C-statistic=0.75 95% CI (0.72, 0.78), 95% prediction interval (PI) (0.68, 0.81); high certainty), TRS-HFDM (C-statistic=0.75 95% CI (0.69, 0.81), 95% PI (0.58, 0.87); low certainty) and WATCH-DM (C-statistic=0.70 95% CI (0.67, 0.73), 95% PI (0.63, 0.76); moderate certainty) showed the best performance. QDiabetes-HF demonstrated also good discrimination but was externally validated only once and not meta-analysed.

CONCLUSIONS

Among the prognostic models identified, four models showed promising performance and, thus, could be implemented in current clinical practice.

Benefits of bariatric surgery on microvascular outcomes in adult patients with type 2 diabetes: a systematic review and meta-analysis

BACKGROUND

Microvascular diabetes complications impair patients' health-related quality of life. Bariatric surgery (BS) emerged as a compelling treatment that demonstrated to have beneficial effects on patients with diabetes and obesity.

OBJECTIVE

We aimed to synthesize the benefit of bariatric surgery on microvascular outcomes in adult patients with type 2 diabetes.

SETTING

2011-2021.

METHODS

We included both cohort studies and randomized trials that evaluated bariatric surgery added to medical therapy compared with medical therapy alone in the treatment of adult patients with type 2 diabetes. Studies must have evaluated the incidence of any microvascular complication of the disease for a period of at least 6 months. We performed our search using PubMed, Scopus, EMBASE, Web of Science, and COCHRANE Central database which was performed from inception date until March 2021. PROSPERO (CRD42021243739).

RESULTS

A total of 25 studies (160,072 participants) were included. Pooled analysis revealed bariatric surgery to reduce the incidence of any stage of retinopathy by 71% (odds ratio [OR] .29; 95% confidence interval [CI] .10-.91), nephropathy incidence by 59% (OR .41; 95% CI 17-96), and hemodialysis/end-stage renal disease by 69% (OR .31 95% CI .20-.48). Neuropathy incidence revealed no difference between groups (OR .11; 95% CI .01-1.37). Bariatric surgery increased the odds of albuminuria regression by 15.15 (95% CI 5.96-38.52); higher odds of retinopathy regression were not observed (OR 3.73; 95% CI .29-47.71). There were no statistically significant differences between groups regarding the change in surrogate outcomes.

CONCLUSIONS

Bariatric surgery in adult patients with diabetes reduced the odds of any stage of retinopathy, hemodialysis/end-stage renal disease, and nephropathy composite outcome. However, its effect on many individual outcomes, both surrogates, and clinically significant, remains uncertain.

Comparing Individualized Survival Predictions From Random Survival Forests and Multistate Models in the Presence of Missing Data: A Case Study of Patients With Oropharyngeal Cancer

Background

In recent years, interest in prognostic calculators for predicting patient health outcomes has grown with the popularity of personalized medicine. These calculators, which can inform treatment decisions, employ many different methods, each of which has advantages and disadvantages.

Methods

We present a comparison of a multistate model (MSM) and a random survival forest (RSF) through a case study of prognostic predictions for patients with oropharyngeal squamous cell carcinoma. The MSM is highly structured and takes into account some aspects of the clinical context and knowledge about oropharyngeal cancer, while the RSF can be thought of as a black-box non-parametric approach. Key in this comparison are the high rate of missing values within these data and the different approaches used by the MSM and RSF to handle missingness.

Results

We compare the accuracy (discrimination and calibration) of survival probabilities predicted by both approaches and use simulation studies to better understand how predictive accuracy is influenced by the approach to (1) handling missing data and (2) modeling structural/disease progression information present in the data. We conclude that both approaches have similar predictive accuracy, with a slight advantage going to the MSM.

Conclusions

Although the MSM shows slightly better predictive ability than the RSF, consideration of other differences are key when selecting the best approach for addressing a specific research question. These key differences include the methods' ability to incorporate domain knowledge, and their ability to handle missing data as well as their interpretability, and ease of implementation. Ultimately, selecting the statistical method that has the most potential to aid in clinical decisions requires thoughtful consideration of the specific goals.

Mortality prediction in patients with hyperglycaemic crisis using explainable machine learning: a prospective, multicentre study based on tertiary hospitals

BACKGROUND

Experiencing a hyperglycaemic crisis is associated with a short- and long-term increased risk of mortality. We aimed to develop an explainable machine learning model for predicting 3-year mortality and providing individualized risk factor assessment of patients with hyperglycaemic crisis after admission.

METHODS

Based on five representative machine learning algorithms, we trained prediction models on data from patients with hyperglycaemic crisis admitted to two tertiary hospitals between 2016 and 2020. The models were internally validated by tenfold cross-validation and externally validated using previously unseen data from two other tertiary hospitals. A SHapley Additive exPlanations algorithm was used to interpret the predictions of the best performing model, and the relative importance of the features in the model was compared with the traditional statistical test results.

RESULTS

A total of 337 patients with hyperglycaemic crisis were enrolled in the study, 3-year mortality was 13.6% (46 patients). 257 patients were used to train the models, and 80 patients were used for model validation. The Light Gradient Boosting Machine model performed best across testing cohorts (area under the ROC curve 0.89 [95% CI 0.77-0.97]). Advanced age, higher blood glucose and blood urea nitrogen were the three most important predictors for increased mortality.

CONCLUSION

The developed explainable model can provide estimates of the mortality and visual contribution of the features to the prediction for an individual patient with hyperglycaemic crisis. Advanced age, metabolic disorders, and impaired renal and cardiac function were important factors that predicted non-survival.

