Health economic benefits through the use of diagnostic support systems and expert knowledge

BACKGROUND

Rare diseases are difficult to diagnose. Due to their rarity, heterogeneity, and variability, rare diseases often result not only in extensive diagnostic tests and imaging studies, but also in unnecessary repetitions of examinations, which places a greater overall burden on the healthcare system. Diagnostic decision support systems (DDSS) optimized by rare disease experts and used early by primary care physicians and specialists are able to significantly shorten diagnostic processes. The objective of this study was to evaluate reductions in diagnostic costs incurred in rare disease cases brought about by rapid referral to an expert and diagnostic decision support systems.

METHODS

Retrospectively, diagnostic costs from disease onset to diagnosis were analyzed in 78 patient cases from the outpatient clinic for rare inflammatory systemic diseases at Hannover Medical School. From the onset of the first symptoms, all diagnostic measures related to the disease were taken from the patient files and documented for each day. The basis for the health economic calculations was the Einheitlicher Bewertungsmaßstab (EBM) used in Germany for statutory health insurance, which assigns a fixed flat rate to the various medical services. For 76 cases we also calculated the cost savings that would have been achieved by the diagnosis support system Ada DX applied by an expert.

RESULTS

The expert was able to achieve significant savings for patients with long courses of disease. On average, the expert needed only 27 % of the total costs incurred in the individual treatment odysseys to make the correct diagnosis. The expert also needed significantly less time and avoided unnecessary examination repetitions. If a DDSS had been applied early in the 76 cases studied, only 51-68 % of the total costs would have incurred and the diagnosis would have been made earlier. Earlier diagnosis would have significantly reduced costs.

CONCLUSION

The study showed that significant savings in the diagnostic process of rare diseases can be achieved through rapid referral to an expert and the use of DDSS. Faster diagnosis not only achieves savings, but also enables the right therapy and thus an increase in the quality of life for patients.

A Learning Health Care System Using Computer-Aided Diagnosis

Physicians intuitively apply pattern recognition when evaluating a patient. Rational diagnosis making requires that clinical patterns be put in the context of disease prior probability, yet physicians often exhibit flawed probabilistic reasoning. Difficulties in making a diagnosis are reflected in the high rates of deadly and costly diagnostic errors. Introduced 6 decades ago, computerized diagnosis support systems are still not widely used by internists. These systems cannot efficiently recognize patterns and are unable to consider the base rate of potential diagnoses. We review the limitations of current computer-aided diagnosis support systems. We then portray future diagnosis support systems and provide a conceptual framework for their development. We argue for capturing physician knowledge using a novel knowledge representation model of the clinical picture. This model (based on structured patient presentation patterns) holds not only symptoms and signs but also their temporal and semantic interrelations. We call for the collection of crowdsourced, automatically deidentified, structured patient patterns as means to support distributed knowledge accumulation and maintenance. In this approach, each structured patient pattern adds to a self-growing and -maintaining knowledge base, sharing the experience of physicians worldwide. Besides supporting diagnosis by relating the symptoms and signs with the final diagnosis recorded, the collective pattern map can also provide disease base-rate estimates and real-time surveillance for early detection of outbreaks. We explain how health care in resource-limited settings can benefit from using this approach and how it can be applied to provide feedback-rich medical education for both students and practitioners.