Uffe Kock Wiil’s research while affiliated with University of Melbourne and other places

Background/Objectives: This systematic literature review examines the application of Artificial Intelligence (AI) in the diagnosis, treatment, and follow-up of metastatic gastrointestinal cancers. Methods: The databases PubMed, Scopus, Embase (Ovid), and Google Scholar were searched for published articles in English from January 2010 to January 2022, focusing on AI models in metastatic gastrointestinal cancers. Results: forty-six studies were included in the final set of reviewed papers. The critical appraisal and data extraction followed the checklist for systematic reviews of prediction modeling studies. The risk of bias in the included papers was assessed using the prediction risk of bias assessment tool. Conclusions: AI techniques, including machine learning and deep learning models, have shown promise in improving diagnostic accuracy, predicting treatment outcomes, and identifying prognostic biomarkers. Despite these advancements, challenges persist, such as reliance on retrospective data, variability in imaging protocols, small sample sizes, and data preprocessing and model interpretability issues. These challenges limit the generalizability, clinical application, and integration of AI models.

The increasing development of technology has led to the increase of digital data in various fields, such as medication-related texts. Sentiment Analysis (SA) in medication is essential to give clinicians insights into patients’ feedback about the treatment procedure. Therefore, this study intends to develop Artificial Intelligence (AI) models to predict patients’ sentiments. This study used a large medication review dataset to perform a SA of medications. Three scenarios were considered for classification, including two, three, and ten classes. The Word2Vec algorithm and pre-trained word embeddings, including the general and clinical domains, were utilized in model development. Seven Machine Learning (ML) and Deep Learning (DL) models were developed for various scenarios. The best hyperparameters for all models were fine-tuned. Moreover, two ensemble learning models were developed from the proposed ML and DL models. For the first time, a technique was implemented to interpret the results for explainability and interpretability. The results showed that the developed deep ensemble model (DL_ENS), using PubMed and PMC, as pre-trained word embedding representation, achieved the best results, with accuracy and F1-Score of 92.96% and 92.27% in two classes, 92.18% and 88.50 in three classes, and 90.31% and 67.07% in ten classes, respectively. Combining DL models and developing a DL_ENS with clinical domain pre-trained word embedding representation can accurately predict classes and scores of patients’ sentiments about medications compared to previous studies on the same dataset. Due to the transparency in decision-making, our DL_ENS model can be used as an auxiliary tool to help clinicians prescribe medications.

Lung cancer (LC) remains the primary cause of cancer-related mortality, largely due to late-stage diagnoses. Effective strategies for early detection are therefore of paramount importance. In recent years, machine learning (ML) has demonstrated considerable potential in healthcare by facilitating the detection of various diseases. In this retrospective development and validation study, we developed an ML model based on dynamic ensemble selection (DES) for LC detection. The model leverages standard blood sample analysis and smoking history data from a large population at risk in Denmark. The study includes all patients examined on suspicion of LC in the Region of Southern Denmark from 2009 to 2018. We validated and compared the predictions by the DES model with diagnoses provided by five pulmonologists. Among the 38,944 patients, 9,940 had complete data of which 2,505 (25%) had LC. The DES model achieved an area under the roc curve of 0.77±0.01, sensitivity of 76.2%±2.04%, specificity of 63.8%±2.3%, positive predictive value of 41.6%±1.2%, and F1-score of 53.8%±1.0%. The DES model outperformed all five pulmonologists, achieving a sensitivity 6.5% higher than their average. The model identified smoking status, lactate dehydrogenase, age, total calcium levels, low values of sodium, leucocytes, neutrophil count, and C-reactive protein as the most important factors for LC detection. The results highlight the successful application of the ML approach in detecting LC, surpassing pulmonologists’ performance. Incorporating clinical and laboratory data in future risk assessment models can improve decision-making and facilitate timely referrals.

