Improving the performance of machine learning penicillin adverse drug reaction classification with synthetic data and transfer learning.

BACKGROUND: Machine learning may assist with the identification of potentially inappropriate penicillin allergy labels. Strategies to improve the performance of existing models for this task include the use of additional training data, synthetic data and transfer learning. AIMS: The aims of this study were to investigate the use of additional training data and novel machine learning strategies, namely synthetic data and transfer learning, to improve the performance of penicillin adverse drug reaction (ADR) machine learning classification. METHODS: Machine learning natural language processing was applied to free-text penicillin ADR data extracted from a public health system electronic health record (EHR). The models were developed by training on various labelled data sets. ADR entries were split into training and testing data sets and used to develop and test a variety of machine learning models. The effect of training on additional data and synthetic data versus the use of transfer learning was analysed. RESULTS: Following the application of these techniques, the area under the receiver operator curve of best-performing models for the classification of penicillin allergy (vs intolerance) and high-risk allergy (vs low-risk allergy) improved to 0.984 (using the artificial neural network model) and 0.995 (with the transfer learning approach) respectively. CONCLUSIONS: Machine learning models demonstrate high levels of accuracy in the classification and risk stratification of penicillin ADR labels using the reaction documented in the EHR. The model can be further optimised by incorporating additional training data and using transfer learning. Practical applications include automating case detection for penicillin allergy delabelling programmes.

Meeting medical emergency response criteria for hypertension is not associated with an increased likelihood of in-hospital mortality in a tertiary referral center.

Backgrounds: Rapid response team or medical emergency team (MET) calls are typically activated by significant alterations of vital signs in inpatients. However, the clinical significance of a specific criterion, blood pressure elevations, is uncertain. Objectives: The aim of this study was to evaluate the likelihood ratios associated with MET-activating vital signs, particularly in-patient hypertension, for predicting in-hospital mortality among general medicine inpatients who met MET criteria at any point during admission in a South Australian metropolitan teaching hospital. Results: Among the 15,734 admissions over a two-year period, 4282 (27.2%) met any MET criteria, with a positive likelihood ratio of 3.05 (95% CI 2.93 to 3.18) for in-hospital mortality. Individual MET criteria were significantly associated with in-hospital mortality, with the highest positive likelihood ratio for respiratory rate ≤ 7 breaths per minute (9.83, 95% CI 6.90 to 13.62), barring systolic pressure ≥ 200 mmHg (LR + 1.26, 95% CI 0.86 to 1.69). Conclusions: Our results show that meeting the MET criteria for hypertension, unlike other criteria, was not significant associated with in-hospital mortality. This observation warrants further research in other patient cohorts to determine whether blood pressure elevations should be routinely included in MET criteria.