Deep learning image analysis for filamentous fungi taxonomic classification: Dealing with small datasets with class imbalance and hierarchical grouping.

Deep learning applications in taxonomic classification for animals and plants from images have become popular, while those for microorganisms are still lagging behind. Our study investigated the potential of deep learning for the taxonomic classification of hundreds of filamentous fungi from colony images, which is typically a task that requires specialized knowledge. We isolated soil fungi, annotated their taxonomy using standard molecular barcode techniques, and took images of the fungal colonies grown in petri dishes (n = 606). We applied a convolutional neural network with multiple training approaches and model architectures to deal with some common issues in ecological datasets: small amounts of data, class imbalance, and hierarchically structured grouping. Model performance was overall low, mainly due to the relatively small dataset, class imbalance, and the high morphological plasticity exhibited by fungal colonies. However, our approach indicates that morphological features like color, patchiness, and colony extension rate could be used for the recognition of fungal colonies at higher taxonomic ranks (i.e. phylum, class, and order). Model explanation implies that image recognition characters appear at different positions within the colony (e.g. outer or inner hyphae) depending on the taxonomic resolution. Our study suggests the potential of deep learning applications for a better understanding of the taxonomy and ecology of filamentous fungi amenable to axenic culturing. Meanwhile, our study also highlights some technical challenges in deep learning image analysis in ecology, highlighting that the domain of applicability of these methods needs to be carefully considered.

Towards consensual representation: Model-agnostic knowledge extraction for dual heterogeneous federated fault diagnosis.

Federated fault diagnosis has attracted increasing attention in industrial cloud-edge collaboration scenarios, where a ubiquitous assumption is that client models have the same architecture. Practically, this assumption cannot always be fulfilled due to requirements for personalized models, thereby resulting in the problem of model heterogeneity. Many approaches dealing with heterogeneous models tend to neglect the issue of representation bias, particularly in the context of non-identically and independently distributed data. In this article, to address the representation bias problem, Federated Model-Agnostic Knowledge Extraction (FedMAKE) is proposed. To bridge the information gap among clients, different from methods with public datasets, we initially develop two novel architecture-independent knowledge carriers. These carriers are derived based on the importance of process variables, without the need for additional datasets. Subsequently, we introduce a bi-directional distillation algorithm utilizing the two knowledge carriers. This algorithm facilitates the mutual transfer of knowledge embedded in carriers between a generative network and client models, thereby enabling the generation of fault data that is unbiased and well-balanced across categories. Furthermore, to mitigate the impact of statistical heterogeneity, we formulate a local objective for each client using two global knowledge carriers to guide local knowledge extraction and constrain client drift. Extensive experiments conducted on two prevalent industry datasets (TE and CWRU) illustrate that our proposed FedMAKE outperforms baseline methods. Specifically, FedMAKE enhances fault diagnosis accuracy by up to 11.7% on the TE dataset and up to 3.31% on the CWRU dataset compared to the sub-optimal method.

Explainable AI: Machine Learning Interpretation in Blackcurrant Powders.

Recently, explainability in machine and deep learning has become an important area in the field of research as well as interest, both due to the increasing use of artificial intelligence (AI) methods and understanding of the decisions made by models. The explainability of artificial intelligence (XAI) is due to the increasing consciousness in, among other things, data mining, error elimination, and learning performance by various AI algorithms. Moreover, XAI will allow the decisions made by models in problems to be more transparent as well as effective. In this study, models from the 'glass box' group of Decision Tree, among others, and the 'black box' group of Random Forest, among others, were proposed to understand the identification of selected types of currant powders. The learning process of these models was carried out to determine accuracy indicators such as accuracy, precision, recall, and F1-score. It was visualized using Local Interpretable Model Agnostic Explanations (LIMEs) to predict the effectiveness of identifying specific types of blackcurrant powders based on texture descriptors such as entropy, contrast, correlation, dissimilarity, and homogeneity. Bagging (Bagging_100), Decision Tree (DT0), and Random Forest (RF7_gini) proved to be the most effective models in the framework of currant powder interpretability. The measures of classifier performance in terms of accuracy, precision, recall, and F1-score for Bagging_100, respectively, reached values of approximately 0.979. In comparison, DT0 reached values of 0.968, 0.972, 0.968, and 0.969, and RF7_gini reached values of 0.963, 0.964, 0.963, and 0.963. These models achieved classifier performance measures of greater than 96%. In the future, XAI using agnostic models can be an additional important tool to help analyze data, including food products, even online.

