Citations

A diabetic foot infection (DFI) is among the most serious, incurable, and costly to treat conditions. The presence of a DFI renders machine learning (ML) systems extremely nonlinear, posing difficulties in CVD/stroke risk stratification. In addition, there is a limited number of well-explained ML paradigms due to comorbidity, sample size limits, and weak scientific and clinical validation methodologies. Deep neural networks (DNN) are potent machines for learning that generalize nonlinear situations. The objective of this article is to propose a novel investigation of deep learning (DL) solutions for predicting CVD/stroke risk in DFI patients. The Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) search strategy was used for the selection of 207 studies. We hypothesize that a DFI is responsible for increased morbidity and mortality due to the worsening of atherosclerotic disease and affecting coronary artery disease (CAD). Since surrogate biomarkers for CAD, such as carotid artery disease, can be used for monitoring CVD, we can thus use a DL-based model, namely, Long Short-Term Memory (LSTM) and Recurrent Neural Networks (RNN) for CVD/stroke risk prediction in DFI patients, which combines covariates such as office and laboratory-based biomarkers, carotid ultrasound image phenotype (CUSIP) lesions, along with the DFI severity. We confirmed the viability of CVD/stroke risk stratification in the DFI patients. Strong designs were found in the research of the DL architectures for CVD/stroke risk stratification. Finally, we analyzed the AI bias and proposed strategies for the early diagnosis of CVD/stroke in DFI patients. Since DFI patients have an aggressive atherosclerotic disease, leading to prominent CVD/stroke risk, we, therefore, conclude that the DL paradigm is very effective for predicting the risk of CVD/stroke in DFI patients.

Diabetes is one of the main causes of the rising cases of blindness in adults. This microvascular complication of diabetes is termed diabetic retinopathy (DR) and is associated with an expanding risk of cardiovascular events in diabetes patients. DR, in its various forms, is seen to be a powerful indicator of atherosclerosis. Further, the macrovascular complication of diabetes leads to coronary artery disease (CAD). Thus, the timely identification of cardiovascular disease (CVD) complications in DR patients is of utmost importance. Since CAD risk assessment is expensive for low-income countries, it is important to look for surrogate biomarkers for risk stratification of CVD in DR patients. Due to the common genetic makeup between the coronary and carotid arteries, low-cost, high-resolution imaging such as carotid B-mode ultrasound (US) can be used for arterial tissue characterization and risk stratification in DR patients. The advent of artificial intelligence (AI) techniques has facilitated the handling of large cohorts in a big data framework to identify atherosclerotic plaque features in arterial ultrasound. This enables timely CVD risk assessment and risk stratification of patients with DR. Thus, this review focuses on understanding the pathophysiology of DR, retinal and CAD imaging, the role of surrogate markers for CVD, and finally, the CVD risk stratification of DR patients. The review shows a step-by-step cyclic activity of how diabetes and atherosclerotic disease cause DR, leading to the worsening of CVD. We propose a solution to how AI can help in the identification of CVD risk. Lastly, we analyze the role of DR/CVD in the COVID-19 framework.

Background: A composite metric for the quality of glycemia from continuous glucose monitor (CGM) tracings could be useful for assisting with basic clinical interpretation of CGM data. Methods: We assembled a data set of 14-day CGM tracings from 225 insulin-treated adults with diabetes. Using a balanced incomplete block design, 330 clinicians who were highly experienced with CGM analysis and interpretation ranked the CGM tracings from best to worst quality of glycemia. We used principal component analysis and multiple regressions to develop a model to predict the clinician ranking based on seven standard metrics in an Ambulatory Glucose Profile: very low–glucose and low-glucose hypoglycemia; very high–glucose and high-glucose hyperglycemia; time in range; mean glucose; and coefficient of variation. Results: The analysis showed that clinician rankings depend on two components, one related to hypoglycemia that gives more weight to very low-glucose than to low-glucose and the other related to hyperglycemia that likewise gives greater weight to very high-glucose than to high-glucose. These two components should be calculated and displayed separately, but they can also be combined into a single Glycemia Risk Index (GRI) that corresponds closely to the clinician rankings of the overall quality of glycemia (r = 0.95). The GRI can be displayed graphically on a GRI Grid with the hypoglycemia component on the horizontal axis and the hyperglycemia component on the vertical axis. Diagonal lines divide the graph into five zones (quintiles) corresponding to the best (0th to 20th percentile) to worst (81st to 100th percentile) overall quality of glycemia. The GRI Grid enables users to track sequential changes within an individual over time and compare groups of individuals. Conclusion: The GRI is a single-number summary of the quality of glycemia. Its hypoglycemia and hyperglycemia components provide actionable scores and a graphical display (the GRI Grid) that can be used by clinicians and researchers to determine the glycemic effects of prescribed and investigational treatments.

