Deep Learning Paradigm for Cardiovascular Disease/Stroke Risk Stratification in Parkinson’s Disease Affected by COVID-19: A Narrative Review

Background and Motivation: Parkinson’s disease (PD) is one of the most serious, non-curable, and expensive to treat. Recently, machine learning (ML) has shown to be able to predict cardiovascular/stroke risk in PD patients. The presence of COVID-19 causes the ML systems to become severely non-linear and poses challenges in cardiovascular/stroke risk stratification. Further, due to comorbidity, sample size constraints, and poor scientific and clinical validation techniques, there have been no well-explained ML paradigms. Deep neural networks are powerful learning machines that generalize non-linear conditions. This study presents a novel investigation of deep learning (DL) solutions for CVD/stroke risk prediction in PD patients affected by the COVID-19 framework. Method: The PRISMA search strategy was used for the selection of 292 studies closely associated with the effect of PD on CVD risk in the COVID-19 framework. We study the hypothesis that PD in the presence of COVID-19 can cause more harm to the heart and brain than in non-COVID-19 conditions. COVID-19 lung damage severity can be used as a covariate during DL training model designs. We, therefore, propose a DL model for the estimation of, (i) COVID-19 lesions in computed tomography (CT) scans and (ii) combining the covariates of PD, COVID-19 lesions, office and laboratory arterial atherosclerotic image-based biomarkers, and medicine usage for the PD patients for the design of DL point-based models for CVD/stroke risk stratification. Results: We validated the feasibility of CVD/stroke risk stratification in PD patients in the presence of a COVID-19 environment and this was also verified. DL architectures like long short-term memory (LSTM), and recurrent neural network (RNN) were studied for CVD/stroke risk stratification showing powerful designs. Lastly, we examined the artificial intelligence bias and provided recommendations for early detection of CVD/stroke in PD patients in the presence of COVID-19. Conclusion: The DL is a very powerful tool for predicting CVD/stroke risk in PD patients affected by COVID-19.

The Role of Peritoneal Dialysis in Different Phases of Kidney Transplantation

The utilization of peritoneal dialysis (PD) has been increasing in the past decade owing to various government initiatives and recognition of benefits such as better preservation of residual renal function, quality of life, and lower cost. The Advancing American Kidney Health initiative aims to increase the utilization of home therapies such as PD and kidney transplantation to treat end stage kidney disease (ESKD). A natural consequence of this development is that more patients will receive PD, and many will eventually undergo kidney transplantation. Therefore, it is important to understand the effect of pretransplant PD on posttransplant outcomes such as delayed graft function (DGF), rejection, thrombosis, graft, and patient survival. Furthermore, some of these patients may develop DGF, which raises the question of the utility of PD during DGF and its risks. Although transplant is the best renal replacement therapy option, it is not everlasting, and many transplant recipients must go on dialysis after allograft failure. Can PD be a good option for these patients? This is another critical question. Furthermore, a significant proportion of nonrenal solid organ transplant recipients develop ESKD. Is PD feasible in this group? In this review, we try to address all of these questions in the light of available evidence.

Cardiovascular/Stroke Risk Stratification in Parkinson's Disease Patients Using Atherosclerosis Pathway and Artificial Intelligence Paradigm: A Systematic Review

