A Machine Learning-Based Severity Prediction Tool for the Michigan Neuropathy Screening Instrument

Diabetic sensorimotor polyneuropathy (DSPN) is a serious long-term complication of diabetes, which may lead to foot ulceration and amputation. Among the screening tools for DSPN, the Michigan neuropathy screening instrument (MNSI) is frequently deployed, but it lacks a straightforward rating of severity. A DSPN severity grading system has been built and simulated for the MNSI, utilizing longitudinal data captured over 19 years from the Epidemiology of Diabetes Interventions and Complications (EDIC) trial. Machine learning algorithms were used to establish the MNSI factors and patient outcomes to characterise the features with the best ability to detect DSPN severity. A nomogram based on multivariable logistic regression was designed, developed and validated. The extra tree model was applied to identify the top seven ranked MNSI features that identified DSPN, namely vibration perception (R), 10-gm filament, previous diabetic neuropathy, vibration perception (L), presence of callus, deformities and fissure. The nomogram's area under the curve (AUC) was 0.9421 and 0.946 for the internal and external datasets, respectively. The probability of DSPN was predicted from the nomogram and a DSPN severity grading system for MNSI was created using the probability score. An independent dataset was used to validate the model's performance. The patients were divided into four different severity levels, i.e., absent, mild, moderate, and severe, with cut-off values of 10.50, 12.70 and 15.00 for a DSPN probability of less than 50, 75 and 100%, respectively. We provide an easy-to-use, straightforward and reproducible approach to determine prognosis in patients with DSPN.

The severity of corneal nerve loss differentiates motor subtypes in patients with Parkinson's disease

Background

Parkinson's disease (PD) is a heterogeneous movement disorder with patients manifesting with either tremor-dominant (TD) or postural instability and gait disturbance (PIGD) motor subtypes. Small nerve fiber damage occurs in patients with PD and may predict motor progression, but it is not known whether it differs between patients with different motor subtypes.

Objective

The aim of this study was to explore whether there was an association between the extent of corneal nerve loss and different motor subtypes.

Methods

Patients with PD classified as TD, PIGD, or mixed subtype underwent detailed clinical and neurological evaluation and corneal confocal microscopy (CCM). Corneal nerve fiber density (CNFD), corneal nerve branch density (CNBD), and corneal nerve fiber length (CNFL) were compared between groups, and the association between corneal nerve fiber loss and motor subtypes was investigated.

Results

Of the 73 patients studied, 29 (40%) had TD, 34 (46%) had PIGD, and 10 (14%) had a mixed subtype. CNFD (no./mm², 24.09 ± 4.58 versus 28.66 ± 4.27; p < 0.001), CNBD (no./mm², 28.22 ± 11.11 versus 37.37 ± 12.76; p = 0.015), and CNFL (mm/mm², 13.11 ± 2.79 versus 16.17 ± 2.37; p < 0.001) were significantly lower in the PIGD group compared with the TD group. Multivariate logistic regression showed that higher CNFD (OR = 1.265, p = 0.019) and CNFL (OR = 1.7060, p = 0.003) were significantly associated with the TD motor subtype. The receiver operating characteristic (ROC) analysis demonstrated that combined corneal nerve metrics showed excellent discrimination between TD and PIGD, with an area under the curve (AUC) of 0.832.

Conclusion

Greater corneal nerve loss occurs in patients with PIGD compared with TD, and patients with a higher CNFD or CNFL were more likely to have the TD subtype. CCM may have clinical utility in differentiating different motor subtypes in PD.

Corneal nerve and nerve conduction abnormalities in children with type 1 diabetes

OBJECTIVE

In vivo corneal confocal microscopy (CCM) is a novel, rapid, and non-invasive technique that identifies early small fiber damage and can predict the progression and development of clinical neuropathy in adults with type 1 diabetes. However, its usefulness in children is not well established. This study compared corneal confocal microscopy with neuropathic symptoms, signs, and objective measures of neuropathy for the diagnosis of diabetic neuropathy in children with type 1 diabetes.

RESEARCH DESIGN AND METHODS

A total of 83 children with type 1 diabetes and 83 healthy participants of similar age underwent assessment of neuropathy symptoms, signs, nerve conduction studies, quantitative sensory and autonomic function testing, and in vivo CCM.

