Overactive Bladder is a Distress Symptom in Heart Failure

Unsupervised Feature Selection to Identify Important ICD-10 and ATC Codes for Machine Learning on a Cohort of Patients With Coronary Heart Disease: Retrospective Study

Background

The application of machine learning in health care often necessitates the use of hierarchical codes such as the International Classification of Diseases (ICD) and Anatomical Therapeutic Chemical (ATC) systems. These codes classify diseases and medications, respectively, thereby forming extensive data dimensions. Unsupervised feature selection tackles the "curse of dimensionality" and helps to improve the accuracy and performance of supervised learning models by reducing the number of irrelevant or redundant features and avoiding overfitting. Techniques for unsupervised feature selection, such as filter, wrapper, and embedded methods, are implemented to select the most important features with the most intrinsic information. However, they face challenges due to the sheer volume of ICD and ATC codes and the hierarchical structures of these systems.

Objective

The objective of this study was to compare several unsupervised feature selection methods for ICD and ATC code databases of patients with coronary artery disease in different aspects of performance and complexity and select the best set of features representing these patients.

Methods

We compared several unsupervised feature selection methods for 2 ICD and 1 ATC code databases of 51,506 patients with coronary artery disease in Alberta, Canada. Specifically, we used the Laplacian score, unsupervised feature selection for multicluster data, autoencoder-inspired unsupervised feature selection, principal feature analysis, and concrete autoencoders with and without ICD or ATC tree weight adjustment to select the 100 best features from over 9000 ICD and 2000 ATC codes. We assessed the selected features based on their ability to reconstruct the initial feature space and predict 90-day mortality following discharge. We also compared the complexity of the selected features by mean code level in the ICD or ATC tree and the interpretability of the features in the mortality prediction task using Shapley analysis.

Results

In feature space reconstruction and mortality prediction, the concrete autoencoder-based methods outperformed other techniques. Particularly, a weight-adjusted concrete autoencoder variant demonstrated improved reconstruction accuracy and significant predictive performance enhancement, confirmed by DeLong and McNemar tests (P<.05). Concrete autoencoders preferred more general codes, and they consistently reconstructed all features accurately. Additionally, features selected by weight-adjusted concrete autoencoders yielded higher Shapley values in mortality prediction than most alternatives.

Conclusions

This study scrutinized 5 feature selection methods in ICD and ATC code data sets in an unsupervised context. Our findings underscore the superiority of the concrete autoencoder method in selecting salient features that represent the entire data set, offering a potential asset for subsequent machine learning research. We also present a novel weight adjustment approach for the concrete autoencoders specifically tailored for ICD and ATC code data sets to enhance the generalizability and interpretability of the selected features.

Relationship between body roundness index and the risk of heart failure in Chinese adults: the Kailuan cohort study

AIMS

Body roundness index (BRI) is an obesity-related anthropometric index that combines waist circumference and height to better reflect body fat. This study aims to prospectively explore the relationship between BRI and the risk of heart failure (HF) based on a community-based cohort.

METHODS AND RESULTS

A total of 140 362 individuals without tumour and HF at baseline were included from the Kailuan cohort study. Their demographic information, anthropometric parameters, and biochemical indexes were collected or measured. The participants were followed up until 31 December 2016 or death or diagnosed with HF, whichever came first. Cox proportional hazards model was used to calculate the hazard ratios (HRs) and 95% confidence intervals (CIs) for incident HF. Restricted cubic spline analysis was applied to further evaluate the possible non-linear dose-response relationship between BRI and the risk of HF. After a median follow-up period of 9.84 years, we identified 1990 HF events. The participants were grouped into four groups according to the quartiles of BRI (Q1: ≤2.93, Q2: 2.93-3.59, Q3: 3.59-4.38, and Q4: ≥4.38). After adjustment for potential confounders, compared with the group of participants in the lowest quartile of BRI, the adjusted HRs (95%CI) were 1.03 (95%CI: 0.87-1.22), 1.27 (95%CI: 1.07-1.49), and 1.50 (95%CI: 1.26-1.78) for subjects in the Q2, Q3, and Q4 groups, respectively. With each standard deviation (here is 1.10) of BRI increasing, the risk of HF increased by 18% (HR: 1.18, 95%CI: 1.12-1.24). Subgroup analysis indicated that the association between BRI and HF was more prominent in younger people (HR: 2.94, 95%CI: 1.80-4.80) than older (HR: 1.89, 95%CI: 1.57-2.27) (P for interaction < 0.001). A significant linear dose-response relationship between BRI and HF was also observed (P for non-linearity = 0.730).

CONCLUSIONS

Our study suggests that higher BRI is associated with an increased risk of HF. If these findings can be replicated in other populations, future studies need to examine whether lowering the BRI may lower the risk of incident HF.

