Predicting the performance of lithium adsorption and recovery from unconventional water sources with machine learning.

Selective lithium (Li) recovery from unconventional water sources (UWS) (e.g., shale gas waters, geothermal brines, and rejected seawater desalination brines) using inorganic lithium-ion sieve (LIS) materials can address Li supply shortages and distribution issues. However, the development of high-performance LIS materials and the optimization of recovery-related operating parameters are hampered by the variety of production methods, intricate procedures, and experimental expenses. Machine learning (ML) techniques offer potential solutions for enhancing LIS material development. We collected literature data on Li adsorption, categorizing 16 parameters into adsorbent parameters, operating parameters, and solution components. Three tree-based algorithms-Random Forest (RF), Gradient Boosting Decision Trees (GBDT), and Extreme Gradient Boosting (XGBoost)-were used to evaluate the impact of these parameters on lithium adsorption. The grouped random splitting method limited data leakage and mitigated overfitting. XGBoost demonstrated the best performance, with an R² of 0.98 and a root-mean-squared error (RMSE) of 1.72. The SHAP values highlighted that operating parameters were the most influential, followed by adsorbent parameters and coexisting ion concentrations. Therefore, focusing on optimizing operating parameters or making targeted improvements on LIS based on operating conditions will enhance LIS performances in UWS. These insights are crucial for optimizing Li adsorption processes and designing effective inorganic LIS materials.

Changes in the Pneumococcal Vaccination Uptake and Its Determinants before, during, and after the COVID-19 Pandemic among Community-Living Older Adults in Hong Kong, China: Repeated Random Telephone Surveys.

Pneumococcal vaccination (PV) is effective in preventing vaccine-type pneumococcal diseases. This study investigated the changes in PV uptake and its determinants before, during, and after the Coronavirus Disease 2019 (COVID-19) pandemic among community-living older adults aged ≥65 years in Hong Kong, China. Three rounds of random telephone surveys were conducted every two years from May 2019 to October 2023. Multivariate logistic regression models were fitted to examine the between-round differences in PV uptake rate and factors associated with PV uptake in each round. This study included 1563 participants. The standardized PV uptake rate in Round 1, 2, and 3 was 17.3%, 28.3%, and 35.5%, respectively. A significant difference in the PV uptake rate was found between Rounds 2 and 1 (p = 0.02), but not between Rounds 3 and 2 (p = 0.98). Perceived barriers, cue to action and self-efficacy, were significant determinants of PV uptake in all rounds. Perceived benefits were significant determinants of PV uptake in the first and second rounds, but not in the third round. Continuous monitoring of PV uptake and its determinants, and evaluating and adjusting the PV program, might contribute to the success of such a vaccination program in the post-pandemic era.

DDI-MuG: Multi-aspect graphs for drug-drug interaction extraction.

Introduction: Drug-drug interaction (DDI) may lead to adverse reactions in patients, thus it is important to extract such knowledge from biomedical texts. However, previously proposed approaches typically focus on capturing sentence-aspect information while ignoring valuable knowledge concerning the whole corpus. In this paper, we propose a Multi-aspect Graph-based DDI extraction model, named DDI-MuG. Methods: We first employ a bio-specific pre-trained language model to obtain the token contextualized representations. Then we use two graphs to get syntactic information from input instance and word co-occurrence information within the entire corpus, respectively. Finally, we combine the representations of drug entities and verb tokens for the final classification. Results: To validate the effectiveness of the proposed model, we perform extensive experiments on two widely used DDI extraction dataset, DDIExtraction-2013 and TAC 2018. It is encouraging to see that our model outperforms all twelve state-of-the-art models. Discussion: In contrast to the majority of earlier models that rely on the black-box approach, our model enables visualization of crucial words and their interrelationships by utilizing edge information from two graphs. To the best of our knowledge, this is the first model that explores multi-aspect graphs to the DDI extraction task, and we hope it can establish a foundation for more robust multi-aspect works in the future.

Utilizing Text Mining, Data Linkage and Deep Learning in Police and Health Records to Predict Future Offenses in Family and Domestic Violence.

Family and Domestic violence (FDV) is a global problem with significant social, economic, and health consequences for victims including increased health care costs, mental trauma, and social stigmatization. In Australia, the estimated annual cost of FDV is $22 billion, with one woman being murdered by a current or former partner every week. Despite this, tools that can predict future FDV based on the features of the person of interest (POI) and victim are lacking. The New South Wales Police Force attends thousands of FDV events each year and records details as fixed fields (e.g., demographic information for individuals involved in the event) and as text narratives which describe abuse types, victim injuries, threats, including the mental health status for POIs and victims. This information within the narratives is mostly untapped for research and reporting purposes. After applying a text mining methodology to extract information from 492,393 FDV event narratives (abuse types, victim injuries, mental illness mentions), we linked these characteristics with the respective fixed fields and with actual mental health diagnoses obtained from the NSW Ministry of Health for the same cohort to form a comprehensive FDV dataset. These data were input into five deep learning models (MLP, LSTM, Bi-LSTM, Bi-GRU, BERT) to predict three FDV offense types ("hands-on," "hands-off," "Apprehended Domestic Violence Order (ADVO) breach"). The transformer model with BERT embeddings returned the best performance (69.00% accuracy; 66.76% ROC) for "ADVO breach" in a multilabel classification setup while the binary classification setup generated similar results. "Hands-off" offenses proved the hardest offense type to predict (60.72% accuracy; 57.86% ROC using BERT) but showed potential to improve with fine-tuning of binary classification setups. "Hands-on" offenses benefitted least from the contextual information gained through BERT embeddings in which MLP with categorical embeddings outperformed it in three out of four metrics (65.95% accuracy; 78.03% F1-score; 70.00% precision). The encouraging results indicate that future FDV offenses can be predicted using deep learning on a large corpus of police and health data. Incorporating additional data sources will likely increase the performance which can assist those working on FDV and law enforcement to improve outcomes and better manage FDV events.

iCBLS: An interactive case-based learning system for medical education.

Medical students should be able to actively apply clinical reasoning skills to further their interpretative, diagnostic, and treatment skills in a non-obtrusive and scalable way. Case-Based Learning (CBL) approach has been receiving attention in medical education as it is a student-centered teaching methodology that exposes students to real-world scenarios that need to be solved using their reasoning skills and existing theoretical knowledge. In this paper, we propose an interactive CBL System, called iCBLS, which supports the development of collaborative clinical reasoning skills for medical students in an online environment. The iCBLS consists of three modules: (i) system administration (SA), (ii) clinical case creation (CCC) with an innovative semi-automatic approach, and (iii) case formulation (CF) through intervention of medical students' and teachers' knowledge. Two evaluations under the umbrella of the context/input/process/product (CIPP) model have been performed with a Glycemia study. The first focused on the system satisfaction, evaluated by 54 students. The latter aimed to evaluate the system effectiveness, simulated by 155 students. The results show a high success rate of 70% for students' interaction, 76.4% for group learning, 72.8% for solo learning, and 74.6% for improved clinical skills.