A review of model evaluation metrics for machine learning in genetics and genomics

Deep Learning to Enhance Diagnosis and Management of Intrahepatic Cholangiocarcinoma

Intrahepatic cholangiocarcinoma (iCCA) is associated with a poor prognosis and necessitates a multimodal, multidisciplinary approach from diagnosis to treatment to achieve optimal outcomes. A noninvasive preoperative diagnosis using abdominal imaging techniques can represent a clinical challenge. Given the differential response of iCCA to localized and systemic therapies compared with hepatocellular carcinoma and secondary hepatic malignancies, an accurate diagnosis is crucial. Deep learning (DL) models for image analysis have emerged as a promising adjunct for the abdominal radiologist, potentially enhancing the accurate detection and diagnosis of iCCA. Over the last five years, several reports have proposed robust DL models, which demonstrate a diagnostic accuracy that is either comparable to or surpasses that of radiologists with varying levels of experience. Recent studies have expanded DL applications into other aspects of iCCA management, including histopathologic diagnosis, the prediction of histopathological features, the preoperative prediction of survival, and the pretreatment prediction of responses to systemic therapy. We herein critically evaluate the expanding body of research on DL applications in the diagnosis and management of iCCA, providing insights into the current progress and future research directions. We comprehensively synthesize the performance and limitations of DL models in iCCA research, identifying key challenges that serve as a translational reference for clinicians.

New Strategies and Artificial Intelligence Methods for the Mitigation of Toxigenic Fungi and Mycotoxins in Foods

The proliferation of toxigenic fungi in food and the subsequent production of mycotoxins constitute a significant concern in the fields of public health and consumer protection. This review highlights recent strategies and emerging methods aimed at preventing fungal growth and mycotoxin contamination in food matrices as opposed to traditional approaches such as chemical fungicides, which may leave toxic residues and pose risks to human and animal health as well as the environment. The novel methodologies discussed include the use of plant-derived compounds such as essential oils, classified as Generally Recognized as Safe (GRAS), polyphenols, lactic acid bacteria, cold plasma technologies, nanoparticles (particularly metal nanoparticles such as silver or zinc nanoparticles), magnetic materials, and ionizing radiation. Among these, essential oils, polyphenols, and lactic acid bacteria offer eco-friendly and non-toxic alternatives to conventional fungicides while demonstrating strong antimicrobial and antifungal properties; essential oils and polyphenols also possess antioxidant activity. Cold plasma and ionizing radiation enable rapid, non-thermal, and chemical-free decontamination processes. Nanoparticles and magnetic materials contribute advantages such as enhanced stability, controlled release, and ease of separation. Furthermore, this review explores recent advancements in the application of artificial intelligence, particularly machine learning methods, for the identification and classification of fungal species as well as for predicting the growth of toxigenic fungi and subsequent mycotoxin production in food products and culture media.

Artificial intelligence prediction model for readmission after DIEP flap breast reconstruction based on NSQIP data

BACKGROUND

Readmissions following deep inferior epigastric perforator (DIEP) flap breast reconstruction represent a significant healthcare burden, yet current risk prediction methods lack precision in identifying high-risk patients. We developed a machine learning model to predict 30-day readmission risk using a large national surgical quality database.

METHODS

This retrospective analysis examined 13,312 DIEP flap procedures from the American College of Surgeons National Surgical Quality Improvement Program database (2016-2022). A stacked machine learning model was developed incorporating patient demographics, comorbidities, operative characteristics, and laboratory values. Model performance was assessed using accuracy, precision, recall, and F1 score.

RESULTS

The overall readmission rate was 5.42% (723 patients). The stacked model achieved 88% accuracy and 79% recall for readmission prediction with an area under the receiver operating characteristic curve of 0.8921 (95% CI: 0.853-0.927) on the test set. Key predictors included days from operation until superficial incisional surgical site infection complications, operative time, body mass index, and preoperative albumin.

CONCLUSION

This stacked machine learning approach demonstrates strong predictive capability for post-DIEP flap readmissions, with high sensitivity for identifying at-risk patients. The model's performance suggests clinical utility in preoperative risk stratification and resource allocation. Implementation could enable targeted intervention strategies to potentially reduce readmission rates in high-risk populations.

Cytokine-Based Insights into Bloodstream Infections and Bacterial Gram Typing in ICU COVID-19 Patients

Background: Timely and accurate identification of bloodstream infections (BSIs) in intensive care unit (ICU) patients remains a key challenge, particularly in COVID-19 settings, where immune dysregulation can obscure early clinical signs. Methods: Cytokine profiling was evaluated to discriminate between ICU patients with and without BSIs, and, among those with confirmed BSIs, to further stratify bacterial infections by Gram type. Serum samples from 45 ICU COVID-19 patients were analyzed using a 21-cytokine panel, with feature selection applied to identify candidate markers. Results: A machine learning workflow identified key features, achieving robust performance metrics with AUC values up to 0.97 for BSI classification and 0.98 for Gram typing. Conclusions: In contrast to traditional approaches that focus on individual cytokines or simple ratios, the present analysis employed programmatically generated ratios between pro-inflammatory and anti-inflammatory cytokines, refined through feature selection. Although further validation in larger and more diverse cohorts is warranted, these findings underscore the potential of advanced cytokine-based diagnostics to enhance precision medicine in infection management.

Combining a Standardized Growth Class Assessment, UAV Sensor Data, GIS Processing, and Machine Learning Classification to Derive a Correlation with the Vigour and Canopy Volume of Grapevines

Assessing vines' vigour is essential for vineyard management and automatization of viticulture machines, including shaking adjustments of berry harvesters during grape harvest or leaf pruning applications. To address these problems, based on a standardized growth class assessment, labeled ground truth data of precisely located grapevines were predicted with specifically selected Machine Learning (ML) classifiers (Random Forest Classifier (RFC), Support Vector Machines (SVM)), utilizing multispectral UAV (Unmanned Aerial Vehicle) sensor data. The input features for ML model training comprise spectral, structural, and texture feature types generated from multispectral orthomosaics (spectral features), Digital Terrain and Surface Models (DTM/DSM- structural features), and Gray-Level Co-occurrence Matrix (GLCM) calculations (texture features). The specific features were selected based on extensive literature research, including especially the fields of precision agri- and viticulture. To integrate only vine canopy-exclusive features into ML classifications, different feature types were extracted and spatially aggregated (zonal statistics), based on a combined pixel- and object-based image-segmentation-technique-created vine row mask around each single grapevine position. The extracted canopy features were progressively grouped into seven input feature groups for model training. Model overall performance metrics were optimized with grid search-based hyperparameter tuning and repeated-k-fold-cross-validation. Finally, ML-based growth class prediction results were extensively discussed and evaluated for overall (accuracy, f1-weighted) and growth class specific- classification metrics (accuracy, user- and producer accuracy).