TRIAL REGISTRATION NUMBER

ChiCTR1800015981, 2018/05/04.

Machine learning models for prediction of HF and CKD development in early-stage type 2 diabetes patients

Chronic kidney disease (CKD) and heart failure (HF) are the first and most frequent comorbidities associated with mortality risks in early-stage type 2 diabetes mellitus (T2DM). However, efficient screening and risk assessment strategies for identifying T2DM patients at high risk of developing CKD and/or HF (CKD/HF) remains to be established. This study aimed to generate a novel machine learning (ML) model to predict the risk of developing CKD/HF in early-stage T2DM patients. The models were derived from a retrospective cohort of 217,054 T2DM patients without a history of cardiovascular and renal diseases extracted from a Japanese claims database. Among algorithms used for the ML, extreme gradient boosting exhibited the best performance for CKD/HF diagnosis and hospitalization after internal validation and was further validated using another dataset including 16,822 patients. In the external validation, 5-years prediction area under the receiver operating characteristic curves for CKD/HF diagnosis and hospitalization were 0.718 and 0.837, respectively. In Kaplan-Meier curves analysis, patients predicted to be at high risk showed significant increase in CKD/HF diagnosis and hospitalization compared with those at low risk. Thus, the developed model predicted the risk of developing CKD/HF in T2DM patients with reasonable probability in the external validation cohort. Clinical approach identifying T2DM at high risk of developing CKD/HF using ML models may contribute to improved prognosis by promoting early diagnosis and intervention.

Artificial intelligence based prediction models for individuals at risk of multiple diabetic complications: A systematic review of the literature

AIM

The aim of this review is to examine the effectiveness of artificial intelligence in predicting multimorbid diabetes-related complications.

BACKGROUND

In diabetic patients, several complications are often present, which have a significant impact on the quality of life; therefore, it is crucial to predict the level of risk for diabetes and its complications.

EVALUATION

International databases PubMed, CINAHL, MEDLINE and Scopus were searched using the terms artificial intelligence, diabetes mellitus and prediction of complications to identify studies on the effectiveness of artificial intelligence for predicting multimorbid diabetes-related complications. The results were organized by outcomes to allow more efficient comparison.

KEY ISSUES

Based on the inclusion/exclusion criteria, 11 articles were included in the final analysis. The most frequently predicted complications were diabetic neuropathy (n = 7). Authors included from two to a maximum of 14 complications. The most commonly used prediction models were penalized regression, random forest and Naïve Bayes model neural network.

CONCLUSION

The use of artificial intelligence can predict the risks of diabetes complications with greater precision based on available multidimensional datasets and provides an important tool for nurses working in preventive health care.

IMPLICATIONS FOR NURSING MANAGEMENT

Using artificial intelligence contributes to a better quality of care, better autonomy of patients in diabetes management and reduction of complications, costs of medical care and mortality.

Association of Preoperative Glycosylated Hemoglobin Level with 30-Day Outcomes Following Laparoscopic Roux-en-Y Gastric Bypass: an Analysis of the ACS-MBSAQIP Database

PURPOSE

Elevated glycosylated hemoglobin (HbA₁c) levels have been associated with increased morbidity and mortality following several cardiac, colorectal, orthopedic, and vascular surgery operations. The purpose of this study was to determine if there is a HgA₁c cut-point that can be used in patients undergoing laparoscopic Roux-en-Y gastric bypass to decrease the risk of 30-day wound events and additional 30-day morbidity and mortality.

MATERIALS AND METHODS

All patients undergoing first-time, elective Roux-en-Y gastric bypass in 2017 and 2018 with a diagnosis of diabetes mellitus (DM) and a preoperative HbA₁c level were identified within the American College of Surgeons Metabolic and Bariatric Surgery Accreditation Quality Improvement Program (ACS-MBSAQIP) database. The association of preoperative HbA₁c levels with 30-day morbidity and mortality was investigated.

RESULTS

A total of 13,806 patients met inclusion criteria. Two natural HbA₁c inflection points for composite wound events, including superficial, deep, and organ space surgical site infections (SSI) and wound dehiscence, were found. A HbA₁c level of ≤ 6.5% was associated with a decreased odds of experiencing the composite 30-day wound event outcome while a HbA₁c level of > 8.6% was associated with an increased odds of experiencing the composite 30-day wound event outcome. The differences in the incidence of the 30-day composite wound event outcomes were driven primarily by superficial and organ space SSI, including anastomotic leaks.

CONCLUSION

Patients with DM being evaluated for RYGB surgery with a HbA₁c level > 8.6% are at an increased risk for 30-day wound events, including superficial and organ space SSI.

Long-term Remission of Type 2 Diabetes and Patient Survival After Biliopancreatic Diversion with Duodenal Switch

PURPOSE

This study investigates the long-term effects of biliopancreatic diversion with duodenal switch (BPD-DS) on patients with advanced type 2 diabetes mellitus (T2DM) while paying special attention to preoperative diabetes severity.

MATERIALS AND METHODS

A retrospective analysis was conducted using prospective and current data on patients who underwent an open BPD-DS 6-12 years ago. Patients were stratified according to preoperative diabetes severity into 4 groups (group 1: oral antidiabetic drugs only; group 2: insulin < 5 years; group 3: insulin 5-10 years; group 4: insulin > 10 years). The primary endpoint was T2DM remission rate 6-12 years after BPD-DS as a function of preoperative diabetes severity.