Background: Epsilon (e) variants in the Apolipoprotein E (APOE) gene are well-established risk factors for spontaneous intracerebral hemorrhage (s-ICH). We tested the hypothesis that APOE-e variants are also associated with warfarin-related ICH (w-ICH) and examined interactions between APOE and warfarin. Methods: Prospective multicenter 2-stage (discovery and replication) study. ICH was classified as lobar and non-lobar based on admission head CT. In the discovery stage, w-ICH cases were matched with warfarin-exposed controls (w-controls). In replication, w-ICH cases were matched with non-warfarin controls (nw-controls). APOE was directly genotyped. Association testing was performed using multivariable logistic regression. Gene-environment interaction between APOE and warfarin was formally tested using a case only approach (combining s-ICH and w-ICH cases). Results: The discovery stage included 316 w-ICHs (43% lobar and 57% non-lobar) and 355 w-controls. Results are presented in the Table: APOE-e2 was associated with lobar and non-lobar w-ICH, and APOE-e4 was associated with lobar but not with non-lobar w-ICH. In case-only analysis, 885 s-ICHs were combined with w-ICHs (total n=1201) and no evidence of interaction between APOE and warfarin was found (all p>0.20). The replication included 63 w-ICHs (44% lobar and 56% non-lobar) and 990 nw-controls. The distribution of APOE variants was similar in w-controls (discovery) and nw-controls (replication) for both e2 (p=0.81) and e4 (p=0.88). In replication, APOE-e2 and e4 were associated with lobar but not with non-lobar w-ICH. Conclusions: APOE-e variants constitute strong risk factors for lobar w-ICH. An effect may also exist between APOE-e2 and non-lobar hemorrhages, but given the lack of replication larger sample sizes are required to properly assess this association. APOE exerts its effect independently of warfarin, although power limitations render this absence of interaction preliminary.

Purpose: Intracerebral hemorrhage (ICH) is the acute manifestation of a progressive disease of the cerebral small vessels. The severity of this disease appears to influence not only risk of ICH, but also the size of the hematoma. As the burden of high blood pressure(BP)-associated alleles is associated with hypertension-related end-organ damage, we sought to determine if this burden influences ICH admission hematoma volume (AHV). Methods: Prospective study undertaken in 441 ICH patients of European ancestry (210 deep and 231 lobar intracranial hematomas). Forty-three single-nucleotide polymorphisms (SNPs) known to be associated with high BP were genotyped in Illumina610-Quad. Single-SNP association analyses with AHV were performed using linear regression. Subsequently, a genetic risk score was calculated as the sum of the products generated by multiplying, at each of the 43 loci, the number risk alleles times the reported effect of that allele on BP. The score was utilized as the independent variable of univariate and multivariate regression models for 2 outcomes: AHV and poor clinical outcome (modified Rankin Scale 3-6). Principal components analysis was utilized to account for population structure. Results: Individually assessed, no single SNP was associated with AHV. In univariate linear regression, the genetic risk score was associated with AHV in all (deep and lobar) and deep locations (Figure 1), but not in lobar hemorrhages. In multivariate regression analyses, each additional standard deviation of the genetic risk score increased mean deep AHV by 21% (or 2.7-milliliter increase, beta=0.21, standard error=0.08, p=0.01) and risk poor clinical outcome by 55% (odds ratio=1.55, 95% confidence interval 1.05-2.28, p=0.03). No significant associations were observed when considering all (deep and lobar) and lobar hemorrhages. Conclusion: In deep ICH, increasing numbers of high BP-related alleles are associated with larger AHV and poor clinical outcome.

