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.

Artificial intelligence and the potential for perioperative delabeling of penicillin allergies for neurosurgery inpatients.

PURPOSE OF THE ARTICLE: Patients with penicillin allergy labels are more likely to have postoperative wound infections. When penicillin allergy labels are interrogated, a significant number of individuals do not have penicillin allergies and may be delabeled. This study was conducted to gain preliminary evidence into the potential role of artificial intelligence in assisting with perioperative penicillin adverse reaction (AR) evaluation. MATERIAL AND METHODS: A single-centre retrospective cohort study of consecutive emergency and elective neurosurgery admissions was conducted over a two-year period. Previously derived artificial intelligence algorithms for the classification of penicillin AR were applied to the data. RESULTS: There were 2063 individual admissions included in the study. The number of individuals with penicillin allergy labels was 124; one patient had a penicillin intolerance label. Of these labels, 22.4% were not consistent with classifications using expert criteria. When the artificial intelligence algorithm was applied to the cohort, the algorithm maintained a high level of classification performance (classification accuracy 98.1% for allergy versus intolerance classification). CONCLUSIONS: Penicillin allergy labels are common among neurosurgery inpatients. Artificial intelligence can accurately classify penicillin AR in this cohort, and may assist in identifying patients suitable for delabeling.

Professionalism and clinical short answer question marking with machine learning.

Machine learning may assist in medical student evaluation. This study involved scoring short answer questions administered at three centres. Bidirectional encoder representations from transformers were particularly effective for professionalism question scoring (accuracy ranging from 41.6% to 92.5%). In the scoring of 3-mark professionalism questions, as compared with clinical questions, machine learning had a lower classification accuracy (P < 0.05). The role of machine learning in medical professionalism evaluation warrants further investigation.

Neurosurgery inpatient outcome prediction for discharge planning with deep learning and transfer learning.

INTRODUCTION: Deep learning may be able to assist with the prediction of neurosurgical inpatient outcomes. The aims of this study were to investigate deep learning and transfer learning in the prediction of several inpatient outcomes including timing of discharge and discharge destination. METHOD: Data were collected on consecutive neurosurgical admissions from existing databases over a 15-month period. Following pre-processing artificial neural networks were applied to admission notes and ward round notes to predict four inpatient outcomes. Models were developed on the training dataset, before being tested on a hold-out test dataset and a validation dataset. RESULTS: 1341 individual admissions were included in the study. Using transfer learning and an artificial neural network an area under the receiver operator curve (AUC) of 0.81 and 0.80 on the derivation and validation datasets was able to be achieved for the prediction of discharge within the next 48 hours using daily ward round notes. This result is in comparison to an AUC of 0.71 and 0.68 using an artificial neural network without transfer learning for the same outcome. When the artificial neural network with transfer learning was applied to the other outcomes AUC of 0.72, 0.93 and 0.83 was achieved on the validation datasets for predicting discharge within the next 7 days, survival to discharge and discharge to home as a destination. CONCLUSIONS: Deep learning may predict inpatient neurosurgery outcomes from free-text medical data. Recurrent predictions with ward round notes enable the use of information obtained throughout hospital admissions in these estimates.

The Efficacy, Adverse Effects and Economic Implications of Oral Versus Intravenous Methylprednisolone for the Treatment of Optic Neuritis: A Systematic Review.

INTRODUCTION: Optic neuritis may occur in a variety of conditions, including as a manifestation of multiple sclerosis. Despite significant research into the efficacy of corticosteroids as a first-line treatment, the optimal route of administration has not been well defined. This review aims to explore the efficacy, adverse effects and economic implications of using oral versus intravenous methylprednisolone to treat acute optic neuritis. METHODS: A systematic search of the databases PubMed/MEDLINE, Embase and CENTRAL was performed to July 2022, prior to data collection and risk of bias analysis in accordance with the PRISMA guidelines. RESULTS: Six articles fulfilled the inclusion criteria. The results showed that in the treatment of acute optic neuritis, oral methylprednisolone has a non-inferior efficacy and adverse effect profile in comparison to intravenous methylprednisolone. In a cost analysis, oral methylprednisolone to be more cost-effective than intravenous methylprednisolone. CONCLUSIONS: Oral methylprednisolone has comparable efficacy and adverse effect profiles to intravenous methylprednisolone for the treatment of optic neuritis. The analysis suggests oral administration is more cost-effective than intravenous administration; however, further analyses of the formal cost-benefit ratio are required.

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.

Artificial intelligence for predicting acute appendicitis: a systematic review.