RESULTS

Ninety-one patients with advanced T2DM were included. Sixty-two patients were available for follow-up (rate of 77%). Follow-up was performed (mean ± SD) 8.9 ± 1.3 years after surgery. Glycated hemoglobin (HbA_1c) levels were 9.4 ± 2.0% before surgery and decreased to 5.1 ± 0.8% after 1 year and 5.4 ± 1.0% after 6-12 years. Insulin discontinuation rate after surgery as well as the rate of long-term remission decreased steadily from groups 1 to 4, while long-term mortality increased. T2DM remission rates were 93%, 88%, 45%, and 40% in groups 1, 2, 3, and 4, respectively. Late relapse of T2DM occurred in 3 patients (5%).

CONCLUSIONS

BPD-DS causes a rapid and long-lasting normalization of glycemic metabolism in patients with advanced T2DM. T2DM remission rate after 6-12 years varies significantly (from 40% to more than 90%) and is highly dependent on preoperative diabetes severity.

Prediction of complications of type 2 Diabetes: A Machine learning approach

AIM

To construct predictive models of diabetes complications (DCs) by big data machine learning, based on electronic medical records.

METHODS

Six groups of DCs were considered: eye complications, cardiovascular, cerebrovascular, and peripheral vascular disease, nephropathy, diabetic neuropathy. A supervised, tree-based learning approach (XGBoost) was used to predict the onset of each complication within 5 years (task 1). Furthermore, a separate prediction for early (within 2 years) and late (3-5 years) onset of complication (task 2) was performed. A dataset of 147.664 patients seen during 15 years by 23 centers was used. External validation was performed in five additional centers. Models were evaluated by considering accuracy, sensitivity, specificity, and area under the ROC curve (AUC).

RESULTS

For all DCs considered, the predictive models in task 1 showed an accuracy > 70 %, and AUC largely exceeded 0.80, reaching 0.97 for nephropathy. For task 2, all predictive models showed an accuracy > 70 % and an AUC > 0.85. Sensitivity in predicting the early occurrence of the complication ranged between 83.2 % (peripheral vascular disease) and 88.5 % (nephropathy).

CONCLUSIONS

Machine learning approach offers the opportunity to identify patients at greater risk of complications. This can help overcoming clinical inertia and improving the quality of diabetes care.

Convolutional Neural Networks for Classification of T2DM Cognitive Impairment Based on Whole Brain Structural Features

Purpose

Cognitive impairment is generally found in individuals with type 2 diabetes mellitus (T2DM). Although they may not have visible symptoms of cognitive impairment in the early stages of the disorder, they are considered to be at high risk. Therefore, the classification of these patients is important for preventing the progression of cognitive impairment.

Methods

In this study, a convolutional neural network was used to construct a model for classifying 107 T2DM patients with and without cognitive impairment based on T1-weighted structural MRI. The Montreal cognitive assessment score served as an index of the cognitive status of the patients.

Results

The classifier could identify T2DM-related cognitive decline with a classification accuracy of 84.85% and achieved an area under the curve of 92.65%.

Conclusions

The model can help clinicians analyze and predict cognitive impairment in patients and enable early treatment.

Prediction models of diabetes complications: a scoping review

BACKGROUND

Diabetes often places a large burden on people with diabetes (hereafter 'patients') and the society, that is, in part attributable to its complications. However, evidence from models predicting diabetes complications in patients remains unclear. With the collaboration of patient partners, we aimed to describe existing prediction models of physical and mental health complications of diabetes.

METHODS

Building on existing frameworks, we systematically searched for studies in Ovid-Medline and Embase. We included studies describing prognostic prediction models that used data from patients with pre-diabetes or any type of diabetes, published between 2000 and 2020. Independent reviewers screened articles, extracted data and narratively synthesised findings using established reporting standards.

RESULTS

Overall, 78 studies reported 260 risk prediction models of cardiovascular complications (n=42 studies), mortality (n=16), kidney complications (n=14), eye complications (n=10), hypoglycaemia (n=8), nerve complications (n=3), cancer (n=2), fracture (n=2) and dementia (n=1). Prevalent complications deemed important by patients such as amputation and mental health were poorly or not at all represented. Studies primarily analysed data from older people with type 2 diabetes (n=54), with little focus on pre-diabetes (n=0), type 1 diabetes (n=8), younger (n=1) and racialised people (n=10). Per complication, predictors vary substantially between models. Studies with details of calibration and discrimination mostly exhibited good model performance.

CONCLUSION

This rigorous knowledge synthesis provides evidence of gaps in the landscape of diabetes complication prediction models. Future studies should address unmet needs for analyses of complications n> and among patient groups currently under-represented in the literature and should consistently report relevant statistics. SCOPING REVIEW REGISTRATION: https://osf.io/fjubt/.

Independent Predictors of Discontinuation of Diabetic Medication after Sleeve Gastrectomy and Gastric Bypass

INTRODUCTION

Both gastric bypass and sleeve gastrectomy can induce diabetes remission. However, deciding which procedure to perform is challenging since remission rates and morbidity can vary depending on patient factors as well as disease severity.

METHODS

Using a state-wide bariatric-specific data registry we evaluated all patients undergoing sleeve gastrectomy and gastric bypass between 2006-2019 who reported taking either oral diabetic medication alone or who were on insulin prior to surgery and who also had 1-year follow-up (n=11,664). Multivariate regression was used to identify independent predictors for discontinuation of oral diabetic medication or insulin, respectively, and risk-adjusted complication rates were compared between procedure types among each group.

RESULTS

At 1-year after surgery, 85.7% of patients reported discontinuation of oral diabetic medication and 66.6% reported discontinuation of insulin. Gastric bypass was an independent predictor for insulin discontinuation (OR 1.17, CI 1.01-1.35, p=0.0329), however procedure type was not associated with discontinuation of oral medication alone. Risk adjusted complication rates were significantly higher after gastric bypass than sleeve gastrectomy, regardless of whether the patient was taking oral diabetic medications alone or was on insulin (11.2% vs 4.8%, p<0.0001 and 12.0% vs 7.4%, p<0.0001, respectively).