RESULTS

Only of 3/83 (4%) children with type 1 diabetes had subclinical neuropathy. However, corneal nerve fiber density (p = 0.001), branch density (p = 0.006), fiber length (p = 0.002), tibial motor nerve amplitude and conduction velocity, and sural sensory nerve amplitude and conduction velocity (all p < 0.004) were lower in participants with type 1 diabetes than in the controls. Vibration, cooling, and warm perception thresholds and deep breathing heart rate variability were not found to be different (all p > 0.05) between children with type 1 diabetes and healthy controls. Multivariate regression analysis identified a possible association between body mass index and decreased corneal nerves.

CONCLUSIONS

Decreased corneal nerves and abnormal nerve conduction were found in children with type 1 diabetes. CCM may allow rapid objective detection of subclinical diabetic neuropathy in children and adolescents with type 1 diabetes.

Continuous glucose monitoring reveals a novel association between duration and severity of hypoglycemia, and small nerve fiber injury in patients with diabetes

Objective

Continuous glucose monitoring (CGM) has revealed that glycemic variability and low time in range are associated with albuminuria and retinopathy. We have investigated the relationship between glucose metrics derived from CGM and a highly sensitive measure of neuropathy using corneal confocal microscopy in participants with type 1 and type 2 diabetes.

Methods

A total of 40 participants with diabetes and 28 healthy controls underwent quantification of corneal nerve fiber density (CNFD), corneal nerve branch density (CNBD), corneal nerve fiber length (CNFL) and inferior whorl length (IWL) and those with diabetes underwent CGM for four consecutive days.

Results

CNBD was significantly lower in patients with high glycemic variability (GV) compared to low GV (median (range) (25.0 (19.0-37.5) vs 38.6 (29.2-46.9); P = 0.007); in patients who spent >4% compared to <4% time in level 1 hypoglycemia (54-69 mg/dL) (25.0 (22.9-37.5) vs 37.5 (29.2-46.9); P = 0.045) and in patients who spent >1% compared to <1% time in level 2 hypoglycemia (<54 mg/dL) (25.0 (19.8-41.7) vs 35.4 (28.1-44.8); P = 0.04). Duration in level 1 hypoglycemia correlated with CNBD (r = -0.342, P = 0.031). Duration in level 1 (181-250 mg/dL) and level 2 (>250 mg/dL) hyperglycemia did not correlate with CNFD (P > 0.05), CNBD (P > 0.05), CNFL (P > 0.05) or IWL (P > 0.05).

Conclusions

Greater GV and duration in hypoglycemia, rather than hyperglycemia, are associated with nerve fiber loss in diabetes.

Metabolic and proteomic signatures of type 2 diabetes subtypes in an Arab population

Type 2 diabetes (T2D) has a heterogeneous etiology influencing its progression, treatment, and complications. A data driven cluster analysis in European individuals with T2D previously identified four subtypes: severe insulin deficient (SIDD), severe insulin resistant (SIRD), mild obesity-related (MOD), and mild age-related (MARD) diabetes. Here, the clustering approach was applied to individuals with T2D from the Qatar Biobank and validated in an independent set. Cluster-specific signatures of circulating metabolites and proteins were established, revealing subtype-specific molecular mechanisms, including activation of the complement system with features of autoimmune diabetes and reduced 1,5-anhydroglucitol in SIDD, impaired insulin signaling in SIRD, and elevated leptin and fatty acid binding protein levels in MOD. The MARD cluster was the healthiest with metabolomic and proteomic profiles most similar to the controls. We have translated the T2D subtypes to an Arab population and identified distinct molecular signatures to further our understanding of the etiology of these subtypes.

Clinical characteristics and outcomes of care in patients hospitalized with diabetic ketoacidosis

AIMS

To assess the clinical characteristics and outcomes of patients hospitalized with DKA.

METHODS

We examined the hospital database for patients admitted with DKA to all government hospitals in Qatar over 6 years.

RESULTS

We evaluated a total of 1330 patients [(37.3 % with type 1 diabetes (T1DM) and 62.7 % with type 2 diabetes (T2DM)] with 1613 episodes of DKA. Patients with T2DM were older than those with T1DM [48.0 (38.0-60.0), 26.0 (21.0-31.0) years] while there was no difference in DKA severity and laboratory values on admission or time to resolution of DKA. Admission to the intensive care unit was higher (38.9 % vs. 26.6 %; P < 0.001) with a longer hospital stay [5 (2.0-9.0) vs. 2 (2.0-4.0) days, P < 0.001] and markedly higher mortality (7.4 % vs. 1 %; P < 0.001) in patients with T2DM compared to T1DM. On multivariable logistic regression analysis, significant predictors of mortality were older age (odds ratio, 1.11; 95 % CI, 1.07-1.15; P = 0.0001), and admission to the intensive care unit (odds ratio, 3.61; 95 % CI, 1.69-7.72;P = 0.001).