Background Stroke is a significant global health concern, ranking as the second leading cause of death and placing a substantial financial burden on healthcare systems, particularly in low- and middle-income countries. Timely evaluation of stroke severity is crucial for predicting clinical outcomes, with standard assessment tools being the Rapid Arterial Occlusion Evaluation (RACE) and the National Institutes of Health Stroke Scale (NIHSS). This study aims to utilize Machine Learning (ML) algorithms to predict stroke severity using these two distinct scales. Methods We conducted this study using two datasets collected from hospitals in Urmia, Iran, corresponding to stroke severity assessments based on RACE and NIHSS. Seven ML algorithms were applied, including K-Nearest Neighbor (KNN), Decision Tree (DT), Random Forest (RF), Adaptive Boosting (AdaBoost), Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), and Artificial Neural Network (ANN). Hyperparameter tuning was performed using grid search to optimize model performance, and SHapley Additive Explanations (SHAP) were used to interpret the contribution of individual features. Results Among the models, the RF achieved the highest performance, with accuracies of 92.68% for the RACE dataset and 91.19% for the NIHSS dataset. The Area Under the Curve (AUC) was 92.02% and 97.86% for the RACE and NIHSS datasets, respectively. The SHAP analysis identified triglyceride levels, length of hospital stay, and age as critical predictors of stroke severity. Conclusions This study is the first to apply ML models to the RACE and NIHSS scales for predicting stroke severity. The use of SHAP enhances the interpretability of the models, increasing clinicians’ trust in these ML algorithms. The best-performing ML model can be a valuable tool for assisting medical professionals in predicting stroke severity in clinical settings.

Background Evidence on how to improve daily physical activity (PA) levels following total knee arthroplasty (TKA) or medial uni-compartmental knee arthroplasty (mUKA) by motivational feedback is lacking. Moreover, it is unknown whether a focus on increased PA after discharge from the hospital improves rehabilitation, physical function, and quality of life. The aim of this randomized controlled trial (RCT) nested in a prospective cohort is (a) to investigate whether PA, physical function, and quality of life following knee replacement can be increased using an activity monitoring device including motivational feedback via a patient app in comparison with activity monitoring without feedback (care-as-usual), and (b) to investigate the potential predictive value of PA level prior to knee replacement for the length of stay, return to work, and quality of life. Methods The study is designed as a multicenter, parallel-group, superiority RCT with balanced randomization (1:1) and blinded outcome assessments. One hundred and fifty patients scheduled for knee replacement (TKA or mUKA) will be recruited through Odense University Hospital, Denmark, Vejle Hospital, Denmark and Herlev/Gentofte Sygehus, Denmark. Patients will be randomized to either 12 weeks of activity monitoring and motivational feedback via a patient app by gamification or 'care-as-usual,' including activity monitoring without motivational feedback. The primary outcome is the between-group change score from baseline to 12-week follow-up of cumulative daily accelerometer counts, which is a valid proxy for average objectively assessed daily PA. Discussion Improving PA through motivational feedback following knee replacement surgery might improve post-surgical function, health-related quality of life, and participation in everyday life. Trial registration ClinicalTrials.gov, ID: NCT06005623. Registered on 2023–08-22. Trial status Recruiting.

Early detection of abnormal heartbeats is of great importance for cardiologists for early diagnosis of cardiac diseases. This will help patients to receive in time diagnosis and prevention. Conventionally, physicians provide cardiac diagnoses by visual examination of electrocardiograms (ECGs). However, this can be a very time consuming and demanding task and, in some cases, may lead to overlooking and wrong diagnosis of life-threatening heart diseases. Therefore, an intelligent model can help to automatically analyze these huge amount of ECGs captured by different devices in clinical practice. A deep transfer learning approach is used to utilize the capability of different trained deep neural networks and to test them on new unseen datasets without the need to fully re-train the model. Two deep neural networks, namely, Visual Geometry Group (VGG) and Residual Network (ResNet) are utilized for classification of ECGs heartbeats. The models are evaluated using two unseen ECG datasets (i.e., SVDB and INCARTDB) by only optimizing their last classification layers. The overall area under curve for receiver operating characteristic (AUCROC) of two VGG and ResNet models are 0.961 and 0.966 on the SVDB dataset, respectively, and both models achieve 0.981 on the INCARTDB. This paper proposes an accurate and explainable model to classify ECG heartbeats into five categories recommended by the ANSI/AAMI standard. The proposed method paves the way to use pre-trained deep neural networks in real-time monitoring of heart patients using ECG data and to help clinicians understand the decision made by the models on each case using an explainable approach.