ACCESS-CM

ACCESS-CM
Name	ACCESS-CM
Type	Clinical decision support / monitoring system
Developer	Consortium of academic centers and industry partners
First release	2019
Latest release	2024
Operating system	Cross-platform

ACCESS-CM

ACCESS-CM is a clinical analytics and decision-support system designed for real-time continuous monitoring and management of cardiometabolic conditions in inpatient and outpatient settings. It integrates physiologic data streams, laboratory results, and pharmacologic records to provide predictive alerts, therapeutic suggestions, and longitudinal reporting for clinicians across hospitals, clinics, and research networks. The platform emphasizes interoperability with electronic health records, device ecosystems, and registries to enable care coordination, quality measurement, and outcomes research.

Overview

ACCESS-CM functions as an interoperable clinical tool that ingests data from bedside monitors, ambulatory devices, laboratory information systems, and pharmacy records to produce actionable intelligence for acute and chronic cardiometabolic care. It connects to systems and institutions such as Mayo Clinic, Cleveland Clinic, Johns Hopkins Hospital, Massachusetts General Hospital, Stanford Health Care, Mount Sinai Hospital, UCLA Health, NYU Langone Health, Kaiser Permanente, Geisinger Health System, Partners HealthCare, Cedars-Sinai Medical Center, University of Pennsylvania Health System, University of California, San Francisco Medical Center, Duke University Hospital, Brigham and Women's Hospital, Vanderbilt University Medical Center, Northwestern Memorial Hospital, Providence Health & Services, Intermountain Healthcare, Baylor Scott & White Health, University of Michigan Hospitals, Ohio State University Wexner Medical Center, University of Washington Medical Center, Mount Sinai Health System, Rush University Medical Center, Penn Medicine, CHOP, Children's Hospital of Philadelphia and regional networks to support coordinated management. The system supports guideline-aligned interventions consistent with recommendations from organizations such as the American Heart Association, American Diabetes Association, European Society of Cardiology, National Institutes of Health, Centers for Disease Control and Prevention, World Health Organization, National Institute for Health and Care Excellence, and specialty societies like the Endocrine Society.

History and Development

Development of ACCESS-CM began in collaborations among academic centers, technology firms, and healthcare consortia following initiatives to modernize clinical surveillance and chronic disease management. Early pilot work involved partnerships with institutions like Harvard Medical School, Yale School of Medicine, Columbia University Irving Medical Center, University of Oxford, Imperial College London, Karolinska Institutet, University of Toronto, McMaster University, University of Melbourne, Monash University, University of Sydney, and research funding from agencies including National Science Foundation, European Commission, Wellcome Trust, and Medical Research Council. Prototype evaluations were presented at conferences such as American College of Cardiology Annual Scientific Session, European Association for the Study of Diabetes, American Diabetes Association Scientific Sessions, and Heart Rhythm Society Scientific Sessions. Iterative refinement incorporated feedback from clinical trials and quality collaboratives led by organizations like Agency for Healthcare Research and Quality, PCORI, and national registries including Get With The Guidelines and National Cardiovascular Data Registry.

Design and Technical Specifications

The architecture of ACCESS-CM is modular, with data ingestion, analytics, decision-support, and visualization layers. It supports standards such as Health Level Seven International (HL7) FHIR, DICOM, LOINC, SNOMED CT, ICD-10, and RxNorm to interoperate with vendors like Epic Systems Corporation, Cerner Corporation, Allscripts, McKesson, GE Healthcare, Philips Healthcare, Siemens Healthineers, Medtronic, Abbott Laboratories, Dexcom, Abbott FreeStyle Libre, Fitbit, Apple Watch, Samsung Health, and device manufacturers used in telemetry. Core analytics use validated algorithms derived from published models originating in studies by investigators at Framingham Heart Study, UK Biobank, CARDIA, ARIC, SPRINT, and ADVANCE; machine learning modules leverage frameworks associated with TensorFlow, PyTorch, and scalable cloud platforms from Amazon Web Services, Google Cloud Platform, and Microsoft Azure. Security and privacy adhere to regulatory frameworks such as Health Insurance Portability and Accountability Act, General Data Protection Regulation, and standards promulgated by National Institute of Standards and Technology.

Clinical Applications and Use Cases

ACCESS-CM supports inpatient telemetry escalation, outpatient risk stratification, medication optimization, and population health monitoring. Use cases include early detection of acute coronary syndromes, decompensated heart failure alerts, glycemic excursion identification in diabetes, antihyperglycemic and antihypertensive titration support, lipid management, perioperative cardiometabolic risk assessment, and remote patient monitoring for transitional care. Implementations have been trialed in contexts including cardiovascular intensive care units at St. Thomas' Hospital, ambulatory diabetes clinics at Joslin Diabetes Center, heart failure clinics at Cleveland Clinic Heart Center, and remote monitoring programs coordinated with insurers like UnitedHealthcare and Aetna.

Safety, Efficacy, and Regulatory Status

Safety evaluations for ACCESS-CM have included retrospective validation against registries such as Get With The Guidelines–Heart Failure and prospective pragmatic trials registered with ClinicalTrials.gov. Performance metrics reported include sensitivity, specificity, positive predictive value, and impact on process measures like time-to-intervention, readmission rates, and medication adherence. Regulatory engagement has occurred with agencies such as the U.S. Food and Drug Administration, European Medicines Agency, Medicines and Healthcare products Regulatory Agency, and national health technology assessment bodies; components delivering autonomous recommendations are subject to medical device classification and clearance processes consistent with regional regulations.

Deployment and Implementation

Deployment models range from cloud-hosted services integrated with enterprise EHRs to on-premises installations for health systems requiring local control. Implementation pathways involve clinical workflow mapping with stakeholders including chief medical officers, informatics teams, pharmacy services, cardiology divisions, endocrinology services, nursing leadership, and allied health professionals. Training and change management leverage curricula and certification programs modeled on continuing medical education frameworks endorsed by American Medical Association, Royal College of Physicians, and specialty boards. Monitoring of real-world performance uses quality improvement frameworks developed by Institute for Healthcare Improvement and audit cycles aligned with payer reporting requirements.

Future Directions and Research

Research priorities include enhanced multimodal prediction combining genomics resources such as ClinVar and 1000 Genomes Project with imaging from Cardiac MRI and wearable biosensors, prospective randomized trials comparing ACCESS-CM–guided care to usual care across diverse populations, and integration with value-based payment models promoted by Centers for Medicare & Medicaid Services and international health services. Emerging collaborations aim to link the platform with large-scale initiatives like All of Us Research Program, UK Biobank, Million Veteran Program, European Prospective Investigation into Cancer and Nutrition, and precision-medicine consortia to refine individualized risk estimates and therapeutics.

Category:Clinical decision support systems