Modulation of Medical Condition Likelihood by Patient History Similarity

INTRODUCTION

We describe an analysis that modulates the simple population prevalence derived likelihood of a particular condition occurring in an individual by matching the individual with other individuals with similar clinical histories and determining the prevalence of the condition within the matched group.

METHODS

We have taken clinical event codes and dates from anonymised longitudinal primary care records for 25,979 patients with 749,053 recorded clinical events. Using a nearest neighbour approach, for each patient, the likelihood of a condition occurring was adjusted from the population prevalence to the prevalence of the condition within those patients with the closest matching clinical history.

RESULTS

For conditions investigated, the nearest method performed well in comparison with standard logistic regression.

CONCLUSIONS

Results indicate that it may be possible to use histories to identify 'similar' patients and thus to modulate future likelihoods of a condition occurring.

Terminology, units and reporting - how harmonized do we need to be?

Harmonization initiatives in laboratory medicine seek to eliminate or reduce illogical variations in service to patients, clinicians and other healthcare professionals. Significant effort will be required to achieve consistent application of terminology, units and reporting across laboratory testing providers. Current variations in practice for nomenclature, reference intervals, flagging, units, standardization and traceability between analytical methods, and presentation of cumulative result data are inefficient and inconvenient, or worse yet, patient safety risks. All aspects of laboratory service across the "total testing process" ultimately depend on concise, reliable communication. Clinical terminologies (e.g. SNOMED-CT, LOINC, IFCC/IUPAC NPU) provide a mechanism to correctly identify an analyte or panel of tests within a request for testing and communicate the results back to the clinician or electronic health record (EHR). Electronic systems for requesting and reporting laboratory testing are said to be interoperable when reliable connection and communication of content occur. Modern electronic reports and EHRs will provide greater flexibility and functionality, but also require effective guidelines or standards to ensure consistent representation of laboratory data. Programs to harmonize service in these areas require ongoing local, national and international efforts and should incorporate stakeholders from laboratories, medical staff, information technology and informatics specialists, patient representatives and government. The process of identifying harmonized best practice, then ensuring uptake across many laboratory testing providers, is generally iterative rather than "one off". New opportunities for additional harmonization will be generated as analytical performance, standardization and traceability, and diagnosis and treatment continue to evolve.

A New Era in Clinical Communications: A Report on the Past Year's Work at NEHTA

Across Australia there is a groundswell of support for a better more connected healthcare system. More than 80 per cent of Australians are in favour of electronic health records and the sector is increasingly aware of the safety and quality benefits that e-health can deliver. On behalf of the governments of Australia, the National E-Health Transition Authority (NEHTA) is developing a national e-health infrastructure that will underpin the success of a connected healthcare system. This involves a body of work that includes clinical terminologies, unique healthcare identification and the development and recommendation of standards for the safe transmission and access of healthcare information. Read an update of NEHTA's work and progress in 2008.