Interpreting artificial intelligence models: a systematic review on the application of LIME and SHAP in Alzheimer's disease detection.

Explainable artificial intelligence (XAI) has gained much interest in recent years for its ability to explain the complex decision-making process of machine learning (ML) and deep learning (DL) models. The Local Interpretable Model-agnostic Explanations (LIME) and Shaply Additive exPlanation (SHAP) frameworks have grown as popular interpretive tools for ML and DL models. This article provides a systematic review of the application of LIME and SHAP in interpreting the detection of Alzheimer's disease (AD). Adhering to PRISMA and Kitchenham's guidelines, we identified 23 relevant articles and investigated these frameworks' prospective capabilities, benefits, and challenges in depth. The results emphasise XAI's crucial role in strengthening the trustworthiness of AI-based AD predictions. This review aims to provide fundamental capabilities of LIME and SHAP XAI frameworks in enhancing fidelity within clinical decision support systems for AD prognosis.

Improving prediction of N2O emissions during composting using model-agnostic meta-learning.

Nitrous oxide (N2O) represents a significant environmental challenge as a harmful, long-lived greenhouse gas that contributes to the depletion of stratospheric ozone and exacerbates global anthropogenic greenhouse warming. Composting is considered a promising and economically feasible strategy for the treatment of organic waste. However, recent research indicates that composting is a source of N2O, contributing to atmospheric pollution and greenhouse effect. Consequently, there is a need for the development of effective, cost-efficient methodologies to quantify N2O emissions accurately. In this study, we employed the model-agnostic meta-learning (MAML) method to improve the performance of N2O emissions prediction during manure composting. The highest R2 and lowest root mean squared error (RMSE) values achieved were 0.939 and 18.42 mg d-1, respectively. Five machine learning methods including the backpropagation neural network, extreme learning machine, integrated machine learning method based on ELM and random forest, gradient boosting decision tree, and extreme gradient boosting were adopted for comparison to further demonstrate the effectiveness of the MAML prediction model. Feature analysis showed that moisture content of structure material and ammonium concentration during composting process were the two most significant features affecting N2O emissions. This study serves as proof of the application of MAML during N2O emissions prediction, further giving new insights into the effects of manure material properties and composting process data on N2O emissions. This approach helps determining the strategies for mitigating N2O emissions.

Interpretable machine learning model for early prediction of 28-day mortality in ICU patients with sepsis-induced coagulopathy: development and validation.

OBJECTIVE: Sepsis-induced coagulopathy (SIC) is extremely common in individuals with sepsis, significantly associated with poor outcomes. This study attempted to develop an interpretable and generalizable machine learning (ML) model for early predicting the risk of 28-day death in patients with SIC. METHODS: In this retrospective cohort study, we extracted SIC patients from the Medical Information Mart for Intensive Care III (MIMIC-III), MIMIC-IV, and eICU-CRD database according to Toshiaki Iba's scale. And the overlapping in the MIMIC-IV was excluded for this study. Afterward, only the MIMIC-III cohort was randomly divided into the training set, and the internal validation set according to the ratio of 7:3, while the MIMIC-IV and eICU-CRD databases were considered the external validation sets. The predictive factors for 28-day mortality of SIC patients were determined using recursive feature elimination combined with tenfold cross-validation (RFECV). Then, we constructed models using ML algorithms. Multiple metrics were used for evaluation of performance of the models, including the area under the receiver operating characteristic curve (AUROC), area under the precision recall curve (AUPRC), accuracy, sensitivity, specificity, negative predictive value, positive predictive value, recall, and F1 score. Finally, Shapley Additive Explanations (SHAP), Local Interpretable Model-Agnostic Explanations (LIME) were employed to provide a reasonable interpretation for the prediction results. RESULTS: A total of 3280, 2798, and 1668 SIC patients were screened from MIMIC-III, MIMIC-IV, and eICU-CRD databases, respectively. Seventeen features were selected to construct ML prediction models. XGBoost had the best performance in predicting the 28-day mortality of SIC patients, with AUC of 0.828, 0.913 and 0.923, the AUPRC of 0.807, 0.796 and 0.921, the accuracy of 0.785, 0.885 and 0.891, the F1 scores were 0.63, 0.69 and 0.70 in MIMIC-III (internal validation set), MIMIC-IV, and eICU-CRD databases. The importance ranking and SHAP analyses showed that initial SOFA score, red blood cell distribution width (RDW), and age were the top three critical features in the XGBoost model. CONCLUSIONS: We developed an optimal and explainable ML model to predict the risk of 28-day death of SIC patients 28-day death risk. Compared with conventional scoring systems, the XGBoost model performed better. The model established will have the potential to improve the level of clinical practice for SIC patients.