Background The landmark study of durvalumab as consolidation therapy in NSCLC patients (PACIFIC trial) demonstrated significantly longer progression-free survival (PFS) in patients with locally advanced, unresectable non-small cell lung cancer (NSCLC) treated with durvalumab (immunotherapy, IO) therapy after chemoradiotherapy (CRT). In clinical practice in the USA, durvalumab continues to be used in patients across all levels of programmed cell death ligand-1 (PD-L1) expression. While immune therapies have shown promise in several cancers, some patients either do not respond to the therapy or have cancer recurrence after an initial response. It is not clear so far who will benefit of this therapy or what the mechanisms behind treatment failure are. Methods A total of 133 patients with unresectable stage III NSCLC who underwent durvalumab after CRT or CRT alone were included. Patients treated with durvalumab IO after CRT were randomly split into training (D1=59) and test (D2=59) sets and the remaining 15 patients treated with CRT alone were grouped in D3. Radiomic textural patterns from within and around the target nodules were extracted. A radiomic risk score (RRS) was built and was used to predict PFS and overall survival (OS). Patients were divided into high-risk and low-risk groups based on median RRS. Results RRS was found to be significantly associated with PFS in D1 (HR=2.67, 95% CI 1.85 to 4.13, p<0.05, C-index=0.78) and D2 (HR=2.56, 95% CI 1.63 to 4, p<0.05, C-index=0.73). Similarly, RRS was associated with OS in D1 (HR=1.89, 95% CI 1.3 to 2.75, p<0.05, C-index=0.67) and D2 (HR=2.14, 95% CI 1.28 to 3.6, p<0.05, C-index=0.69), respectively. RRS was found to be significantly associated with PFS in high PD-L1 (HR=3.01, 95% CI 1.41 to 6.45, p=0.0044) and low PD-L1 (HR=2.74, 95% CI 1.8 to 4.14, p=1.77e-06) groups. Moreover, RRS was not significantly associated with OS in the high PD-L1 group (HR=2.08, 95% CI 0.98 to 4.4, p=0.054) but was significantly associated with OS in the low PD-L1 group (HR=1.61, 95% CI 1.14 to 2.28, p=0.0062). In addition, RRS was significantly associated with PFS (HR=2.77, 95% CI 1.17 to 6.52, p=0.019, C-index=0.77) and OS (HR=2.62, 95% CI 1.25 to 5.51, p=0.01, C-index=0.77) in D3, respectively. Conclusions Tumor radiomics of pretreatment CT images from patients with stage III unresectable NSCLC were prognostic of PFS and OS to CRT followed by durvalumab IO and CRT alone.

Abstract Objective To evaluate the content validity and psychometric properties of the Activity Impairment in Migraine Diary (AIM‐D). Background Measuring treatment effects on migraine impairment requires a psychometrically sound patient‐reported outcome (PRO) measure developed consistent with U.S. Food and Drug Administration guidance. Methods The AIM‐D was created from concepts that emerged during qualitative interviews with five clinicians experienced in treating migraine and concept elicitation (CE) interviews with 40 adults with episodic migraine (EM) or chronic migraine (CM). The initial version was refined based on three waves of cognitive interviews with 38 adults with EM or CM and input from a panel of clinical and measurement experts. The AIM‐D was psychometrically evaluated using data from 316 adults with EM or CM who participated in a 13‐week prospective observational study. Study participants completed PRO assessments including the AIM‐D and a daily headache diary. Exploratory and confirmatory factor analysis were used to determine the factor structure. The reliability, validity, and responsiveness of the AIM‐D were assessed. Additional PRO measures including the Patient Global Impression – Severity (PGI‐S), Migraine Specific Quality of Life Questionnaire, Version 2.1 Role Function‐Restrictive domain, and Headache Impact Test were used for psychometric evaluation of the AIM‐D. Results Based on CE interviews with adults with migraine and input from an expert panel, activity impairment was identified as the target in the preliminary conceptual framework, which had two domains: performance of daily activities (PDAs) and physical impairment (PI). Revision of the draft AIM‐D through multiple rounds of cognitive interviews and expert panel meetings resulted in a content valid 11‐item version. Exploratory factor analysis supported both one‐ and two‐domain structures for the AIM‐D, which were further supported by confirmatory factor analysis (factor loadings all >0.90). The AIM‐D domains (PDA and PI) and total score showed high internal consistency reliability (Cronbach's alpha 0.95–0.97), acceptable test–retest reliability for weekly average scores (intraclass correlation coefficient >0.60 for participants with no change in PGI‐S between baseline and week 2), and good convergent and known‐groups validity. There was evidence of responsiveness based on changes in PGI‐S score and monthly migraine days. Conclusion The AIM‐D is a content valid and psychometrically sound measure designed to evaluate activity impairment and is suitable for use in clinical trials of preventive treatments for EM or CM.

