Longitudinal artificial intelligence-based deep learning models for diagnosis and prediction of the future occurrence of polyneuropathy in diabetes and prediabetes.

OBJECTIVE: The objective of this study was to develop artificial intelligence-based deep learning models and assess their potential utility and accuracy in diagnosing and predicting the future occurrence of diabetic distal sensorimotor polyneuropathy (DSPN) among individuals with type 2 diabetes mellitus (T2DM) and prediabetes. METHODS: In 394 patients (T2DM=300, Prediabetes=94), we developed a DSPN diagnostic and predictive model using Random Forest (RF)-based variable selection techniques, specifically incorporating the combined capabilities of the Clinical Toronto Neuropathy Score (TCNS) and nerve conduction study (NCS) to identify relevant variables. These important variables were then integrated into a deep learning framework comprising Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks. To evaluate temporal predictive efficacy, patients were assessed at enrollment and one-year follow-up. RESULTS: RF-based variable selection identified key factors for diagnosing DSPN. Numbness scores, sensory test results (vibration), reflexes (knee, ankle), sural nerve attributes (sensory nerve action potential [SNAP] amplitude, nerve conduction velocity [NCV], latency), and peroneal/tibial motor NCV were candidate variables at baseline and over one year. Tibial compound motor action potential amplitudes were used for initial diagnosis, and ulnar SNAP amplitude for subsequent diagnoses. CNNs and LSTMs achieved impressive AUC values of 0.98 for DSPN diagnosis prediction, and 0.93 and 0.89 respectively for predicting the future occurrence of DSPN. RF techniques combined with two deep learning algorithms exhibited outstanding performance in diagnosing and predicting the future occurrence of DSPN. These algorithms have the potential to serve as surrogate measures, aiding clinicians in accurate diagnosis and future prediction of DSPN.

Baroreflex Sensitivity as a Surrogate Biomarker for Concurrently Assessing the Severity of Arterial Stiffness and Cardiovascular Autonomic Neuropathy in Individuals with Type 2 Diabetes.

This study aimed to investigate whether baroreflex sensitivity (BRS) could serve as a reliable metric for assessing cardiovascular autonomic neuropathy (CAN) and concurrently act as a surrogate biomarker for evaluating the severity of arterial stiffness and CAN in individuals diagnosed with type 2 diabetes mellitus (T2DM). Participants underwent brachial-ankle pulse wave velocity (baPWV) as well as autonomic function evaluations encompassing the Sudoscan-based modified composite autonomic scoring scale (CASS), baroreflex sensitivity, and heart rate variability in time domains and frequency domains. Linear regression analysis was performed to evaluate the influence of independent variables on baPWV and modified CASS. Participants with higher baPWV values were older, with longer diabetes duration, lower body weight, body mass index, waist circumference, elevated systolic and diastolic blood pressure, and mean arterial blood pressure. They also exhibited a higher prevalence of retinopathy as the underlying disease and reduced estimated glomerular filtration rate. Multiple linear regression analysis revealed that age and BRS were significantly associated with baPWV while diabetes duration, UACR, and BRS were significantly associated with modified CASS. Our study confirms the significant association of BRS with baPWV and modified CASS in T2DM, highlighting its pivotal role in linking microvascular and macrovascular complications. This supports BRS as a surrogate marker for assessing both the severity of arterial stiffness and cardiovascular autonomic neuropathy in T2DM, enabling the early identification of complications.

Predictive value of heart rate variability and electrochemical skin conductance measurements for cardiovascular autonomic neuropathy persistence in type 2 diabetes and prediabetes: A 3-year follow-up study.

OBJECTIVE: The study aimed to explore risk stratification approaches for cardiovascular autonomic neuropathy (CAN) in individuals with prediabetes and type 2 diabetes (T2DM) over a three-year follow-up period. METHODS: Participants underwent evaluations of autonomic function encompassing cardiovascular autonomic reflex tests (CARTs), baroreflex sensitivity (BRS), heart rate variability (HRV) in time domains (standard deviation of all normal RR intervals (SDNN)) and frequency domains (high frequency/low frequency ratio), and electrochemical skin conductance (ESC). The diagnosis of CAN relied on abnormal CART results. Subjects were categorized into 4 groups, based on their assessment of cardiac autonomic function at 3-year follow-up, relative to the presence or absence of CAN at baseline assessment: Persistent absence of CAN; Resolution of CAN; Progression to CAN; and Persistent CAN. RESULTS: Participants with T2DM/prediabetes (n = 91/7) were categorized as: Persistent absence of CAN (n = 25), Resolution of CAN (n = 10), Progression to CAN (n = 18), and Persistent CAN (n = 45) groups. The Persistent absence of CAN group showed significant associations with SDNN. The Resolution of CAN group exhibited notable associations with mean HbA1C (follow-up), while the Progression to CAN group displayed a significant link with baseline estimated glomerular filtration rate. The Persistent CAN group demonstrated significant associations with SDNN and Sudoscan CAN risk score. Screening recommendations involve biennial to annual assessments based on risk levels, aiding in CAN detection and subsequent comprehensive and time-intensive autonomic function tests for confirmation. The study's findings offer improved risk categorization approaches for detecting CAN, which has relevance for shaping public health strategies.