A few-shot link prediction framework to drug repurposing using multi-level attention network.

Drug repurposing is a strategy aiming at uncovering novel medical indications of approved drugs. This process of discovery can be effectively represented as a link prediction task within a medical knowledge graph by predicting the missing relation between the disease entity and the drug entity. Typically, the links to be predicted pertain to rare types, thereby necessitating the task of few-shot link prediction. However, the sparsity of neighborhood information and weak triplet interactions result in less effective representations, which brings great challenges to the few-shot link prediction. Therefore, in this paper, we proposed a meta-learning framework based on a multi-level attention network (MLAN) to capture valuable information in the few-shot scenario for drug repurposing. First, the proposed method utilized a gating mechanism and a graph attention network to effectively filter noise information and highlight the valuable neighborhood information, respectively. Second, the proposed commonality relation learner, employing a set transformer, effectively captured triplet-level interactions while remaining insensitive to the size of the support set. Finally, a model-agnostic meta-learning training strategy was employed to optimize the model quickly on each meta task. We conducted validation of the proposed method on two datasets specifically designed for few-shot link prediction in medical field: COVID19-One and BIOKG-One. Experimental results showed that the proposed model had significant advantages over state-of-the-art few-shot link prediction methods. Results also highlighted the valuable insights of the proposed method, which successfully integrated the components within a unified meta-learning framework for drug repurposing.

Convolutional neural network based data interpretable framework for Alzheimer's treatment planning.

Alzheimer's disease (AD) is a neurological disorder that predominantly affects the brain. In the coming years, it is expected to spread rapidly, with limited progress in diagnostic techniques. Various machine learning (ML) and artificial intelligence (AI) algorithms have been employed to detect AD using single-modality data. However, recent developments in ML have enabled the application of these methods to multiple data sources and input modalities for AD prediction. In this study, we developed a framework that utilizes multimodal data (tabular data, magnetic resonance imaging (MRI) images, and genetic information) to classify AD. As part of the pre-processing phase, we generated a knowledge graph from the tabular data and MRI images. We employed graph neural networks for knowledge graph creation, and region-based convolutional neural network approach for image-to-knowledge graph generation. Additionally, we integrated various explainable AI (XAI) techniques to interpret and elucidate the prediction outcomes derived from multimodal data. Layer-wise relevance propagation was used to explain the layer-wise outcomes in the MRI images. We also incorporated submodular pick local interpretable model-agnostic explanations to interpret the decision-making process based on the tabular data provided. Genetic expression values play a crucial role in AD analysis. We used a graphical gene tree to identify genes associated with the disease. Moreover, a dashboard was designed to display XAI outcomes, enabling experts and medical professionals to easily comprehend the prediction results.

A Web-Based Calculator to Predict Early Death Among Patients With Bone Metastasis Using Machine Learning Techniques: Development and Validation Study.