Parkinson’s disease (PD) is a severe, incurable, and costly condition leading to heart failure. The link between PD and cardiovascular disease (CVD) is not available, leading to controversies and poor prognosis. Artificial Intelligence (AI) has already shown promise for CVD/stroke risk stratification. However, due to a lack of sample size, comorbidity, insufficient validation, clinical examination, and a lack of big data configuration, there have been no well-explained bias-free AI investigations to establish the CVD/Stroke risk stratification in the PD framework. The study has two objectives: (i) to establish a solid link between PD and CVD/stroke; and (ii) to use the AI paradigm to examine a well-defined CVD/stroke risk stratification in the PD framework. The PRISMA search strategy selected 223 studies for CVD/stroke risk, of which 54 and 44 studies were related to the link between PD-CVD, and PD-stroke, respectively, 59 studies for joint PD-CVD-Stroke framework, and 66 studies were only for the early PD diagnosis without CVD/stroke link. Sequential biological links were used for establishing the hypothesis. For AI design, PD risk factors as covariates along with CVD/stroke as the gold standard were used for predicting the CVD/stroke risk. The most fundamental cause of CVD/stroke damage due to PD is cardiac autonomic dysfunction due to neurodegeneration that leads to heart failure and its edema, and this validated our hypothesis. Finally, we present the novel AI solutions for CVD/stroke risk prediction in the PD framework. The study also recommends strategies for removing the bias in AI for CVD/stroke risk prediction using the PD framework.

The Fate of Older Diabetic Patients on Peritoneal Dialysis: Myths and Mysteries and Suggestions for Further Research

The outcome of older and especially of female diabetic patients appears to be worse on peritoneal dialysis (PD) than on hemodialysis (HD). This opinion is based mostly on data coming from the USA, whereas data from other regions seem to give a more balanced picture. The questions arise whether indeed outcome is worse in this patient group, and what might be the underlying reasons for this; further research to unravel this phenomenon is warranted. This review proposes several suggestions for further exploration. The observed differences in outcome might be attributable to differences in treatment practices and experience with PD versus HD. As cardiovascular mortality is a major killer in end-stage renal disease patients, differences in fluid homeostasis and how it is achieved are potential explanations. Fluid balance is potentially more difficult to obtain in PD patients, especially as in the past it was spuriously suggested that fluid restriction was less important in PD patients. PD and HD might also have different impacts on factors related to inflammation, insulin resistance, and hormone balance. The adipocytokine network is of special interest in this respect. It is also possible that bias introduced by the way we measure body composition might have a more negative impact on PD than on HD patients. Finally, it still is not fully established that if diabetic patients are treated appropriately, their outcome on PD is worse than that on HD; further observational trials in this respect are needed. All these topics require further clarification and investigation.

Abdominal aortic calcification is an independent predictor of cardiovascular events in peritoneal dialysis patients

Abdominal aortic calcification (AAC) is reported as a predictor for cardiovascular events in general population and in hemodialysis patients. At present, there are no AAC data in peritoneal dialysis. The purpose of this study was to evaluate the prognostic role of AAC score on cardiovascular events in peritoneal dialysis patients. Seventy-four peritoneal dialysis patients were enrolled. AAC was measured on baseline lateral abdomen radiographs by the semi-quantitative method as described by Kauppila. The other cardiovascular risk factors were obtained from patient history and blood examination. The Kaplan-Meier method was used to evaluate freedom from cardiovascular events, and differences were assessed with the log-rank statistic. Multivariate Cox regression models addressed time to cardiovascular events. The median period of follow-up was 30.5months (IQR 19.4-32.7). During follow-up, there were 29 cardiovascular events (39.2%). In univariable analysis, patient's age (HR=1.050; P=0.001), urine output (HR=0.999; P=0.02), and AAC stratified by tertiles (overall P-value<0.001) were significantly associated with cardiovascular events. In multivariable regression analysis, AAC score stratified by tertiles was the only independent predictor for cardiovascular events (overall P-value<0.001). To our knowledge, we have shown for the first time that AAC score is an independent predictor of cardiovascular events in peritoneal dialysis patients. Risk stratification by assessment of AAC score may provide important information for the management of cardiovascular disease in peritoneal dialysis patients without any additional expense, because these patients have several abdominal X-ray scans to evaluate the catheter position.

Predictors of long-term survival on peritoneal dialysis in South India: a multicenter study

BACKGROUND

Little is known about survival on peritoneal dialysis (PD) in Indian patients since the initiation of continuous ambulatory PD (CAPD) in India in 1991. Survival data from single centers with small numbers have been published.