Aging and Cardiovascular Disease: Current Status and Challenges

Cardiovascular disease (CVD) is the leading cause of death worldwide. Population aging is becoming the most important driver of the CVD epidemic. With the rapid increase in an aging population, the burden of CVD will continuously increase. Most old people also suffer multimorbidity, which is strongly associated with impaired quality of life, disability, dependence, and mortality. However, few reviews evaluated the CVD burden accompanied by population aging and the challenges of CVD care in elderly individuals with multimorbidity. This review identified and summarized the current status of the CVD epidemic associated with aging and highlighted the challenges and needs of CVD care for the elderly.

Physical multimorbidity and incident urinary incontinence among community-dwelling adults aged ≥50 years: findings from a prospective analysis of the Irish Longitudinal Study on Ageing

BACKGROUND

There are no prospective studies on the association between multimorbidity and urinary incontinence (UI), while mediators in this association are unknown. Thus, we aimed to (i) investigate the longitudinal association between multimorbidity and UI in a large sample of Irish adults aged ≥50 years and (ii) investigate to what extent physical activity, polypharmacy, cognitive function, sleep problems, handgrip strength and disability mediate the association.

METHODS

Data on 5,946 adults aged ≥50 years old from the Irish Longitudinal Study on Aging were analysed. The baseline survey was conducted between 2009 and 2011 and follow-up after 2 years was conducted. Information on self-reported occurrence of UI in the past 12 months and lifetime diagnosis of 14 chronic conditions were obtained. Multivariable logistic regression and mediation analysis were conducted.

RESULTS

After adjustment for potential confounders, compared to having no chronic conditions at baseline, having three (odds ratio [OR] = 1.79; 95% confidence interval [CI] = 1.30-2.48) and four or more (OR = 1.86; 95% CI = 1.32-2.60), chronic conditions were significantly associated with incident UI. Mediation analysis showed that polypharmacy, sleep problems and disability explained 22.7, 17.8 and 14.7% of the association between multimorbidity (i.e. two or more chronic conditions) and incident UI, respectively.

CONCLUSION

A greater number of chronic conditions at baseline were associated with a higher risk for incident UI at 2-year follow-up among adults aged ≥50 years in Ireland. Considering the effects of different medications on UI and improving sleep quality and disability among people aged ≥50 years with multimorbidity may reduce the incidence of UI.

Cardiovascular care of older adults

Age is an independent risk factor for cardiovascular disease. With the accelerated growth of the population of older adults, geriatric and cardiac care are becoming increasingly entwined. Although cardiovascular disease in younger adults often occurs as an isolated problem, it is more likely to occur in combination with clinical challenges related to age in older patients. Management of cardiovascular disease is transmuted by the context of multimorbidity, frailty, polypharmacy, cognitive dysfunction, functional decline, and other complexities of age. This means that additional insight and skills are needed to manage a broader range of relevant problems in older patients with cardiovascular disease. This review covers geriatric conditions that are relevant when treating older adults with cardiovascular disease, particularly management considerations. Traditional practice guidelines are generally well suited for robust older adults, but many others benefit from a relatively more personalized therapeutic approach that allows for a range of medical circumstances and idiosyncratic goals of care. This requires weighing of risks and benefits amidst the patient's aggregate clinical status and the ability to communicate effectively about this with patients and, where appropriate, their care givers in a process of shared decision making. Such a personalized approach can be particularly gratifying, as it provides opportunities to optimize an older patient's function and quality of life at a time in life when these often become foremost therapeutic priorities.

Effect of systemic atherosclerosis on overactive bladder symptoms in men with benign prostatic hyperplasia

OBJECTIVE

Symptoms of male overactive bladder (OAB) may be caused by several systemic pathophysiological factors rather than a single-source etiology. We investigated the clinical factors associated with the severity of OAB symptoms in treatment-naïve men with coexisting benign prostatic hyperplasia.

METHODS

We obtained records from a health promotion center database of male patients who visited between March 2019 and February 2020. Men without a history of treatment for lower urinary tract symptoms were evaluated using the International Prostate Symptom Score (IPSS), Overactive Bladder Symptom Score, transrectal ultrasonography, medical history, and carotid duplex ultrasound for the evaluation of atherosclerosis. Benign prostatic hyperplasia/lower urinary tract symptoms (BPH/LUTS) was defined as an IPSS of eight points or higher. Patients with comorbidities that may affect their voiding function were excluded.

RESULTS

A total of 764 patients were divided into two groups based on their diagnosis: an OAB group and a non-OAB group. The non-OAB group consisted of 627 patients (82.1%) and the OAB group consisted of 137 patients (17.9%). Using multivariable analysis BPH/LUTS was identified as an independent risk factor for OAB. In the OAB group without BPH/LUTS, carotid atherosclerosis was significantly associated with the severity of OAB symptoms. A history of diabetes mellitus was the only variable that was associated with the severity of urinary urgency. Systolic blood pressure was associated with severity of urinary urgency in the OAB group with BPH/LUTS.

CONCLUSIONS

Factors associated with male OAB exhibit different pathophysiology in the severity of symptoms depending on the presence of BPH/LUTS. Treatment for atherosclerosis and associated systemic pathophysiological factors could lower OAB symptom severity in male patients without BPH/LUTS.