BACKGROUND: Patients with bone metastasis often experience a significantly limited survival time, and a life expectancy of <3 months is generally regarded as a contraindication for extensive invasive surgeries. In this context, the accurate prediction of survival becomes very important since it serves as a crucial guide in making clinical decisions. OBJECTIVE: This study aimed to develop a machine learning-based web calculator that can provide an accurate assessment of the likelihood of early death among patients with bone metastasis. METHODS: This study analyzed a large cohort of 118,227 patients diagnosed with bone metastasis between 2010 and 2019 using the data obtained from a national cancer database. The entire cohort of patients was randomly split 9:1 into a training group (n=106,492) and a validation group (n=11,735). Six approaches-logistic regression, extreme gradient boosting machine, decision tree, random forest, neural network, and gradient boosting machine-were implemented in this study. The performance of these approaches was evaluated using 11 measures, and each approach was ranked based on its performance in each measure. Patients (n=332) from a teaching hospital were used as the external validation group, and external validation was performed using the optimal model. RESULTS: In the entire cohort, a substantial proportion of patients (43,305/118,227, 36.63%) experienced early death. Among the different approaches evaluated, the gradient boosting machine exhibited the highest score of prediction performance (54 points), followed by the neural network (52 points) and extreme gradient boosting machine (50 points). The gradient boosting machine demonstrated a favorable discrimination ability, with an area under the curve of 0.858 (95% CI 0.851-0.865). In addition, the calibration slope was 1.02, and the intercept-in-large value was -0.02, indicating good calibration of the model. Patients were divided into 2 risk groups using a threshold of 37% based on the gradient boosting machine. Patients in the high-risk group (3105/4315, 71.96%) were found to be 4.5 times more likely to experience early death compared with those in the low-risk group (1159/7420, 15.62%). External validation of the model demonstrated a high area under the curve of 0.847 (95% CI 0.798-0.895), indicating its robust performance. The model developed by the gradient boosting machine has been deployed on the internet as a calculator. CONCLUSIONS: This study develops a machine learning-based calculator to assess the probability of early death among patients with bone metastasis. The calculator has the potential to guide clinical decision-making and improve the care of patients with bone metastasis by identifying those at a higher risk of early death.

MW-MADDPG: a meta-learning based decision-making method for collaborative UAV swarm.

Unmanned Aerial Vehicles (UAVs) have gained popularity due to their low lifecycle cost and minimal human risk, resulting in their widespread use in recent years. In the UAV swarm cooperative decision domain, multi-agent deep reinforcement learning has significant potential. However, current approaches are challenged by the multivariate mission environment and mission time constraints. In light of this, the present study proposes a meta-learning based multi-agent deep reinforcement learning approach that provides a viable solution to this problem. This paper presents an improved MAML-based multi-agent deep deterministic policy gradient (MADDPG) algorithm that achieves an unbiased initialization network by automatically assigning weights to meta-learning trajectories. In addition, a Reward-TD prioritized experience replay technique is introduced, which takes into account immediate reward and TD-error to improve the resilience and sample utilization of the algorithm. Experiment results show that the proposed approach effectively accomplishes the task in the new scenario, with significantly improved task success rate, average reward, and robustness compared to existing methods.

Enhanced joint hybrid deep neural network explainable artificial intelligence model for 1-hr ahead solar ultraviolet index prediction.

BACKGROUND AND OBJECTIVE: Exposure to solar ultraviolet (UV) radiation can cause malignant keratinocyte cancer and eye disease. Developing a user-friendly, portable, real-time solar UV alert system especially or wearable electronic mobile devices can help reduce the exposure to UV as a key measure for personal and occupational management of the UV risks. This research aims to design artificial intelligence-inspired early warning tool tailored for short-term forecasting of UV index (UVI) integrating satellite-derived and ground-based predictors for Australian hotspots receiving high UV exposures. The study further improves the trustworthiness of the newly designed tool using an explainable artificial intelligence approach. METHODS: An enhanced joint hybrid explainable deep neural network model (called EJH-X-DNN) is constructed involving two phases of feature selection and hyperparameter tuning using Bayesian optimization. A comprehensive assessment of EJH-X- DNN is conducted with six other competing benchmarked models. The proposed model is explained locally and globally using robust model-agnostic explainable artificial intelligence frameworks such as Local Interpretable Model-Agnostic Explanations (LIME), Shapley additive explanations (SHAP), and permutation feature importance (PFI). RESULTS: The newly proposed model outperformed all benchmarked models for forecasting hourly horizons UVI, with correlation coefficients of 0.900, 0.960, 0.897, and 0.913, respectively, for Darwin, Alice Springs, Townsville, and Emerald hotspots. According to the combined local and global explainable model outcomes, the site-based results indicate that antecedent lagged memory of UVI and solar zenith angle are influential features. Predictions made by EJH-X-DNN model are strongly influenced by factors such as ozone effect, cloud conditions, and precipitation. CONCLUSION: With its superiority and skillful interpretation, the UVI prediction system reaffirms its benefits for providing real-time UV alerts to mitigate risks of skin and eye health complications, reducing healthcare costs and contributing to outdoor exposure policy.

