Random Forest Algorithm for the Classification of Neuroimaging Data in Alzheimer's Disease: A Systematic Review

Artificial intelligence strategies based on random forests for detection of AI-generated content in public health

OBJECTIVES

To train and test a Random Forest machine learning model with the ability to distinguish AI-generated from human-generated textual content in the domain of public health, and public health policy.

STUDY DESIGN

Supervised machine learning study.

METHODS

A dataset comprising 1000 human-generated and 1000 AI-generated paragraphs was created. Textual features were extracted using TF-IDF vectorization which calculates term frequency (TF) and Inverse document frequency (IDF), and combines the two measures to produce a score for individual terms. The Random Forest model was trained and tested using the Scikit-Learn library and Jupyter Notebook service in the Google Colab cloud-based environment, with Google CPU hardware acceleration.

RESULTS

The model achieved a classification accuracy of 81.8 % and an area under the ROC curve of 0.9. For human-generated content, precision, recall, and F1-score were 0.85, 0.78, and 0.81, respectively. For AI-generated content, these metrics were 0.79, 0.86, and 0.82. The MCC value of 0.64 indicated moderate to strong predictive power. The model demonstrated robust sensitivity (recall for AI-generated class) of 0.86 and specificity (recall for human-generated class) of 0.78.

CONCLUSIONS

The model exhibited acceptable performance, as measured by classification accuracy, area under the receiver operating characteristic curve, and other metrics. This approach can be further improved by incorporating additional supervised machine learning techniques and serves as a foundation for the future development of a sophisticated and innovative AI system. Such a system could play a crucial role in combating misinformation and enhancing public trust across various government platforms, media outlets, and social networks.

Role of eccentricity based topological descriptors to predict anti-HIV drugs attributes with supervised machine learning algorithms

Chemical graphs are mathematical representations of molecular structures, where atoms are represented as vertices, while chemical bonds are depicted as edges of a graph. The chemical graphs are widely used in cheminformatics to analyze molecular properties, predict biological activity and design new drugs. A topological index (TI) in drug design is a numerical descriptor of a molecular graph that correlates its structure with biological activity and physicochemical properties. The aim of this study is to use the concepts of chemical graphs to examine the molecular characteristics and structural design of anti-HIV drugs. Secondly, we have utilized the concept of supervised machine learning to create a predictive model. Finally, we have compared the results of different machine learning algorithms such as Random Forest algorithm and XGBoost algorithm. These methods not only enhance drug effectiveness but also aid in predicting new drug candidates.

Which approach better predicts diabetes: Traditional econometric methods or machine learning? Evidence from a cross-sectional study in South Korea

To prevent chronic disease from getting worse, it is important to detect and predict it at an early stage. Therefore, the accuracy of the prediction is particularly important. To investigate the accuracy of different methods, this study compares the out-of-sample errors of machine learning algorithms and traditional econometric methods in predicting diabetes. The object of prediction in this study is fasting blood glucose, and the machine learning algorithms used are stepwise selection, bagging, random forests and support vector machine (SVM). In addition, we demonstrate the linear combination of above machine learning algorithms in this study. The findings indicate that the combined model outperforms both traditional econometric models and individual machine learning algorithms. However, the predictive performance of individual machine learning models does not consistently surpass that of traditional econometric approaches. Based on the data characteristics analyzed in this study, a possible explanation for this finding is that traditional econometric methods may exhibit superior performance in linear data prediction. Finally, the analysis of variable importance suggests that medical indicators and physical condition may play a more significant role in determining fasting blood glucose compared to hereditary factors. To further validate our results, we applied the same methodology to predict hypertension using the same dataset. The findings similarly indicated that the predictive ability of individual machine learning algorithms does not always surpass that of traditional econometric models. And a linear combination of the four machine learning algorithms enhances the predictive accuracy for hypertension.

