Implementation of a scalable, web-based, automated clinical decision support risk-prediction tool for chronic kidney disease using C-CDA and application programming interfaces

Abstract

We validated the use of interoperable documents and open-source components to develop a low-cost tool for automated clinical decision support. Since Consolidated Clinical Document Architecture-based data extraction extends to any certified EHR, this demonstrates a successful modular approach to clinical decision support.

Promises of Big Data and Artificial Intelligence in Nephrology and Transplantation

“…In addition, regarding utilization of ANN and CNN methods, Kolachalama et al [76] recently provided a perspicacity into the association of pathological fibrosis identified from histologic images with clinical phenotypes for patients with CKD, helping the diagnostics and prognostics of these phenotypes. Subsequently, there has been an increasing number of AI studies, with great emphasis on the usage of nephrology and transplantation [85,[87][88][89]. Inspired by the idea of mimicking the biological structure of human brains, deep learning is a subfield of machine learning based on ANN [74].…”

Big data in nephrology: Are we ready for the change?

“…A recent study showed that an automated laboratory‐based CDSS might help to improve physician adherence to guidelines regarding timely monitoring of CKD . Samal et al . have built a modern web‐based CDSS to calculate the risk of kidney failure and display it for CKD patients, and the inputs of the system are real‐time patient data.…”

“…34 A recent study showed that an automated laboratory-based CDSS might help to improve physician adherence to guidelines regarding timely monitoring of CKD. 35 Samal et al 36 have built a modern web-based CDSS to calculate the risk of kidney failure and display it for CKD patients, and the inputs of the system are real-time patient data. However, the sample sizes of aforementioned studies cannot satisfy the "volume" of big data, and the representativeness of samples in those studies needs to be verified.…”

“…In conclusion, problem-driven big data research in nephrology is important for promoting the interdisciplinary 10 and CKD progression [28][29][30] • To build a CKD surveillance system and collaborative network nationally or globally: surveillance systems based on existing databases; international collaborative network through sharing data and research outputs • To build real-world cohorts in a cost-effective manner: design and implementation of large cohorts and pragmatic randomized controlled trials Clinical practice, innovation and decision-making • Risk prediction and clinical decision support: risk prediction of CKD and end-stage kidney disease using machine learning and natural language processing 33,35,36 • Management of acute kidney injury: detection, classification, and automated alerting of acute kidney injury [40][41][42] • To strengthen the application and transformation of artificial intelligence and big data based CDSS: collaboration with computer and data scientists; improvement of interpretability and usability of CDSS • To stimulate the activeness of medical imaging: analysis of renal biopsy images and urine formed elements using machine learning CDSS, clinical decision support systems; CKD, chronic kidney disease; PM 2.5 , fine particulate matter of <2.5 μm in aerodynamic diameter; PM 10 , coarse particulate matter of <10 μm in aerodynamic diameter.…”

Interoperability: What Is It, How Can We Make It Work for Clinicians, and How Should We Measure It in the Future?

“…For example, in a project where we extracted numeric estimated glomerular filtration rates and numeric urine albumin‐to‐creatinine ratios, our laboratory information system output nonstandard text strings for “>60” and “Below Assay”(Samal et al. ).…”