Adaptive visual detection of industrial product defects.

Visual inspection of the appearance defects on industrial products has always been a research hotspot pursued by industry and academia. Due to the lack of samples in the industrial defect dataset and the serious class imbalance, deep learning technology cannot be directly applied to industrial defect visual inspection to meet the real application needs. Transfer learning is a good choice to deal with insufficient samples. However, cross-dataset bias is unavoidable during simple knowledge transfer. We noticed that the appearance defects of industrial products are similar, and most defects can be classified as stains or texture jumps, which provides a research basis for building a universal and adaptive industrial defect detection model. In this article, based on the idea of model-agnostic meta-learning (MAML), we propose an adaptive industrial defect detection model through learning from multiple known industrial defect datasets and then transfer it to the novel anomaly detection tasks. In addition, the Siamese network is used to extract differential features to minimize the influence of defect types on model generalization, and can also highlight defect features and improve model detection performance. At the same time, we add a coordinate attention mechanism to the model, which realizes the feature enhancement of the region of interest in terms of two coordinate dimensions. In the simulation experiments, we construct and publish a visual defect dataset of injection molded bottle cups, termed BC defects, which can complement existing industrial defect visual data benchmarks. Simulation results based on BC defects dataset and other public datasets have demonstrated the effectiveness of the proposed general visual detection model for industrial defects. The dataset and code are available at https://github.com/zhg-SZPT/MeDetection.

Comprehensible Machine-Learning-Based Models for the Pre-Emptive Diagnosis of Multiple Sclerosis Using Clinical Data: A Retrospective Study in the Eastern Province of Saudi Arabia.

Multiple Sclerosis (MS) is characterized by chronic deterioration of the nervous system, mainly the brain and the spinal cord. An individual with MS develops the condition when the immune system begins attacking nerve fibers and the myelin sheathing that covers them, affecting the communication between the brain and the rest of the body and eventually causing permanent damage to the nerve. Patients with MS (pwMS) might experience different symptoms depending on which nerve was damaged and how much damage it has sustained. Currently, there is no cure for MS; however, there are clinical guidelines that help control the disease and its accompanying symptoms. Additionally, no specific laboratory biomarker can precisely identify the presence of MS, leaving specialists with a differential diagnosis that relies on ruling out other possible diseases with similar symptoms. Since the emergence of Machine Learning (ML) in the healthcare industry, it has become an effective tool for uncovering hidden patterns that aid in diagnosing several ailments. Several studies have been conducted to diagnose MS using ML and Deep Learning (DL) models trained using MRI images, achieving promising results. However, complex and expensive diagnostic tools are needed to collect and examine imaging data. Thus, the intention of this study is to implement a cost-effective, clinical data-driven model that is capable of diagnosing pwMS. The dataset was obtained from King Fahad Specialty Hospital (KFSH) in Dammam, Saudi Arabia. Several ML algorithms were compared, namely Support Vector Machine (SVM), Decision Tree (DT), Logistic Regression (LR), Random Forest (RF), Extreme Gradient Boosting (XGBoost), Adaptive Boosting (AdaBoost), and Extra Trees (ET). The results indicated that the ET model outpaced the rest with an accuracy of 94.74%, recall of 97.26%, and precision of 94.67%.

Deep Learning Algorithms with LIME and Similarity Distance Analysis on COVID-19 Chest X-ray Dataset.

In the last few years, many types of research have been conducted on the most harmful pandemic, COVID-19. Machine learning approaches have been applied to investigate chest X-rays of COVID-19 patients in many respects. This study focuses on the deep learning algorithm from the standpoint of feature space and similarity analysis. Firstly, we utilized Local Interpretable Model-agnostic Explanations (LIME) to justify the necessity of the region of interest (ROI) process and further prepared ROI via U-Net segmentation that masked out non-lung areas of images to prevent the classifier from being distracted by irrelevant features. The experimental results were promising, with detection performance reaching an overall accuracy of 95.5%, a sensitivity of 98.4%, a precision of 94.7%, and an F1 score of 96.5% on the COVID-19 category. Secondly, we applied similarity analysis to identify outliers and further provided an objective confidence reference specific to the similarity distance to centers or boundaries of clusters while inferring. Finally, the experimental results suggested putting more effort into enhancing the low-accuracy subspace locally, which is identified by the similarity distance to the centers. The experimental results were promising, and based on those perspectives, our approach could be more flexible to deploy dedicated classifiers specific to different subspaces instead of one rigid end-to-end black box model for all feature space.