Neuroanatomical associations with autistic characteristics in those with acute anorexia nervosa and weight-restored individuals

Common neuroanatomical regions are associated with both states of anorexia nervosa (AN) and autistic characteristics, but restoration of body mass index (BMI) has been associated with decreased presentation of autistic characteristics in some individuals with AN. This study aims to examine neuroanatomical correlates associated with autistic characteristics in those with acute anorexia nervosa (ac-AN) and those previously diagnosed with AN but whose weight has been restored (WR). In total, 183 individuals (healthy controls [HCs] = 67; n[ac-AN] = 68; n[WR] = 48) from the Brain imaging of Emotion And Cognition of adolescents with Anorexia Nervosa (BEACON) study were included, with autistic characteristics determined in both ac-AN and WR individuals (n = 116). To further examine BMI, ac-AN and WR group associations were compared. Random forest regression (RFR) models examined whether autistic characteristics and morphology of the anterior cingulate cortex (ACC), middle frontal gyrus (MFG), and orbitofrontal cortex (OFC) were able to predict future levels of social anhedonia and alexithymia. Group-wise differences were identified within the volume and surface area of the MFG and OFC, which were unrelated to BMI. Autistic characteristics were inversely associated with MFG and ACC volume, with differences in associations between ac-AN and WR groups seen in the surface area of the MFG. RFR models identified moderate-to-weak performance and found that autistic characteristics were not important predictive features in a priori and exploratory models. Findings suggest that the presence of autistic characteristics in those with ac-AN are associated with the volume of the MFG and are unrelated to BMI restoration.

Predicting the progression of MCI and Alzheimer's disease on structural brain integrity and other features with machine learning

Machine learning (ML) on structural MRI data shows high potential for classifying Alzheimer's disease (AD) progression, but the specific contribution of brain regions, demographics, and proteinopathy remains unclear. Using Alzheimer's Disease Neuroimaging Initiative (ADNI) data, we applied an extreme gradient-boosting algorithm and SHAP (SHapley Additive exPlanations) values to classify cognitively normal (CN) older adults, those with mild cognitive impairment (MCI) and AD dementia patients. Features included structural MRI, CSF status, demographics, and genetic data. Analyses comprised one cross-sectional multi-class classification (CN vs. MCI vs. AD dementia, n = 568) and two longitudinal binary-class classifications (CN-to-MCI converters vs. CN stable, n = 92; MCI-to-AD converters vs. MCI stable, n = 378). All classifications achieved 70-77% accuracy and 61-83% precision. Key features were CSF status, hippocampal volume, entorhinal thickness, and amygdala volume, with a clear dissociation: hippocampal properties contributed to the conversion to MCI, while the entorhinal cortex characterized the conversion to AD dementia. The findings highlight explainable, trajectory-specific insights into AD progression.

Machine learning with hyperparameter optimization applied in facies-supported permeability modeling in carbonate oil reservoirs

Most carbonate reservoirs exhibit heterogeneous pore distribution, whereby the matrix displays low permeability, thus impeding the flow of oil. On the other hand, highly permeable fractures function as the main flow conduits within such reservoirs. Permeability measurements are obtained from core and well test analysis, which are too expensive and not available for many wells. Therefore, accurate permeability prediction is a vital step in developing an efficient field development plan, as it plays a pivotal role in the accurate distribution of 3D petrophysical properties throughout a reservoir. Machine learning (ML) algorithms are now widely applied to predict core permeability using conventional well logs to build a model for permeability prediction in uncored wells. This review considers the performance of six ML algorithms (LightGBM, CATBoost, XGBoost, Adaboost, random forest and gradient boosting) for permeability prediction from a high-quality dataset. The dataset incorporates multiple well-log inputs (gamma ray, caliper, density, neutron porosity, shallow and deep resistivity, total porosity, spontaneous potential, water saturation, depth, and facies) in addition to direct core permeability and porosity measurements. Data pre-processing techniques applied include missing data imputation, scale correction, normalization with three different transformations (log, Box-Cox, and NST) and outlier detection. To enhance the ML performance, two search algorithms (random search and Bayesian optimization) are compared in their ability to tune the ML hyperparameters. There is a need to identify a suitable parameter space, especially when the target variable range is changing. ML performance was evaluated with four evaluation metrics (RMSE, MAE, R2, and Adjusted R2). Results showed that the XGBoost algorithm with configuration of (RS as search algorithm, Box Cox as the normalization method, Z-score for outlier detection, without scale correction, old parameter space) delivered the best prediction performance for permeability with RMSE values of 6.9 md and 9.78 md for training and testing, respectively.