CONCLUSIONS

Patients requiring insulin experience higher rates of insulin discontinuation after gastric bypass but also have significantly higher complication rates when compared to sleeve gastrectomy. However, if patients are on oral diabetic medication alone, rates of medication discontinuation at 1 year are greater than 85% and procedure type is not predictive. Disease severity is an important factor when deciding on the optimal procedure for diabetes.

Artificial Intelligence in Bariatric Surgery: Current Status and Future Perspectives

Background

Machine learning (ML) has been successful in several fields of healthcare, however the use of ML within bariatric surgery seems to be limited. In this systematic review, an overview of ML applications within bariatric surgery is provided.

Methods

The databases PubMed, EMBASE, Cochrane, and Web of Science were searched for articles describing ML in bariatric surgery. The Cochrane risk of bias tool and the PROBAST tool were used to evaluate the methodological quality of included studies.

Results

The majority of applied ML algorithms predicted postoperative complications and weight loss with accuracies up to 98%.

Conclusions

In conclusion, ML algorithms have shown promising capabilities in the prediction of surgical outcomes after bariatric surgery. Nevertheless, the clinical introduction of ML is dependent upon the external validation of ML.

Comparing Machine Learning to Regression Methods for Mortality Prediction Using Veterans Affairs Electronic Health Record Clinical Data

BACKGROUND

It is unclear whether machine learning methods yield more accurate electronic health record (EHR) prediction models compared with traditional regression methods.

OBJECTIVE

The objective of this study was to compare machine learning and traditional regression models for 10-year mortality prediction using EHR data.

DESIGN

This was a cohort study.

SETTING

Veterans Affairs (VA) EHR data.

PARTICIPANTS

Veterans age above 50 with a primary care visit in 2005, divided into separate training and testing cohorts (n= 124,360 each).

MEASUREMENTS AND ANALYTIC METHODS

The primary outcome was 10-year all-cause mortality. We considered 924 potential predictors across a wide range of EHR data elements including demographics (3), vital signs (9), medication classes (399), disease diagnoses (293), laboratory results (71), and health care utilization (149). We compared discrimination (c-statistics), calibration metrics, and diagnostic test characteristics (sensitivity, specificity, and positive and negative predictive values) of machine learning and regression models.

RESULTS

Our cohort mean age (SD) was 68.2 (10.5), 93.9% were male; 39.4% died within 10 years. Models yielded testing cohort c-statistics between 0.827 and 0.837. Utilizing all 924 predictors, the Gradient Boosting model yielded the highest c-statistic [0.837, 95% confidence interval (CI): 0.835-0.839]. The full (unselected) logistic regression model had the highest c-statistic of regression models (0.833, 95% CI: 0.830-0.835) but showed evidence of overfitting. The discrimination of the stepwise selection logistic model (101 predictors) was similar (0.832, 95% CI: 0.830-0.834) with minimal overfitting. All models were well-calibrated and had similar diagnostic test characteristics.

LIMITATION

Our results should be confirmed in non-VA EHRs.

CONCLUSION

The differences in c-statistic between the best machine learning model (924-predictor Gradient Boosting) and 101-predictor stepwise logistic models for 10-year mortality prediction were modest, suggesting stepwise regression methods continue to be a reasonable method for VA EHR mortality prediction model development.

Current Applications of Artificial Intelligence in Bariatric Surgery

The application of artificial intelligence technologies is growing in several fields of healthcare settings. The aim of this article is to review the current applications of artificial intelligence in bariatric surgery. We performed a review of the literature on Scopus, PubMed and Cochrane databases, screening all relevant studies published until September 2021, and finally including 36 articles. The use of machine learning algorithms in bariatric surgery is explored in all steps of the clinical pathway, from presurgical risk-assessment and intraoperative management to complications and outcomes prediction. The models showed remarkable results helping physicians in the decision-making process, thus improving the quality of care, and contributing to precision medicine. Several legal and ethical hurdles should be overcome before these methods can be used in common practice.

Metabolomics in Bariatric and Metabolic Surgery Research and the Potential of Deep Learning in Bridging the Gap

During the past several years, there has been a shift in terminology from bariatric surgery alone to bariatric and metabolic surgery (BMS). More than a change in name, this signifies a paradigm shift that incorporates the metabolic effects of operations performed for weight loss and the amelioration of related medical problems. Metabolomics is a relatively novel concept in the field of bariatrics, with some consistent changes in metabolite concentrations before and after weight loss. However, the abundance of metabolites is not easy to handle. This is where artificial intelligence, and more specifically deep learning, would aid in revealing hidden relationships and would help the clinician in the decision-making process of patient selection in an individualized way.