Clinical Manifestations of Overactive Bladder With Migraine as a Comorbidity: A Prospective Cross-Sectional Study

Purpose

The aim of this study was to investigate the clinical manifestations of overactive bladder (OAB) with migraine as a comorbidity and to shed light on possible new treatment strategies.

Methods

This study included patients aged 18 years and older who were admitted to urology and neurology outpatient clinics between March 1, 2019 and March 1, 2020 for OAB and migraine. The study questionnaire contained 3 sections: (1) questions on demographic characteristics, (2) a migraine ID test, and (3) the Overactive Bladder Inquiry Form - V8 (OAB-V8) form.

Results

A total of 265 patients participated in the study. The average age of the participants was 39.75±11.93 years. The patients were divided into 3 groups according to the coexistence of OAB with migraine: group 1, OAB(+)/migraine(+); group 2, OAB(+)/migraine(-); and group 3, OAB(-)/migraine(+). The mean OAB-V8 score was 22.82 ±8.15 in group 1 and 25.64±7.49 in group 2. The mean OAB-V8 score of OAB patients with migraine as a comorbidity was statistically significantly lower than that of OAB patients without migraine (P=0.015). The median visual analogue scale (VAS) score was 7.11 (range, 2–10) in group 1 and 5.95 (range, 2–10) in group 3. This finding indicates that in patients with migraine, having OAB was associated with significantly higher VAS scores (P<0.001).

Conclusions

OAB and migraine may be comorbid conditions coexisting in a single patient. This comorbidity may lead to a lower perception of OAB symptoms in OAB patients or, conversely, to a higher perception of migraine pain. Further studies are needed to elucidate how treatments for each of these diseases can affect the other disease.

Evaluation and treatment of urinary incontinence in the aging male

Risk of urinary incontinence (UI) increases with age and can have detrimental effects on patients and caregivers. UI should not be considered a normal part of aging and warrants a comprehensive evaluation. Treatment of UI in the aging male requires special consideration, particularly when it comes to comorbid conditions and potential side effects of intervention. The aim of this review is to discuss the evaluation of, risk factors for, and management of UI in the aging male.

Seasonal Variation of Drug Prescription Rate for Overactive Bladder in Men Based on National Health Insurance Claims Data, 2012-2016

Purpose

Overactive bladder (OAB) symptoms might be affected by weather, but only a few clinical studies have investigated this issue. We investigated seasonal variations in OAB-drug prescription rate (DPR) in men using nationwide claims data in Korea.

Methods

A total of 2,824,140 men aged over 18 years were included from the Health Insurance Review and Assessment service – National Patient Sample data between 2012 and 2016. Depending on the monthly average temperature, the seasons were divided into 3 groups, namely, hot (June, July, August, and September), intermediate (April, May, October, and November), and cold (January, February, March, and December) seasons. OAB-DPR was estimated using the claims data, and differences in its rate were examined among the 3 seasonal groups.

Results

The overall OAB-DPR was 1.97% (55,574 of 2,824,140). The OAB-DPR were 0.38%, 0.63%, 0.92%, 1.74%, 4.18%, 7.55%, and 9.69% in the age groups of under 30, 30s, 40s, 50s, 60s, 70s, and over 80 years, respectively; thus, the prescription rate increased with age (P<0.001), with a steeper increase after 60 years of age. OAB-DPR was 1.02% in the hot season, 1.19% in the intermediate season, and 1.27% in the cold season, with significant differences among the 3 seasonal groups (P<0.001). These seasonal variations persisted in the subgroup analysis in each age decade (P<0.001).

Conclusions

OAB-DPR varied with seasons and was significantly higher in the cold season than in the hot season, suggesting that cold weather may affect development and aggravation of OAB symptoms in men.

A Novel Alternative in the Treatment of Detrusor Overactivity? In Vivo Activity of O-1602, the Newly Synthesized Agonist of GPR55 and GPR18 Cannabinoid Receptors

The aim of the research was to assess the impact of O-1602—novel GPR55 and GPR18 agonist—in the rat model of detrusor overactivity (DO). Additionally, its effect on the level of specific biomarkers was examined. To stimulate DO, 0.75% retinyl acetate (RA) was administered to female rats’ bladders. O-1602, at a single dose of 0.25 mg/kg, was injected intra-arterially during conscious cystometry. Furthermore, heart rate, blood pressure, and urine production were monitored for 24 h, and the impact of O-1602 on the levels of specific biomarkers was evaluated. An exposure of the urothelium to RA changed cystometric parameters and enhanced the biomarker levels. O-1602 did not affect any of the examined cystometric parameters or levels of biomarkers in control rats. However, the O-1602 injection into animals with RA-induced DO ameliorated the symptoms of DO and caused a reversal in the described changes in the concentration of CGRP, OCT₃, BDNF, and NGF to the levels observed in the control, while the values of ERK1/2 and VAChT were significantly lowered compared with the RA-induced DO group, but were still statistically higher than in the control. O-1602 can improve DO, and may serve as a promising novel substance for the pharmacotherapy of bladder diseases.