Research and Validation of a Big Data-Driven Intelligent Decision-Making System for Hemodialysis

Objectives and Scope:This observational study aims to leverage real-world data from Huashan Hospital to develop an AI-driven intelligent decision-making system for assessing dialysis adequacy in maintenance hemodialysis (MHD) patients, and to analyze early warning factors contributing to inadequate dialysis.

Core Research Question:Can an AI-based early warning and diagnostic model, built on multidimensional big data, identify the risk of inadequate hemodialysis at an ultra-early stage and accurately diagnose composite complications such as cardiovascular and cerebrovascular diseases? Methodology:The study will conduct a retrospective analysis of adult MHD patients treated at Huashan Hospital between January 2011 and September 2025. The dataset encompasses multidimensional variables, including sociodemographics, treatment parameters, laboratory indicators, metabolomics, and physical functions. Utilizing Dynamic Network Biomarkers (DNB) technology to screen for early warning markers, combined with artificial intelligence algorithms such as Neural Networks and Support Vector Machines (SVM), the study will construct two primary models: "Ultra-early Warning" and "Disease State Diagnosis." These models are designed to provide clinical decision support for precise interventions.

Study Overview

• Status: Completed
• Conditions: ESRD (End Stage Renal Disease)

Detailed Description

Research Background：End-stage renal disease (ESRD) represents the terminal stage of chronic kidney disease (CKD) progression. By 2020, the global ESRD population exceeded 12 million, with China accounting for nearly 30%, the highest in the world. Renal replacement therapy (RRT), including hemodialysis (HD), peritoneal dialysis (PD), and kidney transplantation, is the primary treatment for ESRD. Over 3.5 million patients worldwide receive maintenance dialysis, 90% of whom undergo HD. According to the Chinese National Renal Data System (CNRDS), the total number of dialysis patients in China approached 1 million in 2022, with maintenance hemodialysis (MHD) patients reaching 840,000-a 3.5-fold increase from 2012. Addressing the rapid growth in dialysis demand by improving medical quality and promoting social reintegration has become a global healthcare priority.Dialysis adequacy is a critical survival indicator for MHD patients. Currently, clinical practice relies on the Urea Reduction Ratio (URR) and Kt/V to assess adequacy. However, the 2002 HEMO study demonstrated that high-flux dialysis based on Kt/V did not improve survival rates. Consequently, existing metrics are criticized for failing to reflect the clearance of middle-molecule toxins and lacking a direct correlation with clinical outcomes, quality of life, and long-term prognosis. Identifying which indicators and computational models best assess dialysis adequacy remains an unresolved challenge in nephrology.Recently, advancements in Artificial Intelligence (AI) have offered new research avenues for assessing dialysis adequacy. Since 2005, studies using Artificial Neural Networks (ANN) and various machine learning (ML) models-including Decision Trees (DT), Random Forest (RF), Support Vector Machines (SVM), and Extreme Gradient Boosting (XGBoost)-have demonstrated superior predictive performance (AUROC up to 0.874) compared to traditional linear regression and formulas (e.g., Smye, Daugirdas). Despite this progress, existing studies often lack comprehensive variables such as dietary nutrition, neuropsychiatric status, and physical function. Furthermore, most current models are "diagnostic" in nature-identifying differences between stable "normal" and "diseased" states-making them suitable for diagnosis but insufficient for early intervention.Therefore, this retrospective study leverages real-world data (RWD) from Huashan Hospital to identify early warning factors for inadequate dialysis. The investigators aim to construct an "Ultra-early AI Warning Model" and an "AI Diagnostic Model" to form an Intelligent Decision-Making System for Hemodialysis, providing precise clinical intervention recommendations.

• Study Type: Observational
• Enrollment (Actual): 778

Contacts and Locations

Study Locations

• China
  • Shanghai Municipality
    • Shanghai, Shanghai Municipality, China, 200040
      • Huashan Hospital, Fudan University

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

The study population consists of patients receiving maintenance hemodialysis at the Hemodialysis Center of Huashan Hospital between January 2011 and September 2025. Eligibility criteria require patients to be aged 18-90 years with a dialysis vintage of at least 3 months. Additionally, participants must have comprehensive clinical and follow-up data maintained within the center's electronic medical record system.

Description

Inclusion Criteria:

• Patients undergoing long-term maintenance hemodialysis with a dialysis vintage of at least 3 months.
• Aged between 18 and 90 years.
• Possess relatively comprehensive hemodialysis records maintained within this center.

Exclusion Criteria:

• Patients with significantly incomplete dialysis-related data.
• Patients with poor compliance during dialysis or those receiving palliative dialysis.
• Other conditions deemed unsuitable by the investigator.

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort

Patients undergoing hemodialysis at this center from January 2011 to September 2025.; Information will be retrospectively collected from patients who underwent hemodialysis at this center between January 2011 and September 2025. Data are primarily sourced from electronic information systems, including the Hemodialysis Electronic Management System, the hospital Health Information System (HIS), and the Inpatient Medical Record System. The dataset encompasses personal information, laboratory results, diagnostic data, medical orders, and nutritional status.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Cardiovascular and Cerebrovascular Diseases (CCVD)	Clinicians diagnose these conditions based on the American Heart Association (AHA) professional guidelines and diagnostic criteria.	15 years (From January 2011 to September 2025)

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Composite Complications	Composite outcome including Protein-Energy Wasting (PEW), Mineral and Bone Disorder (MBD), anemia, infection, and tumors. PEW is diagnosed based on the International Society of Renal Nutrition and Metabolism (ISRNM) criteria. MBD and anemia are diagnosed following the clinical guidelines from Kidney Disease: Improving Global Outcomes (KDIGO), the Japanese Society for Dialysis Therapy (JSDT), or the Japanese Society of Nephrology (JSN). Severe infection is diagnosed according to the Systemic Inflammatory Response Syndrome (SIRS) criteria. Tumors are identified based on clinical diagnoses by physicians.	15 years (From January 2011 to September 2025)

Collaborators and Investigators

• Sponsor: Huashan Hospital
• Investigators: Principal Investigator: Jing Chen, Huashan Hospital

Study record dates

Study Major Dates

• Study Start (Actual): January 1, 2011
• Primary Completion (Actual): September 30, 2025
• Study Completion (Actual): September 30, 2025

Study Registration Dates

• First Submitted: March 8, 2026
• First Submitted That Met QC Criteria: March 8, 2026
• First Posted (Actual): March 12, 2026

Study Record Updates

• Last Update Posted (Actual): March 17, 2026
• Last Update Submitted That Met QC Criteria: March 14, 2026
• Last Verified: January 1, 2026

More Information

Terms related to this study

• Keywords: End-Stage Renal Disease; Maintenance Hemodialysis
• Additional Relevant MeSH Terms: Urogenital Diseases; Pathologic Processes; Male Urogenital Diseases; Kidney Diseases; Urologic Diseases; Female Urogenital Diseases; Female Urogenital Diseases and Pregnancy Complications; Chronic Disease; Disease Attributes; Renal Insufficiency; Pathological Conditions, Signs and Symptoms; Kidney Failure, Chronic; Renal Insufficiency, Chronic
• Other Study ID Numbers: KY2025-1424

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No