Efficacy of Remote Pulmonary Artery Hemodynamic Monitoring System in Reducing Hospital Encounters in Heart Failure Patients With Chronic Kidney Disease

Computational Models Used to Predict Cardiovascular Complications in Chronic Kidney Disease Patients: A Systematic Review

“…Eleven studies are single-center. Of the 11 single-center studies, six papers use datasets with patients from the US [21][22][23][24][25][26], three papers include individuals from Spain [27][28][29], one article includes patients from Korea [30], and one paper includes patients from Portugal [31]. Three of the eleven single-center studies [25,28,29] proposed ML and regression models based on the CRIC (Chronic Renal Insufficiency Cohort Study) [32] or NEFRONA [33] study cohorts.…”

“…Of the included studies, seven papers developed AI/ML models to predict single CV endpoints concerning the most frequent and vital CVC in CKD (SCD, IHD, HF, and arrhythmias). The proposed models predict SCD in hemodialysis patients [39,40], IHD, HF, or arrhythmias in hemodialysis patients [40]; prognostic proteins associated with HF in CKD [21]; death risk in ESRD patients with congestive HF [22]; HF admissions in individuals with CKD [23]; the safety and efficiency of low-dose angiotensin-convertingenzyme inhibitors (ACEIs) and angiotensin II receptor blockers (ARBs) in CKD patients with HF and reduced ejection fraction [24]; and incident atrial fibrillation (AF) in CKD patients without prior AF [25].…”

“…Akbilgic et al [22] had a high adherence to TRIPOD criteria (75%), while Gowda et al [23], Dubin et al [21], and Ahmed et al [24] had poor adherences, with less than 30% of the criteria met. Akbilgic et al [22] used an impressive dataset of 14,800 patients, whereas Gowda et al [23] included data from only 117 patients. The CRIC study [48] proved that ejection fractions significantly decline during more advanced stages of CKD.…”

“…Fourth, automated learning methods dealing with HF predictions in CKD explore the potential of AI solutions to predict not only the risk of incident HF [21,23,40] but also the outcomes of HF [22] and the effectiveness of standard therapies in the particular CKD setting [24]. Models to predict long-term risk of HF in hemodialysis patients using SVM [40] or HF admissions in patients with CKD based on remote IoT (Internet of Things) sensors [23] have been described. Additionally, to assess the risk of occurrence, a model identifies prognostic proteins associated with HF in CKD by random survival forest regression [21].…”

“…An ongoing clinical trial uses AI/ML-based methods to predict the safety and efficiency of low-dose ACEIs and ARBs in CKD patients with HF and reduced ejection fraction [24]. Akbilgic et al [22] had a high adherence to TRIPOD criteria (75%), while Gowda et al [23], Dubin et al [21], and Ahmed et al [24] had poor adherences, with less than 30% of the criteria met. Akbilgic et al [22] used an impressive dataset of 14,800 patients, whereas Gowda et al [23] included data from only 117 patients.…”