The grammar of interactive explanatory model analysis.

The growing need for in-depth analysis of predictive models leads to a series of new methods for explaining their local and global properties. Which of these methods is the best? It turns out that this is an ill-posed question. One cannot sufficiently explain a black-box machine learning model using a single method that gives only one perspective. Isolated explanations are prone to misunderstanding, leading to wrong or simplistic reasoning. This problem is known as the Rashomon effect and refers to diverse, even contradictory, interpretations of the same phenomenon. Surprisingly, most methods developed for explainable and responsible machine learning focus on a single-aspect of the model behavior. In contrast, we showcase the problem of explainability as an interactive and sequential analysis of a model. This paper proposes how different Explanatory Model Analysis (EMA) methods complement each other and discusses why it is essential to juxtapose them. The introduced process of Interactive EMA (IEMA) derives from the algorithmic side of explainable machine learning and aims to embrace ideas developed in cognitive sciences. We formalize the grammar of IEMA to describe human-model interaction. It is implemented in a widely used human-centered open-source software framework that adopts interactivity, customizability and automation as its main traits. We conduct a user study to evaluate the usefulness of IEMA, which indicates that an interactive sequential analysis of a model may increase the accuracy and confidence of human decision making.

Ensemble-based genetic algorithm explainer with automized image segmentation: A case study on melanoma detection dataset.

Explainable Artificial Intelligence (XAI) makes AI understandable to the human user particularly when the model is complex and opaque. Local Interpretable Model-agnostic Explanations (LIME) has an image explainer package that is used to explain deep learning models. The image explainer of LIME needs some parameters to be manually tuned by the expert in advance, including the number of top features to be seen and the number of superpixels in the segmented input image. This parameter tuning is a time-consuming task. Hence, with the aim of developing an image explainer that automizes image segmentation, this paper proposes Ensemble-based Genetic Algorithm Explainer (EGAE) for melanoma cancer detection that automatically detects and presents the informative sections of the image to the user. EGAE has three phases. First, the sparsity of chromosomes in GAs is determined heuristically. Then, multiple GAs are executed consecutively. However, the difference between these GAs are in different number of superpixels in the input image that result in different chromosome lengths. Finally, the results of GAs are ensembled using consensus and majority votings. This paper also introduces how Euclidean distance can be used to calculate the distance between the actual explanation (delineated by experts) and the calculated explanation (computed by the explainer) for accuracy measurement. Experimental results on a melanoma dataset show that EGAE automatically detects informative lesions, and it also improves the accuracy of explanation in comparison with LIME efficiently. The python codes for EGAE, the ground truths delineated by clinicians, and the melanoma detection dataset are available at https://github.com/KhaosResearch/EGAE.

Why did AI get this one wrong? - Tree-based explanations of machine learning model predictions.

Increasingly complex learning methods such as boosting, bagging and deep learning have made ML models more accurate, but harder to interpret and explain, culminating in black-box machine learning models. Model developers and users alike are often presented with a trade-off between performance and intelligibility, especially in high-stakes applications like medicine. In the present article we propose a novel methodological approach for generating explanations for the predictions of a generic machine learning model, given a specific instance for which the prediction has been made. The method, named AraucanaXAI, is based on surrogate, locally-fitted classification and regression trees that are used to provide post-hoc explanations of the prediction of a generic machine learning model. Advantages of the proposed XAI approach include superior fidelity to the original model, ability to deal with non-linear decision boundaries, and native support to both classification and regression problems. We provide a packaged, open-source implementation of the AraucanaXAI method and evaluate its behaviour in a number of different settings that are commonly encountered in medical applications of AI. These include potential disagreement between the model prediction and physician's expert opinion and low reliability of the prediction due to data scarcity.

Combining Model-Agnostic Meta-Learning and Transfer Learning for Regression.

