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.

Assessment of medical malpractice cost at a Japanese national university hospital.

Medical safety management has an economic dimension that has received little attention. Medical expenses associated with medical malpractice in Japan should be investigated in relation to patient safety measures and their consequences. We analyzed medical accidents that occurred within the past seven years at a university hospital. We determined that 197 accidents involved negligence by the hospital in the years from 2011 to 2017, for which the institution bore the costs of the resulting treatment; those expenses totaled JPY 30.547 million. Most incidents occurred in the hospital ward (82, 41.6%); those in the operating room were the most expensive (JPY 19.493 million, 63.8%). The greatest number of cases involved drug administration (63, 32.0%). Materials inadvertently left in surgical sites ("remnants") cost the hospital the most per incident (JPY 9.767 million, 32.0%). Of these, medical treatment costs for remnants associated with vascular invasion were the highest. Although the total number of malpractice incidents increased over time, the annual cost to the hospital decreased, especially in cases in which costs exceeded JPY 100,000, and those associated with the operating room. Our results suggested that adverse events must be addressed to foster patient safety, decrease medical expenses, and improve hospital administrative capacity.

Intervention efficacy for eliminating patient misidentification using step-by-step problem-solving procedures to improve patient safety.

This study aimed to evaluate the efficacy of interventions to reduce patient misidentification incidents classified as level 2 and over (adverse events occurred for patients) with the step-by-step problem-solving method. All incidents related to patient misidentification were selected, and relevant information was collected from the original electronic incident reports. We then conducted an eight-step problem-solving process with the aim of reducing patient misclassification and improving patient safety. Step 1: the number of misidentification-related incident reports and the percentage of these reports in the total incident reports increased each year. Step 2: the most frequent misidentification type was sample collection tubes, followed by drug administration and hospital meals. Step 3: we set a target of an 20% decrease in patient misidentification cases classified as level 2 or over compared with the previous year, and established this as a hospital priority. Step 4: we found that discrepancies in patient identification procedures were the most important causes of misidentification. Step 5: we standardized the patient identification process to achieve an 10% reduction in misidentification. Step 6: we disseminated instructional videos to all staff members. Step 7: we confirmed there was an 18% reduction in level 2 and over patient misidentification compared with the previous year. Step 8: we intend to make additional effort to decrease misidentification of patients by a further 10%. Level 2 and over patient misidentification can be reduced by a patient identification policy using a step-by-step problem-solving procedure. This study aimed to evaluate the efficacy of interventions to reduce patient misidentification incidents with step-by-step problem-solving method. Continued seamless efforts to eliminate patient misidentification are mandatory for this activity.