Leveraging machine learning in precision medicine to unveil organochlorine pesticides as predictive biomarkers for thyroid dysfunction

Exposure to organochlorine pesticides (OCPs) poses significant health risks, including cancer, endocrine dysregulation, neurological disorders, and reproductive disruption. This study investigates the association between OCP exposure and thyroid disturbances using machine learning (ML) models. Blood samples were analyzed for the concentration of 16 OCPs and thyroid hormones (T3, T4, TSH) using traditional methods such as Logistic Regression and least absolute shrinkage and selection operator (LASSO) and more advanced ML models such as Random Forest (RF), Support Vector Machine (SVM), XGBoost, and Gradient Boosting Machine (GBM). High frequencies of OCPs, including Heptachlor, Heptachlor epoxide, γ-HCH, Aldrin, Endrin aldehyde, α-endosulfan, and Methoxychlor, were detected in over 70% of serum samples. The RF and GBM models achieved the highest accuracy at 90.91%, while XGBoost demonstrated a high ROC-AUC score of 94.02%. The SVM model also showed robust performance, whereas Logistic Regression exhibited weaker results. Our findings highlighted specific OCPs, such as Methoxychlor, p,p-DDT, Heptachlor, Endrin, and various HCH isomers, could impact thyroid function. The study supports a strong correlation between OCP exposure and thyroid dysfunction, demonstrating high accuracy in classifying thyroid status using ML models. Significant OCPs identified include p, p-DDT, Methoxychlor, Endrin, β-endosulfan, and Heptachlor, which are associated with thyroid dysfunction.

Untargeted Metabolomic Analysis of Exhaled Breath Condensate Identifies Disease-Specific Signatures in Adults With Asthma

PURPOSE

An objective test for the auxiliary diagnosis of asthma is still lacking. The aim of this study was to discriminate asthma signatures via an untargeted metabolomic analysis of exhaled breath condensate.

MATERIALS AND METHODS

This study enrolled 19 patients diagnosed with asthma and 23 healthy volunteers. Samples of exhaled breath condensate (EBC) were collected from both groups. Untargeted metabolomic analyses of EBC were used to identify disease-specific signatures for asthma.

RESULT

There were 30 identifiable differentially expressed metabolites and 7 disordered metabolic pathways between the EBCs of asthmatic patients and healthy control subjects. The main differential pathways included biosynthesis of unsaturated fatty acids, HIF-1 signalling pathway, Glutathione metabolism, Ascorbate and aldarate metabolism, and fatty acid biosynthesis. The integrated machine learning method was used to construct an asthma EBC metabolomic signature model from four differential metabolites; 3,4'-dimethoxy-2'-hydroxychalcone, C17-sphinganine, (z)-6-octadecenoic acid, and 2-butylaniline. The model showed a high level of discrimination efficiency (area under curve (AUC) = 0.98), with robust validation through logistic regression (LR), random forest (RF), and support vector machine (SVM) (LR AUC = 0.98, RF AUC = 0.94, SVM AUC = 1.00). The discriminative ability of the EBC metabolomic signature model in both the training set (AUC = 1.0) and testing data (AUC = 0.817) was superior to that of FeNO (AUC = 0.515 and 0.567, respectively) and FEV1/FVC % predicted (AUC = 0.767 and 0.765, respectively). Among the four biomarkers, (z)-6-octadecenoic acid was significantly correlated with serum IgE.

CONCLUSION

The EBC metabolomic signature model demonstrated good feasibility for assisting in the diagnosis of asthma in adults.