CONCLUSION

In this national cohort of patients hospitalized with DKA, those with T2DM had a 7-fold increase in inpatient mortality associated with older age and admission to the intensive care unit.

Retinal structure-function correlation in type 2 diabetes

OBJECTIVE

To examine the relationship of visual function as assessed by visual acuity, contrast sensitivity, and multifocal electroretinography (mfERG) to macular structural and microvascular measures on optical coherence tomography (OCT) and angiography (OCTA) in individuals with diabetes.

METHODS

This is a prospective observational study conducted at a tertiary eye care centre in India. Right eyes of 121 adults with type 2 diabetes with no diabetic retinopathy (DR), mild or moderate nonproliferative DR (NPDR) were examined. Severe NPDR, proliferative DR and diabetic macular oedema were excluded. Participants underwent assessment of glycated haemoglobin (HbA1C), blood pressure, best corrected visual acuity (LogMAR), contrast sensitivity (CS), mfERG, ultrawide field fundus photography, OCT and OCTA. Correlations were assessed by Spearman's rank correlation (rho).

RESULTS

Of the total of 121 eyes, 89 had No DR, 32 had mild to moderate NPDR. In the No DR group, the LogMAR acuity was significantly and negatively correlated to central subfoveal thickness (CST) (rho = -0.420), macular vessel density (rho = -0.270) and perfusion (rho = -0.270). (ii) Contrast sensitivity correlated to foveal avascular zone circularity (rho = 0.297); (iii) mfERG P1 response densities were better with higher macular perfusion index (rho = 0.240). In the NPDR group, the LogMAR acuity also showed a significant negative correlation to CST (rho = -0.379). Other correlations were not significant.

CONCLUSION

Retinal and visual functional changes are evident in diabetic patients with No DR and are correlated to subclinical retinal structural changes detectable using multimodal imaging.

Corneal confocal microscopy differentiates patients with Parkinson’s disease with and without autonomic involvement

Autonomic dysregulation in Parkinson’s disease (PD) can precede motor deficits and is associated with reduced quality of life, disease progression, and increased mortality. Objective markers of autonomic involvement in PD are limited. Corneal confocal microscopy (CCM) is a rapid ophthalmic technique that can quantify small nerve damage in a range of peripheral and autonomic neuropathies. Here we investigated whether CCM can be used to assess autonomic symptoms in PD. Based on the scale for outcomes in Parkinson’s disease for autonomic symptoms (SCOPA-AUT), patients with PD were classified into those without autonomic symptoms (AutD-N), with single (AutD-S), and multiple (AutD-M) domain autonomic dysfunction. Corneal nerve fiber pathology was quantified using CCM, and the relationship with autonomic symptoms was explored. The study enrolled 71 PD patients and 30 control subjects. Corneal nerve fiber density (CNFD), corneal nerve branch density (CNBD), corneal nerve fiber length (CNFL), and CNBD/CNFD ratio were lower in PD patients with autonomic symptoms compared to those without autonomic symptoms. Autonomic symptoms correlated positively with CNFD (r = −0.350, p = 0.004), and were not related to Levodopa equivalent daily dose (r = 0.042, p = 0.733) after adjusting for age, disease severity, disease duration or cognitive function. CCM parameters had high sensitivity and specificity in distinguishing patients with PD with and without autonomic symptoms. PD patients with autonomic symptoms have corneal nerve loss, and CCM could serve as an objective ophthalmic imaging technique to identify patients with PD and autonomic symptoms.

The Peripheral Neuropathy Prevalence and Characteristics Are Comparable in People with Obesity and Long-Duration Type 1 Diabetes

INTRODUCTION

Peripheral neuropathy is reported in obesity even in the absence of hyperglycaemia.

OBJECTIVE

To compare the prevalence and characterise the phenotype of peripheral neuropathy in people living with obesity (OB) and long-duration type 1 diabetes (T1D).

