Integration of various sources of information for prediction of disease progression is an unmet need in glaucoma diagnostics. We designed a deep learning-based prognostic model incorporating clinical and structural data for forecasting functional glaucoma progression and compared its performance to clinicians. Retrospective, comparative cohort study of prognostic accuracy. We included 1599 eyes (908 patients) with definite or suspected glaucoma with ≥5 24-2 visual fields (VF) and 3 or more years of follow-up. VF mean deviation (MD) rates of change were estimated with linear regression. Sequential MD rates of change were estimated with each series spanning only 5 years of follow-up. VF progression was declared when four sequential statistically significant negative MD slopes were observed, and slope for the entire follow-up was significant. A convolutional neural network pretrained on ImageNet was designed to predict VF progression using baseline clinical and demographic data, disc photographs, and optical coherence tomography-derived global and sectoral retinal nerve fiber layer and macular thickness measurements. In addition, average intraocular pressure and treatment information during follow-up were put into the model. The same data for a subset of patients was provided to two clinicians to independently predict future progression. The model was validated on a separate cohort of eyes in which optical coherence tomography imaging was done with a different device (291 eyes). Model's area under receiver operating characteristic curves (AUC), accuracy, and area under the precision and recall curves. Average (SD) baseline MD and number of VF exams were -3.5 (4.9) dB and 10.1 (4.7). 399 eyes (25%) deteriorated. The best-performing model incorporated baseline disc photographs, and retinal nerve fiber layer and macular thickness: AUC, 0.839 (0.771-0.906), accuracy, 76.0% (62.0%-85.0%), and area under the precision and recall curves, 0.558 (0.385-0.733). Deep learning model significantly outperformed clinical graders (AUC : 0.629 [0.531-0738], P < .001 and 0.680 [0.584-0.776], P = .001, for grader one and two, respectively). Model performance was similar on the validation cohort (AUC: 0.754 [0.671-0.837], and accuracy: 77% [71%-82%], respectively, P = .122). The model performed well when predicting fast-progression, defined as MD rate <-1.0 dB/y (AUC: 0.869 [0.792-0.947]). Our newly designed deep learning model can combine baseline demographic and clinical data with widely available structural measurements and provide clinically relevant information for the prediction of glaucoma progression.

A Deep Learning Framework for Predicting Teprotumumab Treatment Response in Thyroid Eye Disease.

Mitigating data center bias in cancer classification: Transfer bias unlearning and feature size reduction via conflict-of-interest free multi-objective optimization.

Exploring the feature prioritization and data sampling of PCOS diagnosis via densely connected attention based squeeze deep learning detection model.

Structure-optimized deep forest model for railway port container reloading time prediction: A hybrid integer programming and Bayesian optimization approach

Deep learning prediction models for short-term solar photovoltaic power generation forecasting

Computationally efficient smart building energy management via deep reinforcement learning-enhanced model predictive control

Bioactive peptides-incorporated photo-crosslinking hydrogel for suture-free repair of corneal injuries.

Perturbation distillation and backdoor feature induction for universal defense in deep vision models

Machine learning (ML) is increasingly being used in food science due to its ability to extract insights from large datasets. However, the advantages of ML over traditional mechanistic knowledge-based models remain unclear, especially under the limited data conditions often encountered in food bioprocesses. This study aims to address this gap by critically evaluating supervised ML techniques-specifically decision trees, support vector machines, and neural networks-in comparison to a knowledge-based model (KB), using wine fermentation as a practical, experimental example. We evaluated these approaches in three tasks. Tasks 1 and 2 use time-series fermentation data to (1) classify industrial yeast strains based on their metabolite profiles and (2) predict fermentation dynamics. Task 3 focuses on creating a fast surrogate model using ML techniques applied to synthetic data generated by a mechanistic model. For yeast strain classification, we achieved our highest test accuracy of 74% when utilizing all available metabolite data. In predicting fermentation dynamics, the KB model outperformed the ML models, achieving an average normalized root mean squared error of approximately 6%. The ML models, when additional data was incorporated, had a prediction error of around 7.6%. Lastly, a deep learning surrogate model trained solely on synthetic, mechanistic data demonstrated very low errors (around 0.6%) on test sets, compared to the KB model, while also reducing simulation time by a factor of 30. Our findings highlight the significance of experimental design: although ML models perform well when trained on large and diverse datasets, they often struggle with limited data or when predicting outcomes beyond the conditions observed during training. In contrast, mechanistic models show better generalization and biological interpretability. The complementary nature of both approaches suggests that combining them can lead to more robust, data-informed design and control in complex fermentation systems. Leveraging these complementary strengths, we developed and validated a hybrid model that integrates knowledge-based predictions with a residual neural network to correct systematic errors, reducing overall NRMSE from 6% to 5% and improving prediction for most key compounds.