Prognostic value of longitudinal HbA1c variability in predicting the development of diabetic sensorimotor polyneuropathy among patients with type 2 diabetes mellitus: A prospective cohort observational study.

AIMS/INTRODUCTION: This prospective cohort study aims to identify the optimal measure of glycated hemoglobin (HbA1c) variability and to explore its relationship with the development of new diabetic sensorimotor polyneuropathy (DSPN) in individuals with type 2 diabetes mellitus, building upon previous cross-sectional studies that highlighted a significant association between HbA1c visit-to-visit variability and DSPN. MATERIALS AND METHODS: In a prospective study, 321 participants diagnosed with type 2 diabetes mellitus underwent comprehensive clinical assessments, neurophysiologic studies, and laboratory evaluations at enrollment and follow-up. Various indices, including HbA1c standard deviation (HbA1c SD), coefficient of variation (HbA1c CV), HbA1c change score (HbA1c HVS), and average real variability (HbA1c ARV), were employed to calculate the visit-to-visit variability HbA1c based on 3 month intervals. The investigation focused on examining the associations between these indices and the development of new DSPN. RESULTS: The average follow-up duration was 16.9 ± 6.9 months. The Cox proportional hazards model identified age (P = 0.001), diabetes duration (P = 0.024), and HbA1C ARV (P = 0.031) as the sole factors associated with the development of new DSPN. Furthermore, the cumulative risk of developing DSPN over 1 year demonstrated a significant association with HbA1C ARV (P = 0.03, log-rank test). CONCLUSIONS: Apart from age and diabetes duration, HbA1c variability emerged as a robust predictor for the occurrence of new DSPN. Among the various measures of HbA1c variability evaluated, HbA1c ARV demonstrated the highest potential as a reliable indicator for anticipating the onset of new DSPN.

Impacts of Chemerin Levels and Antioxidant Capacity on the Severity of Cardiovascular Autonomic Neuropathy in Patients with Type 2 Diabetes and Prediabetes.

Existing evidence supports an association between chemerin levels and cardiovascular risk, while reduced thiol levels are linked to diabetes mellitus. It is hypothesized that chemerin may contribute to autonomic dysfunction and cardiovascular risk in type 2 diabetes mellitus (T2DM), potentially mediated by the antioxidant capacity of patients with well-controlled T2DM and prediabetes. Comprehensive cardiovascular autonomic testing and biomarker assessments were conducted for all participants. The severity of cardiovascular autonomic neuropathy (CAN) was evaluated using the composite autonomic scoring scale (CASS). A mediation model was employed to explore the potential relationships among chemerin levels, antioxidant capacity (indicated by thiol levels), and CAN severity (indicated by CASS values). A total of 184 participants were enrolled in this study, comprising 143 individuals with T2DM and 40 individuals with prediabetes. The findings reveal a significant negative association between thiols levels (r = -0.38, p < 0.0001) and the CASS values, while a positive association is observed between chemerin levels (r = 0.47, p < 0.0001) and the CASS values. Linear regression analysis identified chemerin and thiols as independent variables significantly associated with CASS values. Subsequent mediation analysis elucidated that thiols levels act as mediators in the relationship between elevated chemerin levels and an increased CASS value. This study shows that poor cardiovascular function, higher chemerin levels, and reduced antioxidant capacity coexist in individuals with T2DM and prediabetes. Mediation analysis suggests a pathophysiological link between high chemerin levels and low antioxidant capacity, adversely impacting CAN severity.

Sudoscan as substitute for quantitative sudomotor axon reflex test in composite autonomic scoring scale and its correlation with composite autonomic symptom scale 31 in type 2 diabetes.

OBJECTIVE: This study aims to evaluate the feasibility of substituting electrochemical skin conductance measurement using SUDOSCAN for sudomotor function testing in the Composite Autonomic Scoring Scale (CASS) and to correlate the results with the Composite Autonomic Symptom Scale 31 (COMPASS 31) among patients with type 2 diabetes mellitus (T2DM). METHODS: Fifty patients with T2DM underwent cardiovascular autonomic function testing and the SUDOSCAN test and completed the COMPASS 31 questionnaire. We developed a SUDOSCAN-based sudomotor subscore as a substitute for the original sudomotor subscore (based on the quantitative sudomotor axon reflex test [QSART]). The modified CASS score (SUDOSCAN-based sudomotor subscore combined with the adrenergic and cardiovagal subscores) and the original CASS score without suomotor assessment (sum of the adrenergic and cardiovagal subscores) were obtained according to the results of the cardiovascular autonomic function and SUDOSCAN tests. RESULTS: The total COMPASS 31 score was significantly correlated with the modified CASS score (p = 0.019 and 0.037 for the raw and weighted scores, respectively) but not with the CASS score without sudomotor assessment. After adding the SUDOSCAN-based sudomotor subscore, the number of patients identified as having diabetic autonomic neuropathy (DAN) increased from 24 (48 %, based on the CASS score without sudomotor assessment) to 35 (70 %, based on the modified CASS score). The modified CASS score enhances the accuracy of assessing autonomic function and improves the diagnosis of diabetic autonomic neuropathy (DAN) among patients with T2DM. In medical settings where QSART is not accessible, SUDOSCAN testing offers a practical and efficient alternative.