PATIENTS AND METHODS

We performed a prospective cross-sectional study of 130 participants including healthy volunteers (HV) (n = 28), people with T1D (n = 51), and OB (BMI 30-50 kg/m2) (n = 51). Participants underwent assessment of neuropathic symptoms (Neuropathy Symptom Profile, NSP), neurological deficits (Neuropathy Disability Score, NDS), vibration perception threshold (VPT) and evaluation of sural nerve conduction velocity and amplitude.

RESULTS

Peripheral neuropathy was present in 43.1% of people with T1D (age 49.9 ± 12.9 years; duration of diabetes 23.4 ± 13.5 years) and 33.3% of OB (age 48.2 ± 10.8 years). VPT for high risk of neuropathic foot ulceration (VPT ≥ 25 V) was present in 31.4% of T1D and 19.6% of OB. Participants living with OB were heavier (BMI 42.9 ± 3.5 kg/m2) and had greater centripetal adiposity with an increased body fat percentage (FM%) (P < 0.001) and waist circumference (WC) (P < 0.001) compared to T1D. The OB group had a higher NDS (P < 0.001), VAS for pain (P < 0.001), NSP (P < 0.001), VPT (P < 0.001) and reduced sural nerve conduction velocity (P < 0.001) and amplitude (P < 0.001) compared to HV, but these parameters were comparable in T1D. VPT was positively associated with increased WC (P = 0.011), FM% (P = 0.001) and HbA1c (P < 0.001) after adjusting for age (R2 = 0.547). Subgroup analysis of respiratory quotient (RQ) measured in the OB group did not correlate with VPT (P = 0.788), nerve conduction velocity (P = 0.743) or amplitude (P = 0.677).

CONCLUSION

The characteristics of peripheral neuropathy were comparable between normoglycaemic people living with obesity and people with long-duration T1D, suggesting that metabolic factors linked to obesity play a pivotal role in the development of peripheral neuropathy. Further studies are needed to investigate the mechanistic link between visceral adiposity and neuropathy.

Bariatric Surgery-induced High-density Lipoprotein Functionality Enhancement Is Associated With Reduced Inflammation

BACKGROUND

Emerging evidence suggests an association between impaired high-density lipoprotein (HDL) functionality and cardiovascular disease (CVD). HDL is essential for reverse cholesterol transport (RCT) and reduces inflammation and oxidative stress principally via paraoxonase-1 (PON1). RCT depends on HDL's capacity to accept cholesterol (cholesterol efflux capacity [CEC]) and active transport through ATP-binding cassette (ABC) A1, G1, and scavenger receptor-B1 (SR-B1). We have studied the impact of Roux-en-Y gastric bypass (RYGB) in morbidly obese subjects on RCT and HDL functionality.

METHODS

Biomarkers associated with increased CVD risk including tumour necrosis factor-α (TNF-α), high-sensitivity C-reactive protein (hsCRP), myeloperoxidase mass (MPO), PON1 activity, and CEC in vitro were measured in 44 patients before and 6 and 12 months after RYGB. Overweight but otherwise healthy (mean body mass index [BMI] 28 kg/m2) subjects acted as controls. Twelve participants also underwent gluteal subcutaneous adipose tissue biopsies before and 6 months after RYGB for targeted gene expression (ABCA1, ABCG1, SR-B1, TNF-α) and histological analysis (adipocyte size, macrophage density, TNF-α immunostaining).

RESULTS

Significant (P < 0.05) improvements in BMI, HDL-cholesterol, hsCRP, TNF-α, MPO mass, PON1 activity, and CEC in vitro were observed after RYGB. ABCG1 (fold-change, 2.24; P = 0.005) and ABCA1 gene expression increased significantly (fold-change, 1.34; P = 0.05). Gluteal fat adipocyte size (P < 0.0001), macrophage density (P = 0.0067), and TNF-α immunostaining (P = 0.0425) were reduced after RYBG and ABCG1 expression correlated inversely with TNF-α immunostaining (r = -0.71; P = 0.03).

CONCLUSION

RYGB enhances HDL functionality in association with a reduction in adipose tissue and systemic inflammation.

