Chris Kelman

OBJECTIVE: To investigate the time relations between long haul air travel and venous thromboembolism. DESIGN: Record linkage study using the case crossover approach. SETTING: Western Australia. PARTICIPANTS: 5408 patients admitted to hospital with venous thromboembolism and matched with data for arrivals of international flights during 1981-99. RESULTS: The risk of venous thromboembolism is increased for only two weeks after a long haul flight; 46 Australian citizens and 200 non-Australian citizens had an episode of venous thromboembolism during this so called hazard period. The relative risk during this period for Australian citizens was 4.17 (95% confidence interval, 2.94 to 5.40), with 76% of cases (n = 35) attributable to the preceding flight. A "healthy traveller" effect was observed, particularly for Australian citizens. CONCLUSIONS: The annual risk of venous thromboembolism is increased by 12% if one long haul flight is taken yearly. The average risk of death from flight related venous thromboembolism is small compared with that from motor vehicle crashes and injuries at work. The individual risk of death from flight related venous thromboembolism for people with certain pre-existing medical conditions is, however, likely to be greater than the average risk of 1 per 2 million for passengers arriving from a flight. Airlines and health authorities should continue to advise passengers on how to minimise risk.

In various real-world applications, it is very useful mining unanticipated episodes where certain event patterns unexpectedly lead to outcomes, e.g., taking two medicines together sometimes causing an adverse reaction. These unanticipated episodes are usually unexpected and infrequent, which makes existing data mining techniques, mainly designed to find frequent patterns, ineffective. In this paper, we propose unexpected temporal association rules (UTARs) to describe them. To handle the unexpectedness, we introduce a new interestingness measure, residual-leverage, and develop a novel case-based exclusion technique for its calculation. Combining it with an event-oriented data preparation technique to handle the infrequency, we develop a new algorithm MUTARC to find pairwise UTARs. The MUTARC is applied to generate adverse drug reaction (ADR) signals from real-world healthcare administrative databases. It reliably shortlists not only six known ADRs, but also another ADR, flucloxacillin possibly causing hepatitis, which our algorithm designers and experiment runners have not known before the experiments. The MUTARC performs much more effectively than existing techniques. This paper clearly illustrates the great potential along the new direction of ADR signal generation from healthcare administrative databases.

In this paper, we discuss a problem of finding risk patterns in medical data. We define risk patterns by a statistical metric, relative risk, which has been widely used in epidemiological research. We characterise the problem of mining risk patterns as an optimal rule discovery problem. We study an anti-monotone property for mining optimal risk pattern sets and present an algorithm to make use of the property in risk pattern discovery. The method has been applied to a real world data set to find patterns associated with an allergic event for ACE inhibitors. The algorithm has generated some useful results for medical researchers.