CRISPR-Responsive Reprogrammable Label-Free Fluorescent Nanoclusters for ML-Assisted Pathogenic Genome Detection on Solid Substrates

The development of a paper-based genome detection assay using target-responsive DNA-templated silver nanoclusters (DFN-1) is presented. The reported nanoclusters exhibit intrinsic fluorescence, which is regulated by the cleavage of the DNA template surrounding the silver core. To enable the nanoclusters to respond to a specific genome, CRISPR-Cas12a is employed for highly specific and programmable digestion of the nanoclusters. Upon detection of the target, the DNA template is cleaved by the CRISPR-Cas12a complex, leading to a reduction in fluorescence. This assay successfully demonstrates for the detection of the Salmonella genome in the liquid phase and on 2 mm solid filter paper discs. By altering only the crRNA in the CRISPR complex, the assay is programmed to detect two different Salmonella serotypes. The selectivity of the assay is evaluated in DNA mixtures with and without the target genomic fragments. The assay also demonstrates the detection of as little as 33 copies of the full Salmonella genome by incorporating an isothermal amplification step. Furthermore, 60 unknown samples with different target content in standard 344 well plates are evaluated. The results are analyzed using custom-developed machine-learning algorithms, successfully detecting the presence of the target with 100% prediction accuracy.

Diagnostic performance of deep learning-assisted [18F]FDG PET imaging for Alzheimer's disease: a systematic review and meta-analysis

PURPOSE

This study aims to calculate the diagnostic performance of deep learning (DL)-assisted 18F-fluorodeoxyglucose ([18F]FDG) PET imaging in Alzheimer's disease (AD).

METHODS

The Ovid MEDLINE, Ovid Embase, Web of Science Core Collection, Cochrane, and IEEE Xplore databases were searched for related studies from inception to May 24, 2024. We included original studies that developed a DL algorithm for [18F]FDG PET imaging to assess diagnostic performance in classifying AD, mild cognitive impairment (MCI), and normal control (NC). A bivariate random-effects model was employed to assess the area under the curve (AUC).

RESULTS

We identified 36 studies that met the inclusion criteria. Of these, 35 studies distinguished AD from NC, with a pooled AUC of 0.98 (95% CI: 0.96-0.99). Thirteen studies distinguished AD from MCI, with a pooled AUC of 0.95 (95% CI: 0.92-0.96). Nineteen studies distinguished MCI from NC, with a pooled AUC of 0.94 (95% CI: 0.91-0.95). Additionally, we found large amounts of heterogeneity across studies which could be partially attributed to variations in DL methods and imaging modalities.

CONCLUSION

This systematic review and meta-analysis shows that DL-assisted [18F]FDG PET imaging has high diagnostic performance in identifying AD. The significant heterogeneity among studies underscores the necessity for future research to incorporate external validation, utilize large sample size, and adhere to rigorous guideline to provide robust support for clinical decision-making.

Asymmetric Inter-Hemisphere Communication Contributes to Speech Acquisition of Toddlers with Cochlear Implants

How the lateralized language network and its functions emerge with early auditory experiences remains largely unknown. Here, early auditory development is examined using repeated optical imaging for cochlear implanted (CI) toddlers with congenital deafness from onset of restored hearing to around one year of CI hearing experiences. Machine learning models are constructed to resolve how functional organization of the bilateral language network and its sound processing support the CI children's post-implantation development of auditory and verbal communication skills. Behavioral improvement is predictable by cortical processing as well as by network organization changes, with the highest classification accuracy of 81.57%. For cortical processing, behavioral prediction is better for the left than the right hemisphere and for speech than non-speech processing. For network organization, the best prediction is obtained for resting state, with greater contribution from inter-hemisphere connections between non-homologous regions than from within-hemisphere connections. Most interestingly, systematic connectivity-to-activity models reveal that speech processing of the left language network is developmentally supported largely by global network organization, particularly asymmetric inter-hemisphere communication, rather than functional segregation of local network. These findings collectively confirm the importance of asymmetric inter-hemisphere communication in formation of the lateralized language network and its functional development with early auditory experiences.

Use machine learning to predict treatment outcome of early childhood caries

BACKGROUND

Early childhood caries (ECC) is a major oral health problem among preschool children that can significantly influence children's quality of life. Machine learning can accurately predict the treatment outcome but its use in ECC management is limited. The aim of this study is to explore the application of machine learning in predicting the treatment outcome of ECC.

