Pretreatment data is highly predictive of liver chemistry signals in clinical trials.

PURPOSE: The goal of this retrospective analysis was to assess how well predictive models could determine which patients would develop liver chemistry signals during clinical trials based on their pretreatment (baseline) information. PATIENTS AND METHODS: Based on data from 24 late-stage clinical trials, classification models were developed to predict liver chemistry outcomes using baseline information, which included demographics, medical history, concomitant medications, and baseline laboratory results. RESULTS: Predictive models using baseline data predicted which patients would develop liver signals during the trials with average validation accuracy around 80%. Baseline levels of individual liver chemistry tests were most important for predicting their own elevations during the trials. High bilirubin levels at baseline were not uncommon and were associated with a high risk of developing biochemical Hy's law cases. Baseline γ-glutamyltransferase (GGT) level appeared to have some predictive value, but did not increase predictability beyond using established liver chemistry tests. CONCLUSION: It is possible to predict which patients are at a higher risk of developing liver chemistry signals using pretreatment (baseline) data. Derived knowledge from such predictions may allow proactive and targeted risk management, and the type of analysis described here could help determine whether new biomarkers offer improved performance over established ones.

National differences in reporting 'pneumonia' and 'pneumonia interstitial': an analysis of the WHO International Drug Monitoring Database on 15 drugs in nine countries for seven pulmonary conditions.

PURPOSE: Increased post-marketing reports of 'interstitial pneumonia' as an adverse drug reaction (ADR) from the use of gefitinib, irinotecan, or leflunomide among patients in Japan have not been noted in other countries. The WHO International Drug Monitoring Database was analyzed to examine Japan's pattern of reporting the term 'pneumonia interstitial' for 15 selected drugs with a mixed history of association with pulmonary ADRs. METHODS: ADR counts from the WHO Database for 1992-2001 were obtained for 15 disparate drugs (three androgen blockers, eight cytotoxics, one proton pump inhibitor, one monoclonal antibody, and two anti-epileptics) from nine countries (Australia, France, Germany, Italy, Japan, Spain, Thailand, U.K., and U.S.A.) for seven pulmonary ADR terms (alveolitis fibrosing, pneumonia, pulmonary fibrosis, lung fibrosis interstitial, pulmonary infiltration, interstitial lung disease, and pneumonia interstitial). Statistical analyses included estimating Poisson-distributed expected rates, observed/expected (O/E) ratios, and 95% confidence intervals (CI). The overlapping nature and changes in definition over time of these terms in medical texts and in the WHO-ART, COSTART, J-ART, and MedDRA coding systems is also noted. RESULTS: Compared to other countries, both Japan and France did not have higher O/E reporting ratios for all seven pulmonary ADRs combined, but did have higher O/E ratios for 'pneumonia interstitial' and lower O/E ratios for 'pneumonia' for the same drugs. CONCLUSIONS: Japan and France were found to preferentially use the term 'pneumonia interstitial' for ADR where other countries used 'pneumonia.' This cultural pattern coincides with the fact that 'pneumonia interstitial' in older versions of COSTART, J-ART, and MedDRA were subsumed under infectious pulmonary diseases.