Machine learning for diabetes clinical decision support: a review

Type 2 diabetes has recently acquired the status of an epidemic silent killer, though it is non-communicable. There are two main reasons behind this perception of the disease. First, a gradual but exponential growth in the disease prevalence has been witnessed irrespective of age groups, geography or gender. Second, the disease dynamics are very complex in terms of multifactorial risks involved, initial asymptomatic period, different short-term and long-term complications posing serious health threat and related co-morbidities. Majority of its risk factors are lifestyle habits like physical inactivity, lack of exercise, high body mass index (BMI), poor diet, smoking except some inevitable ones like family history of diabetes, ethnic predisposition, ageing etc. Nowadays, machine learning (ML) is increasingly being applied for alleviation of diabetes health burden and many research works have been proposed in the literature to offer clinical decision support in different application areas as well. In this paper, we present a review of such efforts for the prevention and management of type 2 diabetes. Firstly, we present the medical gaps in diabetes knowledge base, guidelines and medical practice identified from relevant articles and highlight those that can be addressed by ML. Further, we review the ML research works in three different application areas namely—(1) risk assessment (statistical risk scores and ML-based risk models), (2) diagnosis (using non-invasive and invasive features), (3) prognosis (from normoglycemia/prior morbidity to incident diabetes and prognosis of incident diabetes to related complications). We discuss and summarize the shortcomings or gaps in the existing ML methodologies for diabetes to be addressed in future. This review provides the breadth of ML predictive modeling applications for diabetes while highlighting the medical and technological gaps as well as various aspects involved in ML-based diabetes clinical decision support.

Magnetic Resonance Imaging-Visible Perivascular Spaces in the Basal Ganglia Are Associated With the Diabetic Retinopathy Stage and Cognitive Decline in Patients With Type 2 Diabetes

Purpose: The aim of this study was to evaluate whether perivascular space (PVS) severity and retinal ganglion cell layer (GCL) thickness differed based on the stage of diabetic retinopathy (DR) and the cognitive status in patients with DR.

Methods: A total of 81 patients with DR (51 in the non-proliferative group and 30 in the proliferative group) were included in this retrospective, cross-sectional study. PVS severity was assessed in the basal ganglia (BG) and centrum semiovale using MRI. The total cerebral small vessel disease (SVD) score was determined based on the numbers of lacunes and microbleeds and the severity of white matter hyperintensity. Optical coherence tomography was used to measure foveal and perifoveal GCL thicknesses. Cerebral SVD markers and cognitive function were compared between the groups, and correlations between the BG-PVS severity and the Mini-Mental Status Examination (MMSE) scores and GCL parameters were evaluated.

Results: Patients with proliferative DR had higher BG-PVS severity (P = 0.012), higher total cerebral SVD scores (P = 0.035), reduced GCL thicknesses in the inferior (P = 0.027), superior (P = 0.046), and temporal (P = 0.038) subfields compared to patients with non-proliferative DR. In addition, the BG-PVS severity was negatively correlated with the MMSE score (P = 0.007), and the GCL thickness was negatively correlated with the BG-PVS severity (P-values < 0.05 for inferior, superior, and temporal subfields).

Conclusion: BG-PVS severity and retinal GCL thickness may represent novel imaging biomarkers reflecting the stage of DR and cognitive decline in diabetic patients. Furthermore, these results suggest a possible link between cerebral and retinal neurodegeneration at the clinical level.

Artificial intelligence and diabetes technology: A review

Artificial intelligence (AI) is widely discussed in the popular literature and is portrayed as impacting many aspects of human life, both in and out of the workplace. The potential for revolutionizing healthcare is significant because of the availability of increasingly powerful computational platforms and methods, along with increasingly informative sources of patient data, both in and out of clinical settings. This review aims to provide a realistic assessment of the potential for AI in understanding and managing diabetes, accounting for the state of the art in the methodology and medical devices that collect data, process data, and act accordingly. Acknowledging that many conflicting definitions of AI have been put forth, this article attempts to characterize the main elements of the field as they relate to diabetes, identifying the main perspectives and methods that can (i) affect basic understanding of the disease, (ii) affect understanding of risk factors (genetic, clinical, and behavioral) of diabetes development, (iii) improve diagnosis, (iv) improve understanding of the arc of disease (progression and personal/societal impact), and finally (v) improve treatment.

An explainable machine learning model for predicting in-hospital amputation rate of patients with diabetic foot ulcer

Diabetic foot ulcer (DFU) is one of the most serious and alarming diabetic complications, which often leads to high amputation rates in diabetic patients. Machine learning is a part of the field of artificial intelligence, which can automatically learn models from data and better inform clinical decision‐making. We aimed to develop an accurate and explainable prediction model to estimate the risk of in‐hospital amputation in patients with DFU. A total of 618 hospitalised patients with DFU were included in this study. The patients were divided into non‐amputation, minor amputation or major amputation group. Light Gradient Boosting Machine (LightGBM) and 5‐fold cross‐validation tools were used to construct a multi‐class classification model to predict the three outcomes of interest. In addition, we used the SHapley Additive exPlanations (SHAP) algorithm to interpret the predictions of the model. Our area under the receiver‐operating‐characteristic curve (AUC) demonstrated a 0.90, 0.85 and 0.86 predictive ability for non‐amputation, minor amputation and major amputation outcomes, respectively. Taken together, our data demonstrated that the developed explainable machine learning model provided accurate estimates of the amputation rate in patients with DFU during hospitalisation. Besides, the model could inform individualised analyses of the patients' risk factors.

Identification and Predictors for Cardiovascular Disease Risk Equivalents among Adults With Diabetes Mellitus

OBJECTIVE

We examined diabetes mellitus (DM) as a cardiovascular disease (CVD) risk equivalent based on diabetes severity and other CVD risk factors.

RESEARCH DESIGN AND METHODS

We pooled 4 US cohorts (ARIC, JHS, MESA, FHS-Offspring) and classified subjects by baseline DM/CVD. CVD risks between DM+/CVD- vs. DM-/CVD+ were examined by diabetes severity and in subgroups of other CVD risk factors. We developed an algorithm to identify subjects with CVD risk equivalent diabetes by comparing the relative CVD risk of being DM+/CVD- vs. DM-/CVD+.

