It was 1980 when Johnny Lee’s recording of ‘Lookin’ for Love (in all the wrong places)’ was released with the soundtrack of Urban Cowboy. In 1993, Dans paraphrased the title in ‘Looking for Answers in All the Wrong Places’ with an editorial that expounded on the discrepancies between a well-curated clinical data set and an ICD-9-CM (international classification of diseases, ninth revision, clinical modification) administrative data set.1 Responding to a report comparing clinical and administrative data to identify 12 straight-forward adult cardiovascular conditions, he added analyses and reinforced the conclusion reached by Jollis et al that, ‘Future studies should examine methods to improve the reliability of claims data, such as constructing clear, usable definitions for each condition, tying claims data collection more directly to the process of clinical care, and modifying coding guidelines to support a secondary goal of accurate clinical characterisation of patients’.2 Both the report and the editorial ring true decades later.3

Today we have ICD-10 with about 68 000 unique codes (rather than the paltry 13 000 ICD-9 codes). We have bigger and faster computers running more sophisticated computational analytics. We have more data sets. But to reuse another …