OBJECTIVE

A retrospective 4-center analysis for predictors of survival >3 years in south Indian chronic PD patients.

METHODS

A total of 309 patients were trained during the observation period (from 1999 to 2004) and were analyzed in a multicenter study (4 centers), including 150 patients (male:female 109:41) that survived > or = 3 years and 59 patients that did not survive > or = 3 years (nonsurvivors; male: female 43:16) that were taken as controls. The patients were on chronic PD, predominantly CAPD, using double-bag disconnect systems. They were supervised by 4 nephrologists. Mean age in the nonsurvival group was 56.6 +/- 10.6 years. In the survival group, mean age was 50.9 +/- 14.9 years; there were 92 (62%) nondiabetics and 58 (38%) diabetics; the majority were nonvegetarians; 148 patients were doing 6 - 8 L exchanges and 2 were doing >8 L exchanges daily; 93 of 102 patients were average transporters based on peritoneal equilibration testing. At the beginning, mean combined Kt/V was 2.31 and weekly creatinine clearance was 73 L. Patients making one lifetime payment were 46% and 21% belonged to the full reimbursement group.

RESULTS

Body mass index (BMI) was normal in 114 patients (76%). Ultrafiltration volume was 1377 +/- 452 at the start and 1400 +/- 461 mL/day after 3 years. Anuric patients at the start were 12% and after 3 years 44%; urine output decreased from 527 +/- 26 to 253 +/- 14 mL/day from the start to after 3 years. Peritonitis rate was 1 episode/75 patient-months at the beginning and after 3 years it was 1 episode/30 patient-months. Exit-site care was done daily by 88% and 3 times weekly by 12%. Nonsmokers were 92% and smokers were 8%. Those that lived in the city were 62% and rural areas were 38%. Mean blood pressure was 143 +/- 16/88 +/- 10 and 136 +/- 18/85 +/- 9 mmHg, calcium x phosphorus product 44.6 +/- 15.6 and 45.9 +/- 15.7 mg(2)/dL(2), albumin 3.33 +/- 0.5 and 3.25 +/- 0.4 g/dL, hemoglobin 9.18 +/- 2 and 9.48 +/- 1.8 g/dL at the beginning and after 3 years, respectively. Statistical analysis showed a significant fall in both systolic (p < or = 0.001) and diastolic blood pressure (p < or = 0.05), an increase in BMI (p < or = 0.01), and a decrease in blood urea (p < or = 0.001) in the survival group. Those with Hb > or = 11 g/dL survived longer (p < or= 0.001), those with serum albumin > or = 3 g/dL had better survival (p = 0.001), and anuric patients survived longer (p = 0.001).

CONCLUSION

This multicenter cohort study of prevalent continuous PD patients in south India showed nondiabetics, average transporters, nonsmokers with reasonable nutritional status, with Hb 11 g/dL, with low peritonitis rate, with over 1 L ultrafiltration volume per day, the great majority that joined the once per lifetime payment scheme, and the reimbursement group survived for 3 years or longer.

Peritoneal dialysis is not associated with myocardial stunning

BACKGROUND

Hemodynamic changes during hemodialysis can precipitate subclinical myocardial ischemia, which over time contributes to the development of cardiac failure and is associated with a poor prognosis. Peritoneal dialysis (PD) is also associated with acute changes in systemic hemodynamics and a similarly high incidence of cardiovascular disease; we therefore sought to examine whether the hemodynamic effects of a PD exchange would be sufficient to induce subclinical myocardial ischemia.

METHODS

10 patients on PD entered a prospective observational study to determine whether left ventricular (LV) regional wall motion abnormalities (RWMAs) developed following a dialysate exchange. Serial echocardiography with quantitative analysis was used to assess ejection fraction and regional systolic LV function (shortening fraction). Blood pressure (BP) and hemodynamic variables were measured using continuous pulse wave analysis.