RESULTS

The pooled cohort included 27,730 subjects (mean age of 58.5 years, 44.6% male). CVD rates per 1000 person-years were 16.5, 33.4, 43.2 and 71.4 among those with DM-/CVD-, DM+/CVD-, DM-/CVD+ and DM+/CVD+, respectively. Compared with those with DM-/CVD+, CVD risks were similar or higher for those with HbA1c ≥ 7%, diabetes duration ≥10 years, or diabetes medication use while those with less severe diabetes had lower risks. Hazard ratios (95%CI) for DM+/CVD- vs. DM-/CVD+ were 0.96(0.86-1.07), 0.97(0.88-1.07), 0.96(0.82-1.13), 1.18(0.98-1.41), 0.93(0.85-1.02) and 1.00(0.89-1.13) among women, white race, age <55 years, triglycerides ≥2.26 mmol/L, hs-CRP ≥ 2 mg/L and eGFR<60 mL/min/1.73m2, respectively. In DM+/CVD- group, 19.1% had CVD risk equivalent diabetes with a lower risk score but a higher observed CVD risk.

CONCLUSION

Diabetes is a CVD risk equivalent in one-fifth of CVD-free adults living with diabetes. High HbA1c, long diabetes duration, and diabetes medication use were predictors of CVD risk equivalence. Diabetes is a CVD risk equivalent for women, white people, those of younger age, with higher triglycerides or CRP, or reduced kidney function.

A Scoping Review of Artificial Intelligence and Machine Learning in Bariatric and Metabolic Surgery: Current Status and Future Perspectives

Artificial intelligence (AI) is a revolution in data analysis with emerging roles in various specialties and with various applications. The objective of this scoping review was to retrieve current literature on the fields of AI that have been applied to metabolic bariatric surgery (MBS) and to investigate potential applications of AI as a decision-making tool of the bariatric surgeon. Initial search yielded 3260 studies published from January 2000 until March 2021. After screening, 49 unique articles were included in the final analysis. Studies were grouped into categories, and the frequency of appearing algorithms, dataset types, and metrics were documented. The heterogeneity of current studies showed that meticulous validation, strict reporting systems, and reliable benchmarking are mandatory for ensuring the clinical validity of future research.

Machine Learning Approaches to Predict Risks of Diabetic Complications and Poor Glycemic Control in Nonadherent Type 2 Diabetes

Purpose: The objective of this study was to evaluate the efficacy of machine learning algorithms in predicting risks of complications and poor glycemic control in nonadherent type 2 diabetes (T2D). Materials and Methods: This study was a real-world study of the complications and blood glucose prognosis of nonadherent T2D patients. Data of inpatients in Sichuan Provincial People's Hospital from January 2010 to December 2015 were collected. The T2D patients who had neither been monitored for glycosylated hemoglobin A nor had changed their hyperglycemia treatment regimens within the last 12 months were the object of this study. Seven types of machine learning algorithms were used to develop 18 prediction models. The predictive performance was mainly assessed using the area under the curve of the testing set. Results: Of 800 T2D patients, 165 (20.6%) met the inclusion criteria, of which 129 (78.2%) had poor glycemic control (defined as glycosylated hemoglobin A ≥7%). The highest area under the curves of the testing set for diabetic nephropathy, diabetic peripheral neuropathy, diabetic angiopathy, diabetic eye disease, and glycosylated hemoglobin A were 0.902 ± 0.040, 0.859 ± 0.050, 0.889 ± 0.059, 0.832 ± 0.086, and 0.825 ± 0.092, respectively. Conclusion: Both univariate analysis and machine learning methods reached the same conclusion. The duration of T2D and the duration of unadjusted hypoglycemic treatment were the key risk factors of diabetic complications, and the number of hypoglycemic drugs was the key risk factor of glycemic control of nonadherent T2D. This was the first study to use machine learning algorithms to explore the potential adverse outcomes of nonadherent T2D. The performances of the final prediction models we developed were acceptable; our prediction performances outperformed most other previous studies in most evaluation measures. Those models have potential clinical applicability in improving T2D care.

Cardiovascular Risk Reduction Following Metabolic and Bariatric Surgery

Cardiovascular disease (CVD) remains a leading cause of morbidity and mortality in developed countries, with worsening pandemics of type 2 diabetes mellitus and obesity as major cardiovascular (CV) risk factors. Clinical trials of nonsurgical obesity treatments have not shown benefits in CVD, although recent diabetes trials have demonstrated major CV benefits. In many retrospective and prospective cohort studies, however, metabolic (bariatric) surgery is associated with substantial and reproducible CVD benefits. Despite a lack of prospective, randomized clinical trials, data suggest metabolic surgery may be the most effective modality for CVD risk reduction, likely through weight loss and weight loss-independent mechanisms.

ASMBS position statement on the rationale for performance of upper gastrointestinal endoscopy before and after metabolic and bariatric surgery

The following position statement is issued by the American Society for Metabolic and Bariatric Surgery in response to inquiries made to the Society by patients, physicians, society members, hospitals, health insurance payors, the media, and others regarding the need and possible strategies for screening endoscopic examination before metabolic and bariatric surgery (MBS), as well as the rationale, indications, and strategies for postoperative surveillance for mucosal abnormalities, including gastroesophageal reflux disease and associated esophageal mucosal injuries (erosive esophagitis and Barrett's esophagus) that may develop in the long term after MBS, specifically for patients undergoing sleeve gastrectomy or Roux-en-Y gastric bypass. The general principles described here may also apply to procedures such as biliopancreatic diversion (BPD) and BPD with duodenal switch (DS); however, the paucity of procedure-specific literature for BPD and DS limits the value of this statement to those procedures. In addition, children with obesity undergoing MBS may have unique considerations and are not specifically addressed in this position statement. This recommendation is based on current clinical knowledge, expert opinion, and published peer-reviewed scientific evidence available at this time. The statement is not intended to be and should not be construed as stating or establishing a local, regional, or national standard of care. The statement will be revised in the future as additional evidence becomes available.