METHODS

This study was a secondary analysis of a recently published clinical trial that recruited 1,070 children aged 3- to 4-year-old with ECC. Machine learning algorithms including Naive Bayes, logistic regression, decision tree, random forest, support vector machine, and extreme gradient boosting were adopted to predict the caries-arresting outcome of ECC at 30-month follow-up after receiving fluoride and silver therapy. Candidate predictors included clinical parameters (caries experience and oral hygiene status), oral health-related behaviours (toothbrushing habits, feeding history and snacking preference) and socioeconomic backgrounds of the children. Model performance was evaluated using discrimination and calibration metrics including accuracy, recall, precision, F1 score, area under the receiver operating characteristic curve (AUROC) and Brier score. Shapley additive explanations were deployed to identify the important predictors.

RESULTS

All machine learning models showed good performance in predicting the treatment outcome of ECC. The accuracy, recall, precision, F1 score, AUROC, and Brier score of the six models ranged from 0.674 to 0.740, 0.731 to 0.809, 0.762 to 0.802, 0.741 to 0.804, 0.771 to 0.859, and 0.134 to 0.227, respectively. The important predictors of the caries-arresting outcome were the surface and tooth location of the carious lesions, newly developed caries during follow-ups, baseline caries experience, whether the children had assisted toothbrushing and oral hygiene status.

CONCLUSIONS

Machine learning can provide promising predictions of the treatment outcome of ECC. The identified key predictors would be particularly informative for targeted management of ECC.

Comparative analysis of machine learning models for predicting pathological complete response to neoadjuvant chemotherapy in breast cancer: An MRI radiomics approach

PURPOSE

The aim of this work is to compare different machine learning models for predicting pathological complete response (pCR) to neoadjuvant chemotherapy (NAC) in breast cancer using radiomics features from dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI).

METHOD

The study included 55 patients with breast cancer, among whom 18 achieved pCR and 37 did not respond completely to NAC (non-pCR). After some pre-processing steps, 1446 features were extracted and corrected for batch effects using ComBat. Five machine learning algorithms, namely random forest (RF), decision tree (DT), logistic regression (LR), k-nearest neighbors (k-NN), and extreme gradient boosting (XGB), were evaluated using area under the receiver operating characteristic curve (AUC), accuracy, precision, recall, and F1 score as classification metrics. A Leave-Group-Out cross validation (LGOCV) was applied in the outer loop.

RESULTS

RF and DT models exhibited the highest performances compared to the other algorithms. DT achieved an accuracy of 0.96 ± 0.07, and RF achieved 0.95 ± 0.05. The AUC values for RF and DT were 0.98 ± 0.06 and 0.94 ± 0.07, respectively. LR and k-NN demonstrated lower performance across all metrics, while XGB showed competitive results but slightly lower than RF and DT.

CONCLUSIONS

This study demonstrates the potential of radiomics and machine learning for predicting pCR to NAC in breast cancer. RF and DT models proved to be the most effective in capturing underlying patterns in radiomics data. Further research is required to validate and strengthen the proposed approach and explore its applicability in diverse radiomics datasets and clinical scenarios.

Classification of neuroimaging data in Alzheimer's disease using particle swarm optimization: A systematic review

AIM

Particle swarm optimization (PSO) is an algorithm that involves the optimization of Non-linear and Multidimensional problems to reach the best solutions with minimal parameterization. This metaheuristic model has frequently been used in the Pathological domain. This optimization model has been used in diverse forms while predicting Alzheimer's disease. It is a robust algorithm that works on linear and multi-modal data while predicting Alzheimer's disease. PSO techniques have been in action for quite some time for detecting various diseases and this paper systematically reviews the papers on various kinds of PSO techniques.

METHODS

To perform the systematic review, PRISMA guidelines were followed and a Boolean search ("particle swarm optimization" OR "PSO") AND Neuroimaging AND (Alzheimer's disease prediction OR classification OR diagnosis) were performed. The query was run in 4-reputed databases: Google Scholar, Scopus, Science Direct, and Wiley publications.

RESULTS

For the final analysis, 10 papers were incorporated for qualitative and quantitative synthesis. PSO has shown a dominant character while handling the uni-modal as well as the multi-modal data while predicting the conversion from MCI to Alzheimer's. It can be seen from the table that almost all the 10 reviewed papers had MRI-driven data. The accuracy rate was accentuated while adding other modalities or Neurocognitive measures.