COVID-19 and the hidden threat of diabetic microvascular complications

The coronavirus disease 2019 (COVID-19) pandemic affected at least 200 million individuals worldwide and resulted in nearly 5 million deaths as of October 2021. According to the latest data from the International Diabetes Federation (IDF) in 2021, the diabetes pandemic has affected 537 million people and is associated with 6.7 million deaths. Given the high prevalence of both diabetes and COVID-19 and common pathological outcomes, a bidirectional relationship could have a catastrophic outcome. The increased risk of COVID-19 in those with obesity and diabetes and higher morbidity and mortality has received considerable attention. However, little attention has been given to the relationship between COVID-19 and microvascular complications. Indeed, microvascular complications are associated with an increased risk of cardiovascular disease (CVD) and mortality in diabetes. This review assesses the evidence for an association between diabetic microvascular complications (neuropathy, nephropathy, and retinopathy) and COVID-19. It draws parallels between the pathological changes occurring in the microvasculature in both diseases and assesses whether microvascular disease is a prognostic factor for COVID-19 outcomes in diabetes.

Early retinal functional alteration in relation to diabetes duration in patients with type 2 diabetes without diabetic retinopathy

To examine the retinal structure and function in relation to diabetes duration and glycemia in patients without diabetic retinopathy (DR). 85 adults with type 2 diabetes without DR or macular edema underwent dilated indirect ophthalmoscopy, optical coherence tomography (OCT), ultra-wide field fundus photography, multifocal electroretinography (mfERG) and HbA_1C assessment. Patients were stratified as those with diabetes duration < 10 years and ≥ 10 years. Right eyes of all participants were analyzed. mfERG was analysed as ring 12, 34, 56. No significant differences were noted in OCT-derived retinal thickness measures between groups. mfERG P1 latencies were delayed, and amplitudes (nV/deg²) were reduced in all three rings in those with diabetes duration ≥ 10 years vs. < 10 years, with significant correlations to diabetes duration in all rings. Logistic regression showed that duration of diabetes ≥ 10 years was associated with greater age (odds ratio (OR) 1.081, 95% CI 1.022, 1.143) and lower P1 amplitudes in the middle ring (OR 0.924, 95% CI 0.854, 0.999). No significant correlations were observed between HbA_1c and retinal measures. In the absence of DR, early retinal functional alterations are detectable on mfERG in patients with longer diabetes duration, but with no difference in OCT-derived retinal thickness.

Lipids, Lipid-Lowering Therapy, and Neuropathy: A Narrative Review

Statins, or 3-hydroxy-3-methylglutaryl coenzyme A reductase inhibitors, are the mainstay of treatment for hypercholesterolemia as they effectively reduce LDL-C levels and risk of atherosclerotic cardiovascular disease. Apart from hyperglycemia, dyslipidemia and HDL dysfunction are known risk factors for neuropathy in people with obesity and diabetes. Although there are case reports of statin-induced neuropathy, ad hoc analyses of clinical trials and observational studies have shown that statins may improve peripheral neuropathy. However, large randomized controlled trials and meta-analyses of cardiovascular outcome trials with statins and other lipid-lowering drugs have not reported on neuropathy outcomes. Because neuropathy was not a prespecified outcome in major cardiovascular trials, one cannot conclude whether statins or other lipid-lowering therapies increase or decrease the risk of neuropathy. The aim of this review was to assess if statins have beneficial or detrimental effects on neuropathy and whether there is a need for large well-powered interventional studies using objective neuropathy end points.

Is Clinical Research Serving the Needs of the Global Cancer Burden? An Analysis of Contemporary Global Radiation Therapy Randomized Controlled Trials

PURPOSE

Randomized controlled trials (RCTs) are the cornerstone of delivering sustained improvements in cancer outcome. To inform radiation therapy research policy and prioritization, we analyze the radiation therapy RCT landscape including comparison with trials of systemic therapies over the same period, with a specific focus on funding and disparities across income settings.

METHODS AND MATERIALS

This retrospective cohort study identified all phase 3 RCTs evaluating anticancer therapies published from 2014 to 2017. RCTs were classified according to anticancer modality and country of origin. Descriptive statistics were used to compare key characteristics of radiation therapy RCT studies according to study design characteristics, tumor types evaluated, types of intervention appraised, treatment intent and main funding sources.