Clinical notes as prognostic markers of mortality associated with diabetes mellitus following critical care: A retrospective cohort analysis using machine learning and unstructured big data

BACKGROUND

Clinical notes are ubiquitous resources offering potential value in optimizing critical care via data mining technologies.

OBJECTIVE

To determine the predictive value of clinical notes as prognostic markers of 1-year all-cause mortality among people with diabetes following critical care.

MATERIALS AND METHODS

Mortality of diabetes patients were predicted using three cohorts of clinical text in a critical care database, written by physicians (n = 45253), nurses (159027), and both (n = 204280). Natural language processing was used to pre-process text documents and LASSO-regularized logistic regression models were trained and tested. Confusion matrix metrics of each model were calculated and AUROC estimates between models were compared. All predictive words and corresponding coefficients were extracted. Outcome probability associated with each text document was estimated.

RESULTS

Models built on clinical text of physicians, nurses, and the combined cohort predicted mortality with AUROC of 0.996, 0.893, and 0.922, respectively. Predictive performance of the models significantly differed from one another whereas inter-rater reliability ranged from substantial to almost perfect across them. Number of predictive words with non-zero coefficients were 3994, 8159, and 10579, respectively, in the models of physicians, nurses, and the combined cohort. Physicians' and nursing notes, both individually and when combined, strongly predicted 1-year all-cause mortality among people with diabetes following critical care.

CONCLUSION

Clinical notes of physicians and nurses are strong and novel prognostic markers of diabetes-associated mortality in critical care, offering potentially generalizable and scalable applications. Clinical text-derived personalized risk estimates of prognostic outcomes such as mortality could be used to optimize patient care.

Predicting adverse outcomes due to diabetes complications with machine learning using administrative health data

Across jurisdictions, government and health insurance providers hold a large amount of data from patient interactions with the healthcare system. We aimed to develop a machine learning-based model for predicting adverse outcomes due to diabetes complications using administrative health data from the single-payer health system in Ontario, Canada. A Gradient Boosting Decision Tree model was trained on data from 1,029,366 patients, validated on 272,864 patients, and tested on 265,406 patients. Discrimination was assessed using the AUC statistic and calibration was assessed visually using calibration plots overall and across population subgroups. Our model predicting three-year risk of adverse outcomes due to diabetes complications (hyper/hypoglycemia, tissue infection, retinopathy, cardiovascular events, amputation) included 700 features from multiple diverse data sources and had strong discrimination (average test AUC = 77.7, range 77.7-77.9). Through the design and validation of a high-performance model to predict diabetes complications adverse outcomes at the population level, we demonstrate the potential of machine learning and administrative health data to inform health planning and healthcare resource allocation for diabetes management.

Metabolic surgery: A clinical update

Metabolic and bariatric surgery has grown beyond 'experimental' weight-loss surgery. As techniques have advanced over the last few decades, so has the growing body of research and evidence, proving that both weight-loss and metabolic health improvement are induced. Metabolic surgery has become the more appropriate term for weight-loss surgery because of the altered gastrointestinal anatomy and subsequent beneficial metabolic effects. Although the tool of metabolic surgery has been well refined, a large portion of the global population does not have adequate access to it. This clinical update aims to (a) inform healthcare providers from all disciplines about the myriad of benefits of metabolic surgery and (b) equip them with the necessary knowledge to bridge the gap between patients in need of metabolic treatment and the therapies in metabolic surgery available to them.

Obesity as a multisystem disease: Trends in obesity rates and obesity-related complications

Obesity is a chronic multisystem disease associated with increased morbidity and mortality. The increasing prevalence of obesity makes it a major healthcare challenge across both developed and developing countries. Traditional measures such as body mass index do not always identify individuals at increased risk of comorbidities, yet continue to be used in deciding who qualifies for weight loss treatment. A better understanding of how obesity is associated with comorbidities, in particular non-metabolic conditions, is needed to identify individuals at risk in order to prioritize treatment. For metabolic disorders such as type 2 diabetes (T2D), weight loss can prevent T2D in individuals with prediabetes. It can improve and reverse T2D if weight loss is achieved early in the course of the disease. However, access to effective weight loss treatments is a significant barrier to improved health for people with obesity. In the present paper, we review the rising prevalence of obesity and why it should be classed as a multisystem disease. We will discuss potential mechanisms underlying its association with various comorbidities and how these respond to treatment, with a particular focus on cardiometabolic disease, malignancy and mental health.

Use of Machine Learning Approaches in Clinical Epidemiological Research of Diabetes

PURPOSE OF REVIEW

Machine learning approaches-which seek to predict outcomes or classify patient features by recognizing patterns in large datasets-are increasingly applied to clinical epidemiology research on diabetes. Given its novelty and emergence in fields outside of biomedical research, machine learning terminology, techniques, and research findings may be unfamiliar to diabetes researchers. Our aim was to present the use of machine learning approaches in an approachable way, drawing from clinical epidemiological research in diabetes published from 1 Jan 2017 to 1 June 2020.