RESULTS

We observed a very low frequency of RWMA development (5/100 regions). Only 1 patient had more than 1 RWMA and 6 patients were entirely unaffected. Overall mean shortening fraction increased when comparing pre and post values for both 2-chamber (from 3.06% ± 1.5% to 4.26% ± 1.3%, p = 0.001) and 4-chamber (from 3.00% ± 0.7% to 3.67% ± 0.9%, p = 0.021) analyses. Mean arterial pressure fell by a small degree during drainage of dialysate, with a larger rise in BP observed during instillation. These changes were driven by changes in peripheral resistance that fell during drainage and rose during instillation.

CONCLUSIONS

In contrast to hemodialysis, the acute effects of PD do not result in subclinical myocardial ischemia.

Previous Comorbidity and Lack of Patient Free Choice of Technique Predict Early Mortality in Peritoneal Dialysis

Objective

To study the prognostic factors for mortality and hospital admission for patients on peritoneal dialysis (PD).

Method

Biannual data on individual characteristics, clinical and analytical progress, treatment, and events were studied for a cohort of incident patients undergoing PD (2003-2006) in a reference area of 8.8 million people.

Results

489 patients (age 53.58 years, 61.6% male) with 3-year follow-up were included. They presented at inclusion with Charlson Comorbidity Index (CCI) of 5.25; previous cardiovascular (CV) event, 23.7%; diabetes mellitus (DM), 19.1%; and hypertension (HT), 89.9%. Annual hospitalization rate per patient-year at risk was 0.6. The variables that predicted admission were CCI [odds ratio (OR) 1.14 per point], DM (OR 1.66), and previous CV event (OR 1.90). Anemia maintained significance when corrected for CCI: hemoglobin, 0.79 per 1 g/dL Hb; CCI, 1.15 per point. Annual mortality rate was 5.4%. Those that died were older (67.47 vs 52.78 years) and had a higher CCI (8.35 vs 5.0), a lower initial Hb (11.5 vs 12.2 g/dL), a higher hospital admission rate, a higher annual rate of peritonitis, more previous CV events (50.0% vs 22.1%), and higher prevalence of DM (38.5% vs 17.9%). Survival analysis identified the following prognostic factors: CCI [hazard ratio (HR) 1.51 per point], CV event (HR 2.85), DM (HR 2.52), age (HR 1.06 per year), and mandatory referral to PD (HR 6.54). The effect of CV events and DM persisted after correction for age, and that of choice of technique after correcting for CCI and/or age.

Conclusions

The CCI is useful for risk estimation in PD patients. Previous CV event, DM, and age are the most relevant risk factors. Control of anemia has prognostic value for hospital admissions. Mandatory referral to PD is associated with higher mortality. The prognosis in PD depends on predialysis patient management.

[News in peritoneal dialysis]

Peritoneal dialysis, like hemodialysis, is a first-line therapy for patients with end-stage renal disease. Progress in medical devices and materials has reduced infectious complications such as peritonitis and catheter exit-site infections and thus decreased morbidity. Peritoneal dialysis fluids are increasingly biocompatible, result in fewer glucose degradation products, protect the peritoneal membrane better and thus improve tolerance. The maintenance of residual renal function, together with better comfort and no pain, help control the fluid and sodium balance. Automated peritoneal dialysis can be performed each night, either autonomously or assisted by a visiting nurse twice a day (to prepare, connect, and disconnect the machine). This treatment can thus be provided to most patients, regardless of their age. Peritoneal dialysis is indicated principally for young people waiting for a kidney transplantation (to preserve their vascular network), elderly patients who wish to remain either at home or in an institution, and patients with cardiac insufficiency, because of the better hemodynamic tolerance. Numerous obstacles, mainly nonmedical, still impede the development of peritoneal dialysis. Patients seen in emergencies start hemodialysis without necessarily receiving any information about peritoneal dialysis. Indeed, neither physicians nor patients receive adequate information.