Short-term learning effect of ChatGPT on pharmacy students' learning.

Introduction: Students in pharmacy are positive towards integrating artificial intelligence and ChatGPT into their practice. The aim of this study was to investigate the direct short-term learning effect of using Chat GPT by pharmacy students. Methods: This was an experimental randomized study. Students were allocated into two groups; the intervention group (n = 15) used all study tools and ChatGPT, while the control group (n = 16) used all study tools, except ChatGPT. Differences between groups was measured by how well they performed on a knowledge test before and after a short study period. Results: No significant difference was found between the intervention and control groups in level of competence in the pretest score (p = 0.28). There was also no significant effect of using ChatGPT, with a mean adjusted difference of 0.5 points on a 12-point scale. However there was a trend towards a higher proportion of ChatGPT participants having a large (at least four point) increase in score (4 out of 15) vs control group (1 out of 16). Conclusion: There is a potential for positive effects of ChatGPT on learning outcomes in pharmacy students, however the current study was underpowered to measure a statistically significant effect of ChatGPT on short term learning.

Using machine learning methods to predict all-cause somatic hospitalizations in adults: A systematic review.

AIM: In this review, we investigated how Machine Learning (ML) was utilized to predict all-cause somatic hospital admissions and readmissions in adults. METHODS: We searched eight databases (PubMed, Embase, Web of Science, CINAHL, ProQuest, OpenGrey, WorldCat, and MedNar) from their inception date to October 2023, and included records that predicted all-cause somatic hospital admissions and readmissions of adults using ML methodology. We used the CHARMS checklist for data extraction, PROBAST for bias and applicability assessment, and TRIPOD for reporting quality. RESULTS: We screened 7,543 studies of which 163 full-text records were read and 116 met the review inclusion criteria. Among these, 45 predicted admission, 70 predicted readmission, and one study predicted both. There was a substantial variety in the types of datasets, algorithms, features, data preprocessing steps, evaluation, and validation methods. The most used types of features were demographics, diagnoses, vital signs, and laboratory tests. Area Under the ROC curve (AUC) was the most used evaluation metric. Models trained using boosting tree-based algorithms often performed better compared to others. ML algorithms commonly outperformed traditional regression techniques. Sixteen studies used Natural language processing (NLP) of clinical notes for prediction, all studies yielded good results. The overall adherence to reporting quality was poor in the review studies. Only five percent of models were implemented in clinical practice. The most frequently inadequately addressed methodological aspects were: providing model interpretations on the individual patient level, full code availability, performing external validation, calibrating models, and handling class imbalance. CONCLUSION: This review has identified considerable concerns regarding methodological issues and reporting quality in studies investigating ML to predict hospitalizations. To ensure the acceptability of these models in clinical settings, it is crucial to improve the quality of future studies.

"Using network analysis modularity to group health code systems and decrease dimensionality in machine learning models".

Background: Machine learning (ML) prediction models in healthcare and pharmacy-related research face challenges with encoding high-dimensional Healthcare Coding Systems (HCSs) such as ICD, ATC, and DRG codes, given the trade-off between reducing model dimensionality and minimizing information loss. Objectives: To investigate using Network Analysis modularity as a method to group HCSs to improve encoding in ML models. Methods: The MIMIC-III dataset was utilized to create a multimorbidity network in which ICD-9 codes are the nodes and the edges are the number of patients sharing the same ICD-9 code pairs. A modularity detection algorithm was applied using different resolution thresholds to generate 6 sets of modules. The impact of four grouping strategies on the performance of predicting 90-day Intensive Care Unit readmissions was assessed. The grouping strategies compared: 1) binary encoding of codes, 2) encoding codes grouped by network modules, 3) grouping codes to the highest level of ICD-9 hierarchy, and 4) grouping using the single-level Clinical Classification Software (CCS). The same methodology was also applied to encode DRG codes but limiting the comparison to a single modularity threshold to binary encoding.The performance was assessed using Logistic Regression, Support Vector Machine with a non-linear kernel, and Gradient Boosting Machines algorithms. Accuracy, Precision, Recall, AUC, and F1-score with 95% confidence intervals were reported. Results: Models utilized modularity encoding outperformed ungrouped codes binary encoding models. The accuracy improved across all algorithms ranging from 0.736 to 0.78 for the modularity encoding, to 0.727 to 0.779 for binary encoding. AUC, recall, and precision also improved across almost all algorithms. In comparison with other grouping approaches, modularity encoding generally showed slightly higher performance in AUC, ranging from 0.813 to 0.837, and precision, ranging from 0.752 to 0.782. Conclusions: Modularity encoding enhances the performance of ML models in pharmacy research by effectively reducing dimensionality and retaining necessary information. Across the three algorithms used, models utilizing modularity encoding showed superior or comparable performance to other encoding approaches. Modularity encoding introduces other advantages such as it can be used for both hierarchical and non-hierarchical HCSs, the approach is clinically relevant, and can enhance ML models' clinical interpretation. A Python package has been developed to facilitate the use of the approach for future research.

An introduction to network analysis for studies of medication use.

BACKGROUND: Network Analysis (NA) is a method that has been used in various disciplines such as Social sciences and Ecology for decades. So far, NA has not been used extensively in studies of medication use. Only a handful of papers have used NA in Drug Prescription Networks (DPN). We provide an introduction to NA terminology alongside a guide to creating and extracting results from the medication networks. OBJECTIVE: To introduce the readers to NA as a tool to study medication use by demonstrating how to apply different NA measures on 3 generated medication networks. METHODS: We used the Norwegian Prescription Database (NorPD) to create a network that describes the co-medication in elderly persons in Norway on January 1, 2013. We used the Norwegian Electronic Prescription Support System (FEST) to create another network of severe drug-drug interactions (DDIs). Lastly, we created a network combining the two networks to show the actual use of drugs with severe DDIs. We used these networks to elucidate how to apply and interpret different network measures in medication networks. RESULTS: Interactive network graphs are made available online, Stata and R syntaxes are provided. Various useful network measures for medication networks were applied such as network topological features, modularity analysis and centrality measures. Edge lists data used to generate the networks are openly available for readers in an open data repository to explore and use. CONCLUSION: We believe that NA can be a useful tool in medication use studies. We have provided information and hopefully inspiration for other researchers to use NA in their own projects. While network analyses are useful for exploring and discovering structures in medication use studies, it also has limitations. It can be challenging to interpret and it is not suitable for hypothesis testing.