Background: Atherosclerosis is the primary cause of the cardiovascular disease (CVD). Several risk factors lead to atherosclerosis, and altered nutrition is one among those. Nutrition has been ignored quite often in the process of CVD risk assessment. Altered nutrition along with carotid ultrasound imaging-driven atherosclerotic plaque features can help in understanding and banishing the problems associated with the late diagnosis of CVD. Artificial intelligence (AI) is another promisingly adopted technology for CVD risk assessment and management. Therefore, we hypothesize that the risk of atherosclerotic CVD can be accurately monitored using carotid ultrasound imaging, predicted using AI-based algorithms, and reduced with the help of proper nutrition. Layout: The review presents a pathophysiological link between nutrition and atherosclerosis by gaining a deep insight into the processes involved at each stage of plaque development. After targeting the causes and finding out results by low-cost, user-friendly, ultrasound-based arterial imaging, it is important to (i) stratify the risks and (ii) monitor them by measuring plaque burden and computing risk score as part of the preventive framework. Artificial intelligence (AI)-based strategies are used to provide efficient CVD risk assessments. Finally, the review presents the role of AI for CVD risk assessment during COVID-19. Conclusions: By studying the mechanism of low-density lipoprotein formation, saturated and trans fat, and other dietary components that lead to plaque formation, we demonstrate the use of CVD risk assessment due to nutrition and atherosclerosis disease formation during normal and COVID times. Further, nutrition if included, as a part of the associated risk factors can benefit from atherosclerotic disease progression and its management using AI-based CVD risk assessment.

Stroke is a leading cause of the adult disability epidemic in the United States, with a major contribution from poststroke cognitive impairment and dementia (PSCID), the rates of which are disproportionally high among the health disparity populations. Despite the PSCID’s overwhelming impact on public health, a knowledge gap exists with regard to the complex interaction between the acute stroke event and highly prevalent preexisting brain pathology related to cerebrovascular and Alzheimer disease or related dementia. Understanding the factors that modulate PSCID risk in relation to index stroke event is critically important for developing personalized prognostication of PSCID, targeted interventions to prevent it, and for informing future clinical trial design. The DISCOVERY study (Determinants of Incident Stroke Cognitive Outcomes and Vascular Effects on Recovery), a collaborative network of thirty clinical performance clinical sites with access to acute stroke populations and the expertise and capacity for systematic assessment of PSCID will address this critical challenge. DISCOVERY is a prospective, multicenter, observational, nested-cohort study of 8000 nondemented ischemic and hemorrhagic stroke patients enrolled at the time of index stroke and followed for a minimum of 2 years, with serial cognitive evaluations and assessments of functional outcome, with subsets undergoing research magnetic resonance imaging and positron emission tomography and comprehensive genetic/genomic and fluid biomarker testing. The overall scientific objective of this study is to elucidate mechanisms of brain resilience and susceptibility to PSCID in diverse US populations based on complex interplay between life-course exposure to multiple vascular risk factors, preexisting burden of microvascular and neurodegenerative pathology, the effect of strategic acute stroke lesions, and the mediating effect of genomic and epigenomic variation.