Background/Objectives: Accurate prediction of pediatric appendicitis diagnosis, management, and severity is critical for clinical decision-making. We aimed to evaluate the predictive performance of a wide range of machine learning models, combined with various feature selection techniques, on a pediatric appendicitis dataset. A particular focus was placed on the role of ultrasound (US) image-descriptive features in model performance and explainability. Methods: We conducted a retrospective cohort study on a dataset of 781 pediatric patients aged 0–18 presenting to Children’s Hospital St. Hedwig in Regensburg, Germany, between January 2016 and February 2023. We developed and validated predictive models; machine learning algorithms included the random forest, logistic regression, stochastic gradient descent, and the light gradient boosting machine (LGBM). These were paired exhaustively with feature selection methods spanning filter-based (association and prediction), embedded (LGBM and linear), and a novel redundancy-aware step-up wrapper approach. We employed a machine learning benchmarking study design where AI models were trained to predict diagnosis, management, and severity outcomes, both with and without US image-descriptive features, and evaluated on held-out testing samples. Model performance was assessed using overall accuracy and area under the receiver operating characteristic curve (AUROC). A deep learner optimized for tabular data, GANDALF, was also evaluated in these applications. Results: US features significantly improved diagnostic accuracy, supporting their use in reducing model bias. However, they were not essential for maximizing accuracy in predicting management or severity. In summary, our best-performing models were, for diagnosis, the random forest with embedded LGBM feature selection (98.1% accuracy, AUROC: 0.993), for management, the random forest without feature selection (93.9% accuracy, AUROC: 0.980), and for severity, the LGBM with filter-based association feature selection (90.1% accuracy, AUROC: 0.931). Conclusions: Our results demonstrate that high-performing, interpretable machine learning models can predict key clinical outcomes in pediatric appendicitis. US image features improve diagnostic accuracy but are not critical for predicting management or severity.

Supervised machine learning classification is the most common example of artificial intelligence (AI) in industry and in academic research. These technologies predict whether a series of measurements belong to one of multiple groups of examples on which the machine was previously trained. Prior to real-world deployment, all implementations need to be carefully evaluated with hold-out validation, where the algorithm is tested on different samples than it was provided for training, in order to ensure the generalizability and reliability of AI models. However, established methods for performing hold-out validation do not assess the consistency of the mistakes that the AI model makes during hold-out validation. Here, we show that in addition to standard methods, an enhanced technique for performing hold-out validation—that also assesses the consistency of the sample-wise mistakes made by the learning algorithm—can assist in the evaluation and design of reliable and predictable AI models. The technique can be applied to the validation of any supervised learning classification application, and we demonstrate the use of the technique on a variety of example biomedical diagnostic applications, which help illustrate the importance of producing reliable AI models. The validation software created is made publicly available, assisting anyone developing AI models for any supervised classification application in the creation of more reliable and predictable technologies.

Applying artificial intelligence (AI) and machine learning for chronic kidney disease (CKD) diagnostics and characterization has the potential to improve the standard of patient care through accurate and early detection, as well as providing a more detailed understanding of the condition. This study employed reproducible validation of AI technology with public domain software applied to CKD diagnostics on a publicly available CKD dataset acquired from 400 patients. The approach presented includes patient-specific symptomatic variables and demonstrates performance improvements associated with this approach. Our best-performing AI models, which include patient symptom variables, achieve predictive accuracies ranging from 99.4 to 100% across both hold-out and 5-fold validation with the light gradient boosting machine. We demonstrate that the exclusion of patient symptom variables reduces model performance in line with the literature on the same dataset. We also provide an unsupervised learning cluster analysis to help interpret variability among, and characterize the population of, patients with CKD.

Differentiated thyroid cancer (DTC) poses significant management challenges due to the variable risk of recurrence. This study uses a dataset comprising clinical, pathological, and treatment data from 383 patients to develop and validate machine learning models, combined with feature selection algorithms, for predicting differentiated thyroid cancer recurrence. We evaluated models based on a variety of machine learning technologies (light gradient boosting machine, random forest, k-nearest neighbor, logistic regression, stochastic gradient descent, and an emerging deep learner optimized for tabular data: Gandalf) combined with several feature selection methods. Our feature selection technologies include an emerging redundancy-aware wrapper-based feature selection technique, achieving thyroid cancer recurrence prediction accuracy of 94.8 to 95.9% across two validation methods, based only on whether the patient’s tumor’s response was structurally incomplete, whether their tumor’s stage was advanced (III, IVA, or IVB), and the patient’s age. The results underline the potential for machine learning to enhance the precision of recurrence prediction in DTC while developing technologies whose predictive capacity is more easily explained. Using the same dataset, machine learning and feature selection techniques, this study also provides an analysis on predicting American Thyroid Association (ATA) risk scores. The technologies developed as part of this study have potential for improving the personalization of healthcare through the creation of models based on detailed patient-specific clinical attributes.

In this study, we identify cortical molecular biomarkers potentially associated with learning in mice using artificial intelligence (AI), inclusive of established and novel feature selection combined with supervised learning technologies. We applied multiple machine learning (ML) algorithms, using public domain ML software, to a public domain dataset, in order to support reproducible findings. We developed technologies tasked with predicting whether a given mouse was shocked to learn, based on protein expression levels extracted from their cortices. Results indicate that it is possible to predict whether a mouse has been shocked to learn or not based only on the following cortical molecular biomarkers: brain-derived neurotrophic factor (BDNF), NR2A subunit of N-methyl-D-aspartate receptor, B-cell lymphoma 2 (BCL2), histone H3 acetylation at lysine 18 (H3AcK18), protein kinase R-like endoplasmic reticulum kinase (pERK), and superoxide dismutase 1 (SOD1). These results were obtained with a novel redundancy-aware feature selection method. Five out of six protein expression biomarkers (BDNF, NR2A, H3AcK18, pERK, SOD1) identified have previously been associated with aspects of learning in the literature. Three of the proteins (BDNF, NR2A, and BCL2) have previously been associated with pruning, and one has previously been associated with apoptosis (BCL2), implying a potential connection between learning and both cortical pruning and apoptosis. The results imply that these six protein expression profiles (BDNF, NR2A, BCL2, H3AcK18, pERK, SOD1) are highly predictive of whether or not a mouse has been shocked to learn.