For cases in which a machine learning model needs to be adapted to a new task, various approaches have been developed, including model-agnostic meta-learning (MAML) and transfer learning. In this paper, we investigate how the differences in the data distributions between the old tasks and the new target task impact performance in regression problems. By performing experiments, we discover that these differences greatly affect the relative performance of different adaptation methods. Based on this observation, we develop ensemble schemes combining multiple adaptation methods that can handle a wide range of data distribution differences between the old and new tasks, thus offering more stable performance for a wide range of tasks. For evaluation, we consider three regression problems of sinusoidal fitting, virtual reality motion prediction, and temperature forecasting. The evaluation results demonstrate that the proposed ensemble schemes achieve the best performance among the considered methods in most cases.

Personalized screening and risk profiles for Mild Cognitive Impairment via a Machine Learning Framework: Implications for general practice.

OBJECTIVES: Diagnosis of Mild Cognitive Impairment (MCI) requires lengthy diagnostic procedures, typically available at tertiary Health Care Centers (HCC). This prospective study evaluated a flexible Machine Learning (ML) framework toward identifying persons with MCI or dementia based on information that can be readily available in a primary HC setting. METHODS: Demographic and clinical data, informant ratings of recent behavioral changes, self-reported anxiety and depression symptoms, subjective cognitive complaints, and Mini Mental State Examination (MMSE) scores were pooled from two aging cohorts from the island of Crete, Greece (N = 763 aged 60-93 years) comprising persons diagnosed with MCI (n = 277) or dementia (n = 153), and cognitively non-impaired persons (CNI, n = 333). A Balanced Random Forest Classifier was used for classification and variable importance-based feature selection in nested cross-validation schemes (CNI vs MCI, CNI vs Dementia, MCI vs Dementia). Global-level model-agnostic analyses identified predictors displaying nonlinear behavior. Local level agnostic analyses pinpointed key predictor variables for a given classification result after statistically controlling for all other predictors in the model. RESULTS: Classification of MCI vs CNI was achieved with improved sensitivity (74 %) and comparable specificity (73 %) compared to MMSE alone (37.2 % and 94.3 %, respectively). Additional high-ranking features included age, education, behavioral changes, multicomorbidity and polypharmacy. Higher classification accuracy was achieved for MCI vs Dementia (sensitivity/specificity = 87 %) and CNI vs Dementia (sensitivity/specificity = 94 %) using the same set of variables. Model agnostic analyses revealed notable individual variability in the contribution of specific variables toward a given classification result. CONCLUSIONS: Improved capacity to identify elderly with MCI can be achieved by combining demographic and medical information readily available at the PHC setting with MMSE scores, and informant ratings of behavioral changes. Explainability at the patient level may help clinicians identify specific predictor variables and patient scores to a given prediction outcome toward personalized risk assessment.

Automated Machine Learning in Predicting 30-Day Mortality in Patients with Non-Cholestatic Cirrhosis.

OBJECTIVE: To evaluate the feasibility of automated machine learning (AutoML) in predicting 30-day mortality in non-cholestatic cirrhosis. METHODS: A total of 932 cirrhotic patients were included from the First Affiliated Hospital of Soochow University between 2014 and 2020. Participants were divided into training and validation datasets at a ratio of 8.5:1.5. Models were developed on the H2O AutoML platform in the training dataset, and then were evaluated in the validation dataset by area under receiver operating characteristic curves (AUC). The best AutoML model was interpreted by SHapley Additive exPlanation (SHAP) Plot, Partial Dependence Plots (PDP), and Local Interpretable Model Agnostic Explanation (LIME). RESULTS: The model, based on the extreme gradient boosting (XGBoost) algorithm, performed better (AUC 0.888) than the other AutoML models (logistic regression 0.673, gradient boost machine 0.886, random forest 0.866, deep learning 0.830, stacking 0.850), as well as the existing scorings (the model of end-stage liver disease [MELD] score 0.778, MELD-Na score 0.782, and albumin-bilirubin [ALBI] score 0.662). The most key variable in the XGBoost model was high-density lipoprotein cholesterol, followed by creatinine, white blood cell count, international normalized ratio, etc. Conclusion: The AutoML model based on the XGBoost algorithm presented better performance than the existing scoring systems for predicting 30-day mortality in patients with non-cholestatic cirrhosis. It shows the promise of AutoML in its future medical application.