RESULTS

The study cohort included 694 RCTs of which 64 were radiation therapy RCTs (9%) compared with 601 systemic therapy RCTs (87%). Among all radiation therapy RCTs, 47% of them focused on 2 areas of evaluation: (1) combining radiation therapy with systemic agents (25%) and (2) changes in dose fractionation (22%). The most common cancers studied were head and neck (22%), lung (22%), and breast (14%), with cervical cancer trials representing only 3% of the cohort. Among the radiation therapy RCTs, 33% of them met their primary endpoint, and 62% assessed interventions in the curative setting compared with 31% in systemic therapy RCTs. For their country locations, 77% of radiation therapy RCTs took place in high-income countries, 13% in low-and-middle-income countries, and 11% in both high-income and low-and-middle-income countries. For funding, 17% of radiation therapy RCTs received funding from industry compared with 79% of systemic therapy RCTs.

CONCLUSIONS

This study highlights the need for greater investment in radiation therapy RCTs and the need to look at the disparities in conducting RCTs globally. The study emphases the urgent need for more capacity building for cancer clinical trials in low-and-middle-income countries and more sustainable funding sources.

Perioperative Hypothermia Is Associated With Increased 30-Day Mortality in Hip Fracture Patients in the United Kingdom: Α Systematic Review and Meta-analysis

OBJECTIVES

To undertake a systematic review and meta-analysis to determine the relationship between perioperative hypothermia and mortality after surgery for hip fracture.

DATA SOURCES

A systematic literature search of Medline, EMBASE, CINAHL, and Cochrane CENTRAL databases was performed using the Cochrane methodology for systematic reviews with no publication year limit. Only studies available in the English language were included.

STUDY SELECTION

Predetermined inclusion criteria were patients of any age with a hip fracture, exposure was their body temperature and outcome was mortality rate. Any comparative study design was eligible.

DATA EXTRACTION

The quality of selected studies was assessed according to each study design with the Methodological Index for Non-Randomised Studies (MINORS) used for all the retrospective comparative studies. The GRADE approach was used to assess the quality of evidence.

DATA SYNTHESIS

A meta-analysis was conducted using a random-effects model.

RESULTS

The literature search identified 1016 records. After removing duplicates and those not meeting inclusion criteria, 3 studies measuring 30-day mortality were included. All included studies were carried out in the United Kingdom. The mortality rate was higher in the hypothermic groups as compared with the normothermic group in all the studies, with the difference being significant in 2 of the studies (P < 0.0001). The meta-analysis showed that low body temperature was associated with an increased mortality risk (estimated odds ratio: 2.660; 95% confidence interval: 1.948-3.632; P < 0.001) in patients undergoing surgery for hip fracture.

CONCLUSIONS

This study shows that low body temperature in hip fracture patients is associated with an increased 30-day mortality risk in the United Kingdom. Randomized control trials are required to determine whether the association between perioperative hypothermia in hip fracture patients and mortality is causal. Nevertheless, based on this analysis, we urge the maintenance of normal body temperature in the perioperative period to be included in national hip fracture guidelines.

LEVEL OF EVIDENCE

Prognostic Level III. See Instructions for Authors for a complete description of levels of evidence.

Peripheral Ion Channel Gene Screening in Painful- and Painless-Diabetic Neuropathy

Neuropathic pain is common in diabetic peripheral neuropathy (DN), probably caused by pathogenic ion channel gene variants. Therefore, we performed molecular inversion probes-next generation sequencing of 5 transient receptor potential cation channels, 8 potassium channels and 2 calcium-activated chloride channel genes in 222 painful- and 304 painless-DN patients. Twelve painful-DN (5.4%) patients showed potentially pathogenic variants (five nonsense/frameshift, seven missense, one out-of-frame deletion) in ANO3 (n = 3), HCN1 (n = 1), KCNK18 (n = 2), TRPA1 (n = 3), TRPM8 (n = 3) and TRPV4 (n = 1) and fourteen painless-DN patients (4.6%-three nonsense/frameshift, nine missense, one out-of-frame deletion) in ANO1 (n = 1), KCNK18 (n = 3), KCNQ3 (n = 1), TRPA1 (n = 2), TRPM8 (n = 1), TRPV1 (n = 3) and TRPV4 (n = 3). Missense variants were present in both conditions, presumably with loss- or gain-of-functions. KCNK18 nonsense/frameshift variants were found in painless/painful-DN, making a causal role in pain less likely. Surprisingly, premature stop-codons with likely nonsense-mediated RNA-decay were more frequent in painful-DN. Although limited in number, painful-DN patients with ion channel gene variants reported higher maximal pain during the night and day. Moreover, painful-DN patients with TRP variants had abnormal thermal thresholds and more severe pain during the night and day. Our results suggest a role of ion channel gene variants in neuropathic pain, but functional validation is required.