RECENT FINDINGS

Machine learning approaches using tree-based learners-which produce decision trees to help guide clinical interventions-frequently have higher sensitivity and specificity than traditional regression models for risk prediction. Machine learning approaches using neural networking and "deep learning" can be applied to medical image data, particularly for the identification and staging of diabetic retinopathy and skin ulcers. Among the machine learning approaches reviewed, researchers identified new strategies to develop standard datasets for rigorous comparisons across older and newer approaches, methods to illustrate how a machine learner was treating underlying data, and approaches to improve the transparency of the machine learning process. Machine learning approaches have the potential to improve risk stratification and outcome prediction for clinical epidemiology applications. Achieving this potential would be facilitated by use of universal open-source datasets for fair comparisons. More work remains in the application of strategies to communicate how the machine learners are generating their predictions.

Association is not prediction: A landscape of confused reporting in diabetes - A systematic review

AIMS

Appropriate analysis of big data is fundamental to precision medicine. While statistical analyses often uncover numerous associations, associations themselves do not convey predictive value. Confusion between association and prediction harms clinicians, scientists, and ultimately, the patients. We analyzed published papers in the field of diabetes that refer to "prediction" in their titles. We assessed whether these articles report metrics relevant to prediction.

METHODS

A systematic search was undertaken using NCBI PubMed. Articles with the terms "diabetes" and "prediction" were selected. All abstracts of original research articles, within the field of diabetes epidemiology, were searched for metrics pertaining to predictive statistics. Simulated data was generated to visually convey the differences between association and prediction.

RESULTS

The search-term yielded 2,182 results. After discarding non-relevant articles, 1,910 abstracts were evaluated. Of these, 39% (n = 745) reported metrics of predictive statistics, while 61% (n = 1,165) did not. The top reported metrics of prediction were ROC AUC, sensitivity and specificity. Using the simulated data, we demonstrated that biomarkers with large effect sizes and low P values can still offer poor discriminative utility.

CONCLUSIONS

We demonstrate a landscape of confused reporting within the field of diabetes epidemiology where the term "prediction" is often incorrectly used to refer to association statistics. We propose guidelines for future reporting, and two major routes forward in terms of main analytic procedures and research goals: the explanatory route, which contributes to precision medicine, and the prediction route which contributes to personalized medicine.

How Much Weight Loss is Required for Cardiovascular Benefits? Insights From a Metabolic Surgery Matched-cohort Study

OBJECTIVE

The aim of this study was to determine the minimum amount of weight loss required to see a reduction in major adverse cardiovascular events (MACE).

BACKGROUND

Although obesity is an established risk factor for morbidity and mortality, the minimum amount of weight loss to have a meaningful impact on cardiovascular health and survival is unknown.

METHODS

Patients with obesity (body mass index ≥30 kg/m) and type 2 diabetes who underwent metabolic surgery in an academic center (1998-2017) were propensity-matched 1:5 to nonsurgical patients who received usual care. The adjusted linear and nonlinear effects of weight loss (achieved in the first 18 months after the index date) were studied to identify cut-offs for the minimum weight loss to achieve decreased risk of all-cause mortality and MACE (composite of all-cause mortality, coronary artery events, cerebrovascular events, heart failure, nephropathy, and atrial fibrillation).

RESULTS

A total of 7201 patients (1223 surgical and 5978 nonsurgical) with a median follow-up time of 4.9 years (interquartile range, 3.5-7) were included. The positive effect of metabolic surgery was still present after adjusting for weight loss amounts, suggesting that there are weight loss-independent factors contributing to a reduction in risk of MACE and all-cause mortality in the surgical cohort. After considering the weighted estimates from a diverse set of models, the risk of MACE decreases after approximately 10% of weight is lost in the surgical group and approximately 20% in the nonsurgical group. For all-cause mortality, the threshold for benefit appeared to be approximately 5% weight loss after metabolic surgery and 20% in the nonsurgical group.

CONCLUSIONS

This large matched-cohort study identified the minimum weight loss thresholds for reduction in risk of MACE and all-cause mortality in patients with obesity and diabetes. Furthermore, in our analysis, the effect of surgery was still present after accounting for weight loss, which may suggest the presence of weight-independent beneficial effects of metabolic surgery on MACE and survival.

A Review of the Current Evidence: Impact of Metabolic Surgery on Diabetes Outcomes and Obesity-Associated Macrovascular Complications

PURPOSE OF REVIEW

Type 2 diabetes (T2D) and obesity are comorbidities that generally progress with time even when non-invasive therapies are prescribed. Indeed, weight loss that is achieved with behavioral modification alone is generally inconsistent and often short-lived. In contrast, although patients do experience weight regain with metabolic surgery, they still benefit from a significant net decrease in weight. As a result, T2D remission can be achieved in up to 60% of patients within 2 years after surgery. However, it is unknown if the positive effects of metabolic surgery extend to macrovascular disease risk reduction.

RECENT FINDINGS

As noted in four randomized controlled trials (RCTs), Roux-en-Y gastric bypass (RYGB) facilitates partial remission of T2D in about 30% of volunteers 5 years after surgery. Of the four RCTs, only one investigated the effects of sleeve gastrectomy (SG) at 5 years; that study found that the rate of partial relapse was slightly lower with SG (23%). However, observational studies indicate that the gap between RYGB and SG may be larger than that observed in RCTs. In contrast, the rate of full remission is noted infrequently 5 years after SG or RYGB. Metabolic surgery also mitigates macrovascular disease risk as indicated by multiple observational studies. The effects of metabolic surgery on cardiometabolic parameters are clinically meaningful. The weight loss that is facilitated by metabolic surgery reduces the metabolic and inflammatory stress caused by T2D and obesity. In turn, metabolic surgery likely mitigates macrovascular disease risk. Additional evidence from RCTs is needed to substantiate the effects of metabolic surgery on macrovascular disease risk.