Quantitative thermal testing as a screening and follow-up tool for diabetic sensorimotor polyneuropathy in patients with type 2 diabetes and prediabetes.

Introduction: The diagnosis and assessment of neuropathy severity of diabetic sensorimotor polyneuropathy (DSPN) are mainly based on clinical neuropathy scores and electrophysiologic studies. This study aimed to determine whether quantitative thermal testing (QTT) can be used as a screening and follow-up tool for DSPN of prediabetes and type 2 diabetes at baseline and at 1-year follow-up. Methods: All patients were assessed using the Toronto Clinical Neuropathy Score (TCNS) and underwent electrophysiological testing, including a nerve conduction study (NCS) and QTT, at baseline and at a 1-year follow-up. The TCNS and the composite scores of nerve conduction were used to assess the severity of DSPN. The DSPN status at the 1-year follow-up was classified as remaining no DSPN, remaining DSPN, regression to no DSPN, or progression to DSPN. Results: Diabetic sensorimotor polyneuropathy was initially diagnosed in 89 patients with prediabetes and type 2 diabetes (22%). The regressed to no DSPN in 29 patients and progressed to DSPN in 20 patients at the 1-year follow-up. TCNS was significantly correlated with composite scores of nerve conduction, hand cold detection threshold (CDT), hand warm detection threshold (WDT), foot CDT, and foot WDT. Stepwise logistic regression demonstrated that the foot CDT (p < 0.0001) was independently associated with the presence of DSPN. The TCNS, composite scores of the nerve conduction, hand WDT, hand CDT, foot WDT, and foot CDT were all statistically significant among the four different DSPN status groups at two different time periods (baseline and the 1-year follow-up). Conclusion: The foot CDT can be used as an initial screening tool for DSPN alternatively. The characteristics of nerve damage after 1 year of DSPN can be progressive or reversible, and the neurological functions of large and small fibers have a parallel trend, which can be objectively measured by NCS and QTT.

The Effects of Indoxyl Sulfate and Oxidative Stress on the Severity of Peripheral Nerve Dysfunction in Patients with Chronic Kidney Diseases.

Pieces of evidence support the view that the accumulation of uremic toxins enhances oxidative stress and downstream regulation of signaling pathways, contributing to both endothelial microangiography and cell dysfunction. This study is to address the impact of protein-binding uremic toxins on the severity of peripheral nerve function in patients with chronic kidney disease (CKD). Fifty-four patients with CKD were included in the Toronto Clinical Neuropathy Score (TCNS), nerve conduction study (NCS), and laboratory studies including protein-binding uremic toxin (indoxyl sulfate [IS] and p-cresyl sulfate [PCS]), oxidative stress (Thiol and thiobarbituric acid reacting substances [TBARS]), and endothelial dysfunction (serum intercellular adhesion molecule 1 [sICAM-1] and serum vascular adhesion molecule 1 [sVCAM-1]) at enrollment. We used composite amplitude scores (CAS) to analyze the severity of nerve conductions on peripheral nerve function. TCNS and CAS were higher in the diabetic CKD group (p = 0.02 and 0.01, respectively). The NCS revealed the compound muscle action potential of ulnar and peroneal nerves and the sensory nerve action potential of ulnar and sural nerves (p = 0.004, p = 0.004, p = 0.004, and p = 0.001, respectively), which was found to be significantly low in the diabetic group. CAS was significantly correlated with age (r = 0.27, p = 0.04), urine albumin-creatinine ratio (UACR) (r = 0.29, p = 0.046), free-form IS (r = 0.39, p = 0.009), sICAM-1 (r = 0.31, p = 0.02), sVCAM-1 (r = 0.44, p < 0.0001), TBARS (r = 0.35, p = 0.002), and thiols (r = −0.28, p = 0.045). Linear regression revealed that only TBARS and free-form IS were strongly associated with CAS. The mediation analysis shows that the sVCAM-1 level serves as the mediator between higher IS and higher CAS. IS and oxidative stress contribute to the severity of peripheral nerve dysfunction in patients with CKD, and chronic glycemic impairment can worsen the conditions.