Progressive loss of corneal nerve fibers is associated with physical inactivity and glucose lowering medication associated with weight gain in type 2 diabetes

Aims/Introduction

Limited studies have identified risk factors linked to the progression of diabetic peripheral neuropathy (DPN) in type 2 diabetes. This study examined the association of risk factors with change in neuropathy measures over 2 years.

Materials and Methods

Participants with type 2 diabetes (n = 78) and controls (n = 26) underwent assessment of clinical and metabolic parameters and neuropathy using corneal confocal microscopy (CCM), vibration perception threshold (VPT), and the DN4 questionnaire at baseline and 2 year follow‐up.

Results

Participants with type 2 diabetes had a lower corneal nerve fiber density (CNFD), branch density (CNBD), and fiber length (CNFL) (P ≤ 0.0001) and a higher VPT (P ≤ 0.01) compared with controls. Over 2 years, despite a modest reduction in HbA1c (P ≤ 0.001), body weight (P ≤ 0.05), and LDL (P ≤ 0.05) the prevalence of DPN (P = 0.28) and painful DPN (P = 0.21) did not change, but there was a significant further reduction in CNBD (P ≤ 0.0001) and CNFL (P ≤ 0.05). CNFD, CNBD, and CNFL decreased significantly in physically inactive subjects (P < 0.05–0.0001), whilst there was no change in CNFD (P = 0.07) or CNFL (P = 0.85) in physically active subjects. Furthermore, there was no change in CNFD (P = 0.82), CNBD (P = 0.08), or CNFL (P = 0.66) in patients treated with glucose lowering medication associated with weight loss, whilst CNBD (P = 0.001) decreased in patients on glucose lowering medication associated with weight gain.

Conclusions

In participants with type 2 diabetes, despite a modest improvement in HbA1c, body weight, and LDL there was a progressive loss of corneal nerve fibers; except in those who were physically active or on glucose lowering medication associated with weight loss.

A Novel Machine Learning Approach for Severity Classification of Diabetic Foot Complications Using Thermogram Images

Diabetes mellitus (DM) is one of the most prevalent diseases in the world, and is correlated to a high index of mortality. One of its major complications is diabetic foot, leading to plantar ulcers, amputation, and death. Several studies report that a thermogram helps to detect changes in the plantar temperature of the foot, which may lead to a higher risk of ulceration. However, in diabetic patients, the distribution of plantar temperature does not follow a standard pattern, thereby making it difficult to quantify the changes. The abnormal temperature distribution in infrared (IR) foot thermogram images can be used for the early detection of diabetic foot before ulceration to avoid complications. There is no machine learning-based technique reported in the literature to classify these thermograms based on the severity of diabetic foot complications. This paper uses an available labeled diabetic thermogram dataset and uses the k-mean clustering technique to cluster the severity risk of diabetic foot ulcers using an unsupervised approach. Using the plantar foot temperature, the new clustered dataset is verified by expert medical doctors in terms of risk for the development of foot ulcers. The newly labeled dataset is then investigated in terms of robustness to be classified by any machine learning network. Classical machine learning algorithms with feature engineering and a convolutional neural network (CNN) with image-enhancement techniques are investigated to provide the best-performing network in classifying thermograms based on severity. It is found that the popular VGG 19 CNN model shows an accuracy, precision, sensitivity, F1-score, and specificity of 95.08%, 95.08%, 95.09%, 95.08%, and 97.2%, respectively, in the stratification of severity. A stacking classifier is proposed using extracted features of the thermogram, which is created using the trained gradient boost classifier, XGBoost classifier, and random forest classifier. This provides a comparable performance of 94.47%, 94.45%, 94.47%, 94.43%, and 93.25% for accuracy, precision, sensitivity, F1-score, and specificity, respectively.

