Deliberate self-harm: Case identification and incidence estimate upon data from national patient registry

Background Patient registry is a valuable source for identification of deliberate self-harm (DSH) incidents on a population basis; however, little research has provided sufficient details that could inform best utilization of this complicated data source for DSH research and statistics. In this study we want to use data from the Norwegian Patient Register to delineate a diagnostic coding system to identify medically treated DSH incidents, to profile general characteristics of these incidents, and to estimate incidence rate of DSHs in the national population of Norway. Methods We obtained all records of patient contacts to somatic hospitals and emergency centers due to external causes from 2008 through 2013. For each contact, we retrieved clinical data on primary and comorbid diagnoses, urgency of contact, etc., alongside with personal general information. After careful mining, the data were further processed following a multi-step analytic strategy. Descriptive analysis was used to profile DSH incidents and to estimate incidence rates and corresponding 95% confidence intervals. Findings From 1 459 384 eligible incident contacts for emergency injury treatment, we identified 13 533 incidents that had a recorded diagnosis of DSH, i.e., with a supplemental code of X6n. Upon delineation of these recorded DSHs, we devised a diagnostic coding system to identify all possible DSH incidents. This yielded a total of 38 433 incidents to be considered as likely incidents of DSH (adjusted incidents)-a number that is 2.84 times higher than that of the recorded DSH incidents during the study period. While the proposed diagnostic system captured more incidents by males and old adults, the adjusted DSHs remained more common in females than males, and occurred most frequently within young people of 18-21 years. These incidents imply about 6400 DSH incidents from 5100 persons per year and correspond to a yearly cumulative incidence rate of 121.0 (95% CI: 113.4-128.2) per 100000 population over 10 years old with particularly high rates in teenage girls of 15-19 years old (296.1/100000) and females and males of 20-24 years old (282.5 and 178.8/100000, respectively). Conclusion The insightful details of data processing and the rich findings from this study underscore the importance of patient registry in studying and reporting DSH incidents on a population level.