BACKGROUND: Paediatric appendicitis may be challenging to diagnose, and outcomes difficult to predict. While diagnostic and prognostic scores exist, artificial intelligence (AI) may be able to assist with these tasks. METHOD: A systematic review was conducted aiming to evaluate the currently available evidence regarding the use of AI in the diagnosis and prognostication of paediatric appendicitis. In accordance with the PRISMA guidelines, the databases PubMed, EMBASE, and Cochrane Library were searched. This review was prospectively registered on PROSPERO. RESULTS: Ten studies met inclusion criteria. All studies described the derivation and validation of AI models, and none described evaluation of the implementation of these models. Commonly used input parameters included varying combinations of demographic, clinical, laboratory, and imaging characteristics. While multiple studies used histopathological examination as the ground truth for a diagnosis of appendicitis, less robust techniques, such as the use of ICD10 codes, were also employed. Commonly used algorithms have included random forest models and artificial neural networks. High levels of model performance have been described for diagnosis of appendicitis and, to a lesser extent, subtypes of appendicitis (such as complicated versus uncomplicated appendicitis). Most studies did not provide all measures of model performance required to assess clinical usability. CONCLUSIONS: The available evidence suggests the creation of prediction models for diagnosis and classification of appendicitis using AI techniques, is being increasingly explored. However, further implementation studies are required to demonstrate benefit in system or patient-centred outcomes with model deployment and to progress these models to the stage of clinical usability.

Immune Checkpoint Inhibitors and Optic Neuropathy: A Systematic Review.

INTRODUCTION: Immune checkpoint inhibitors are a class of monoclonal antibodies that are used as a mainstay of immunotherapy for multiple solid organ malignancies. With the recent increase in popularity of these agents, immune-related adverse events including optic neuropathy are becoming more frequently reported. This review aims to explore the association between immune checkpoint inhibitors and optic neuropathy through analysis of incidence, clinical features, investigations, treatment, and patient outcomes. METHOD: A systematic search of the databases PubMed/MEDLINE, Embase, and CENTRAL was performed from inception to September 2022. Data collection and risk of bias analysis was subsequently conducted in accordance with the PRISMA guidelines. RESULTS: Eleven articles fulfilled the inclusion criteria. The results showed an increased incidence of optic neuropathy among patients receiving immune checkpoint inhibitor therapy compared to the general population. Presentation with painless reduced visual acuity and optic disc swelling was most common. Investigation findings were poorly documented. The only two patients who achieved full resolution of symptoms were treated with oral prednisolone. CONCLUSION: There is a strong association between immune checkpoint inhibitor therapy and development of optic neuropathy. Although it remains uncommon, the incidence of optic neuropathy in this population exceeds that of the general population. Future research is needed to further characterise the risk profiles of patients who are most likely to develop ICI-associated optic neuropathy, and treatment pathways for these patients.

Cogan's Lid Twitch for Myasthenia Gravis: A Systematic Review.

INTRODUCTION: Myasthenia gravis is an autoimmune condition affecting the neuromuscular junction of skeletal muscles and may be difficult to diagnose. Several clinical signs may have diagnostic utility, including Cogan's lid twitch. This systematic review aims to synthesise the literature on the accuracy of Cogan's lid twitch for diagnosing myasthenia gravis. METHODS: A systematic search of the databases PubMed/MEDLINE, Embase and CENTRAL was performed from inception to August 2022. Risk of bias analysis and data extraction were performed in accordance with the PRISMA 2020 guidelines. RESULTS: Seven articles satisfied the inclusion criteria. The results showed that for the diagnosis of myasthenia gravis, Cogan's lid twitch has a sensitivity between 50% and 99% and specificity between 75% and 100%. CONCLUSIONS: Cogan's lid twitch is a physical examination finding with moderate diagnostic performance in the diagnosis of myasthenia gravis with ocular involvement. Future studies may seek to evaluate the performance of Cogan's lid twitch in conjunction with other signs of myasthenia gravis with ocular involvements, such as fatigable ptosis or a positive icepack test.

Health Economic Implications of Artificial Intelligence Implementation for Ophthalmology in Australia: A Systematic Review.

PURPOSE: The health care industry is an inherently resource-intense sector. Emerging technologies such as artificial intelligence (AI) are at the forefront of advancements in health care. The health economic implications of this technology have not been clearly established and represent a substantial barrier to adoption both in Australia and globally. This review aims to determine the health economic impact of implementing AI to ophthalmology in Australia. METHODS: A systematic search of the databases PubMed/MEDLINE, EMBASE, and CENTRAL was conducted to March 2022, before data collection and risk of bias analysis in accordance with preferred reporting items for systematic ceviews and meta-analyses 2020 guidelines (PROSPERO number CRD42022325511). Included were full-text primary research articles analyzing a population of patients who have or are being evaluated for an ophthalmological diagnosis, using a health economic assessment system to assess the cost-effectiveness of AI. RESULTS: Seven articles were identified for inclusion. Economic viability was defined as direct cost to the patient that is equal to or less than costs incurred with human clinician assessment. Despite the lack of Australia-specific data, foreign analyses overwhelmingly showed that AI is just as economically viable, if not more so, than traditional human screening programs while maintaining comparable clinical effectiveness. This evidence was largely in the setting of diabetic retinopathy screening. CONCLUSIONS: Primary Australian research is needed to accurately analyze the health economic implications of implementing AI on a large scale. Further research is also required to analyze the economic feasibility of adoption of AI technology in other areas of ophthalmology, such as glaucoma and cataract screening.