Sense and Learn: Recent Advances in Wearable Sensing and Machine Learning for Blood Glucose Monitoring and Trend-Detection

Diabetes mellitus is characterized by elevated blood glucose levels, however patients with diabetes may also develop hypoglycemia due to treatment. There is an increasing demand for non-invasive blood glucose monitoring and trends detection amongst people with diabetes and healthy individuals, especially athletes. Wearable devices and non-invasive sensors for blood glucose monitoring have witnessed considerable advances. This review is an update on recent contributions utilizing novel sensing technologies over the past five years which include electrocardiogram, electromagnetic, bioimpedance, photoplethysmography, and acceleration measures as well as bodily fluid glucose sensors to monitor glucose and trend detection. We also review methods that use machine learning algorithms to predict blood glucose trends, especially for high risk events such as hypoglycemia. Convolutional and recurrent neural networks, support vector machines, and decision trees are examples of such machine learning algorithms. Finally, we address the key limitations and challenges of these studies and provide recommendations for future work.

Retinal vessel multifractals predict pial collateral status in patients with acute ischemic stroke

OBJECTIVES

Pial collateral blood flow is a major determinant of the outcomes of acute ischemic stroke. This study was undertaken to determine whether retinal vessel metrics can predict the pial collateral status and stroke outcomes in patients.

METHODS

Thirty-five patients with acute stroke secondary to middle cerebral artery (MCA) occlusion underwent grading of their pial collateral status from computed tomography angiography and retinal vessel analysis from retinal fundus images.

RESULTS

The NIHSS (14.7 ± 5.5 vs 10.1 ± 5.8, p = 0.026) and mRS (2.9 ± 1.6 vs 1.9 ± 1.3, p = 0.048) scores were higher at admission in patients with poor compared to good pial collaterals. Retinal vessel multifractals: D0 (1.673±0.028vs1.652±0.025, p = 0.028), D1 (1.609±0.027vs1.590±0.025, p = 0.044) and f(α)max (1.674±0.027vs1.652±0.024, p = 0.019) were higher in patients with poor compared to good pial collaterals. Furthermore, support vector machine learning achieved a fair sensitivity (0.743) and specificity (0.707) for differentiating patients with poor from good pial collaterals. Age (p = 0.702), BMI (p = 0.422), total cholesterol (p = 0.842), triglycerides (p = 0.673), LDL (p = 0.952), HDL (p = 0.366), systolic blood pressure (p = 0.727), HbA1c (p = 0.261) and standard retinal metrics including CRAE (p = 0.084), CRVE (p = 0.946), AVR (p = 0.148), tortuosity index (p = 0.790), monofractal Df (p = 0.576), lacunarity (p = 0.531), curve asymmetry (p = 0.679) and singularity length (p = 0.937) did not differ between patients with poor compared to good pial collaterals.

CONCLUSIONS

This is the first translational study to show increased retinal vessel multifractal dimensions in patients with acute ischemic stroke and poor pial collaterals. A retinal vessel classifier was developed to differentiate between patients with poor and good pial collaterals and may allow rapid non-invasive identification of patients with poor pial collaterals.

Effect of Ramadan fasting in patients with type 2 diabetes mellitus treated with sodium-glucose cotransporter 2 inhibitors: A systematic review and meta-analysis

AIMS/INTRODUCTION

Sodium-glucose cotransporter 2 inhibitors (SGLT-2i) improve glycemic control and weight, but might be associated with dehydration, hypotension and ketoacidosis, especially in patients with type 2 diabetes mellitus who fast during Ramadan. This meta-analysis evaluates the effects of Ramadan fasting on patients with type 2 diabetes mellitus treated with SGLT-2i.

MATERIALS AND METHODS

A literature search was carried out in PubMed, Embase and the Cochrane Library. Quality assessment was carried out using the ROBINS-I and Cochrane tools for risk of bias, and analyses were carried out using RevMan version 5.3.

RESULTS

A total of five studies were included in this meta-analysis. During Ramadan, there was a significant reduction in glycated hemoglobin (P < 0.00001) and diastolic blood pressure (P = 0.006), with a non-significant trend for a reduction in weight (P = 0.44) and systolic blood pressure (P = 0.67). The number and severity of hypoglycemic episodes was lower in patients with type 2 diabetes mellitus treated with SGLT-2i compared with sulfonylureas. There was no significant change in estimated glomerular filtration rate, β-hydroxybutyrate, bicarbonate or anion gap. However, we identified considerable heterogeneity among studies, and a lack of head-to-head studies with structured outcome reporting on the risks and benefits of SGLT-2i during Ramadan.

CONCLUSIONS

This systematic review and meta-analysis shows that patients with type 2 diabetes treated with SGLT2i's during Ramadan have an improvement in HbA1c, less hypoglycemia and no major adverse effects.