Development of a scoring system to quantify errors from semantic characteristics in incident reports.

OBJECTIVES: Incident reporting systems are widely used to identify risks and enable organisational learning. Free-text descriptions contain important information about factors associated with incidents. This study aimed to develop error scores by extracting information about the presence of error factors in incidents using an original decision-making model that partly relies on natural language processing techniques. METHODS: We retrospectively analysed free-text data from reports of incidents between January 2012 and December 2022 from Nagoya University Hospital, Japan. The sample data were randomly allocated to equal-sized training and validation datasets. We conducted morphological analysis on free text to segment terms from sentences in the training dataset. We calculated error scores for terms, individual reports and reports from staff groups according to report volume size and compared these with conventional classifications by patient safety experts. We also calculated accuracy, recall, precision and F-score values from the proposed 'report error score'. RESULTS: Overall, 114 013 reports were included. We calculated 36 131 'term error scores' from the 57 006 reports in the training dataset. There was a significant difference in error scores between reports of incidents categorised by experts as arising from errors (p<0.001, d=0.73 (large)) and other incidents. The accuracy, recall, precision and F-score values were 0.8, 0.82, 0.85 and 0.84, respectively. Group error scores were positively associated with expert ratings (correlation coefficient, 0.66; 95% CI 0.54 to 0.75, p<0.001) for all departments. CONCLUSION: Our error scoring system could provide insights to improve patient safety using aggregated incident report data.

Development of a Novel Scoring System to Quantify the Severity of Incident Reports: An Exploratory Research Study.

Incident reporting systems have been widely adopted to collect information about patient safety incidents. Much of the value of incident reports lies in the free-text section. Computer processing of semantic information may be helpful to analyze this. We developed a novel scoring system for decision making to assess the severity of incidents using the semantic characteristics of the text in incident reports, and compared its results with experts' opinions. We retrospectively analyzed free-text data from incident reports from January 2012 to September 2021 at Nagoya University Hospital, Aichi, Japan. The sample was allocated to training and validation datasets using the hold-out method. Morphological analysis was used to segment terms in the training dataset. We calculated a severity term score, a severity report score and severity group score, by report volume size, and compared these with conventional severity classifications by patient safety experts and reporters. We allocated 96,082 incident reports into two groups. We calculated 1,802 severity term scores from the 48,041 reports in the training dataset. There was a significant difference in severity report score between reports categorized as severe and not severe by experts (95% confidence interval [CI] -0.83 to -0.80, p < 0.001, d = 0.81). Severity group scores were positively associated with severity ratings from experts and reporters (correlation coefficients 0.73 [95% CI 0.63-0.80, p < 0.001] and 0.79 [95% CI 0.71-0.85, p < 0.001]) for all departments. Our severity scoring system could therefore contribute to better organizational patient safety.

＜Editors' Choice＞ Developing online lectures using text mining reduces health workers' anxiety in non-epicenter areas of COVID-19.

COVID-19 is indirectly associated with various mental disorders such as anxiety, insomnia, and depression, and healthcare professionals who treat COVID-19 patients are particularly prone to severe anxiety. However, neither the anxiety of healthcare workers in non-epicenter areas nor the effects of knowledge support have been examined thus far. Participants were 458 staff working at the Toyota Regional Medical Center who completed a preliminary questionnaire of their knowledge and anxiety regarding COVID-19. Based on text mining of the questionnaire responses, participants were offered an online lecture. The effect of the lecture was analyzed using a pre- and post-lecture rating of anxiety and knowledge confidence, and quantitative text mining. The response rates were 45.6% pre- and 62.9% post-lecture. Open-ended responses regarding anxiety and knowledge were classified into seven clusters using a co-occurrence network. Before the lecture, 28.2%, 27.2%, and 20.3% of participants were interested in and anxious about "infection prevention and our hospital's response," "infection and impact on myself, family, and neighbors," and "general knowledge of COVID-19," respectively. As a result of the lecture, Likert-scale ratings for anxiety of COVID-19 decreased significantly and knowledge confidence increased significantly. These changes were confirmed by analyses of open-ended responses about anxiety, lifestyle changes, and knowledge. Positive changes were strongly linked to the topics focused on in the lecture, especially infection prevention. The anxieties about COVID-19 of healthcare workers in non-epicenter areas can be effectively reduced through questionnaire surveys and online lectures using text mining.