JMIR Publications

ABSTRACT

Background:

Continuously growing medical knowledge and the increasing amount of data make it difficult for medical professionals to keep track of all new information, and to place this in context of existing information. Digital technologies and artificial intelligence (AI)- based methods have recently emerged as impressively persuasive tools to empower physicians in clinical decision making and improve healthcare quality. A novel DDSS prototype, developed with a focus on traceability, transparency and usability by Ada Health GmbH will be examined more closely in this study.

Objective:

Feasibility and functionality test of a novel DDSS prototype, exploring the potential and performance to identify the underlying cause of acute dyspnea in patients at the University Hospital Basel.

Methods:

A prospective, observational feasibility study was conducted at the Emergency Department (ED) and Internal Medicine ward of the University Hospital Basel Switzerland. A convenience sample of 20 adult patients entering the ED with dyspnea as the chief complaint and a high probability for inpatient admission were selected. A study physician followed the patients admitted to the ED through the hospitalisation without any interference with the routine clinical work. Routinely collected, health-related, personal data from those patients were entered in the DDSS prototype. The DDSS prototype’s resulting disease probability list was compared with the gold standard main diagnosis provided by the treating physician. A panel of three physicians with different levels of clinical experience and expertise evaluated the matching diagnoses from the hospital and from the DDSS prototype.

Results:

The study of the feasibility and functionality of the tool was successful with some limitations. The DDSS had high clarity of information presentation and a user-friendly, novel and transparent interface. The DDSS prototype was not perfectly suited for the emergency department because case entry was time consuming. It provided accurate decision support in the clinical inpatient setting in many patients with dyspnea as a main presenting complaint.

Conclusions:

Used in the right place, the DDSS has the potential to support doctors in their decision-making process by showing new pathways and unintentionally ignored diagnoses. The DDSS prototype had some limitations regarding the process of data input, diagnostic accuracy and the completeness of integrated medical knowledge. The results of this study provide a basis for the tool’s further development. Additionally future studies should be conducted with the aim to overcome the tool’s and study design’s present limitations. Clinical Trial: clinicaltrials.gov RN: NCT04827342