A novel deep learning-based model for fault diagnosis of complex systems with high uncertainty

A deep learning-based terrain feature-aware downscaling model for improved DEM and its derived topographic factor for soil erosion model

Mapping high-resolution real estate value distribution: a multi-attention deep generative model inspired by image inpainting

Entropy-informed weighting channel normalizing flow for deep generative models

De novo engineering of protein interactions: Retrospective and current advances.

Empirical evaluation of variability and multi-institutional generalizability of deep learning survival models: application to renal cancer CT scans.

Deep convolutional state space model as human activity recognizer

This work introduces a novel deep learning-based architecture, termed the Deep Belief Markov Model (DBMM), which provides efficient, model-formulation agnostic inference in Partially Observable Markov Decision Process (POMDP) problems. The POMDP framework allows for modeling and solving sequential decision-making problems under observation uncertainty. In complex, high-dimensional, partially observable environments, existing methods for inference based on exact computations (e.g., via Bayes' theorem) or sampling algorithms do not always scale well. Furthermore, ground truth states may not be available for learning the exact transition dynamics. DBMMs extend deep Markov models into the partially observable decision-making framework and allow efficient belief inference entirely based on available observation data via variational inference methods. By leveraging the potency of neural networks, DBMMs can infer and simulate non-linear relationships in the system dynamics and naturally scale to problems with high dimensionality and discrete or continuous variables. In addition, neural network parameters can be dynamically updated efficiently based on data availability. DBMMs can thus be used to infer a belief variable, thus enabling the derivation of POMDP solutions over the belief space. We evaluate the efficacy of the proposed methodology by evaluating the capability of model-formulation agnostic inference of DBMMs in benchmark problems that include discrete and continuous variables. Finally, we demonstrate the practical utility of the inferred beliefs in a downstream decision-making task, showing that an RL agent guided by DBMMs beliefs significantly outperforms powerful model-free baselines and achieves near-optimal performance.1.

Critical-size femoral defects in rats are a well-established model for preclinical bone regeneration research. Histological evaluation is essential for assessing healing but remains time-consuming and subject to observer variability. Machine learning, particularly convolutional neural networks (CNNs), offers potential for objective and scalable analysis of histological sections. We developed a modified U-Net model to perform semantic segmentation and classification of bone healing stages based on Movat pentachrome-stained histological sections (n=669). Five tissue classes (bone, cartilage, bone marrow, granulation tissue, background) were manually annotated to train the model. Data were split into training (64%), validation (16%), and test (20%) sets. The model then was used to segment and rank histological images. In addition, a subset of 20 independent test images was scored by four orthopedic experts, seven medical students, and the AI using a refined bone healing score ranging from -10 to +10. The model achieved high segmentation performance, particularly for bone and background. AI-generated healing scores showed strong correlation with expert ratings (Spearman r=0.819, p<0.0001) and similar accuracy to student ratings (mean absolute deviation: AI=0.468 vs. students=0.469; p=0.5753). ICC analysis confirmed excellent agreement between AI and experts (ICC=0.820) and revealed a significant difference favoring AI over students (bootstrap p=0.0466). This study introduces a CNN-based model capable of expert-level performance in the histological assessment of bone healing. It offers a reproducible and time-efficient tool for future preclinical applications.

Deep learning regression model based on data pairing and pseudo-label fusion for NIR predictive modeling in food and pharmaceutical quality analysis.