CONCLUSIONS

Through this algorithm, we are providing an opportunity to other researchers to compare this algorithm with other state-of-the-art algorithms, while seeing the classification accuracy, with the aim of early prediction and progression of MCI into Alzheimer's disease.

Derivation and Internal Validation of a Clinical Prediction Model for Diagnosis of Spotted Fever Group Rickettsioses in Northern Tanzania

Spotted fever group rickettsioses (SFGR) pose a global threat as emerging zoonotic infectious diseases; however, timely and cost-effective diagnostic tools are currently limited. We used data from 449 patients presenting to 2 hospitals in northern Tanzania between 2007 and 2008, of which 71 (15.8%) met criteria for acute SFGR based on ≥4-fold rise in antibody titers between acute and convalescent serum samples. We fit random forest classifiers incorporating clinical and demographic data from hospitalized febrile participants as well as Earth observation hydrometeorological predictors from the Kilimanjaro Region. In cross-validation, a prediction model with 10 clinical predictors achieved an area under the receiver operating characteristic curve of 0.65 (95% confidence interval, .48-.82). A combined prediction model with clinical, hydrometeorological, and environmental predictors (20 predictors total) did not significantly improve model performance. Novel strategies are needed to improve the diagnosis of acute SFGR, including the identification of diagnostic biomarkers that could enhance clinical prediction models.

Predicting postoperative adhesive small bowel obstruction in infants under 3 months with intestinal malrotation: a random forest approach

OBJECTIVE

This study aimed to develop a predictive model using a random forest algorithm to determine the likelihood of postoperative adhesive small bowel obstruction (ASBO) in infants under 3 months with intestinal malrotation.

METHODS

A machine learning model was used to predict postoperative adhesive small bowel obstruction using comprehensive clinical data extracted from 107 patients with a follow-up of at least 24 months. The Boruta algorithm was used for selecting clinical features, and nested cross-validation tuned and selected hyper-parameters for the random forest model. The model's performance was validated with 1000 bootstrap samples and assessed using receiver operating characteristic (ROC) analysis, the area under the ROC curve (AUC), sensitivity, specificity, precision, and F1 score.

RESULTS

The random forest model demonstrated high diagnostic accuracy with an AUC of 0.960. Significant predictors of ASBO included pre-operative white blood cell count (pre-WBC), mechanical ventilation (MV) duration, surgery duration, and post-operative albumin levels (post-ALB). Partial dependence plots showed non-linear relationships and threshold effects for these variables. The model achieved high sensitivity (0.805) and specificity (0.952), along with excellent precision (0.809) and a robust F1 score (0.799), indicating balanced recall and precision performance.

CONCLUSION

This study presents a machine learning model to accurately predict postoperative ASBO in infants with intestinal malrotation. Demonstrating high accuracy and robustness, this model shows great promise for enhancing clinical decision-making and patient outcomes in pediatric surgery.

The Scoring Model to Predict ICU Stay and Mortality After Emergency Admissions in Atrial Fibrillation: A Retrospective Study of 30 366 Patients

BACKGROUND

The rapid assessment of the conditions is crucial for the prognosis of atrial fibrillation (AF) patients admitted to the emergency department (ED). We aim to derive and validate a more accurate and simplified scoring model to optimize the triage of AF patients in the ED.

MATERIALS AND METHODS

We conducted a retrospective study using data from the Medical Information Mart for Intensive Care (MIMIC-IV) database and developed scoring models employing the Random Forest algorithm. The area under the receiver operating characteristic (ROC) curve (AUC) was used to measure the performance of the prediction for intensive care unit (ICU) stay, and the death likelihood within 3, 7, and 30 days following the ED admission.

RESULTS

The study included 30 366 AF patients, randomly divided into training, validation, and testing cohorts at a 7:1:2 ratio. The training set consisted of 21 257 patients, the validation set included 3036 patients, and the remaining 6073 patients were classified as the validation set. Among the cohorts, 9594 patients (32%) required ICU transfers, with mortality rates of 1% at 3 days, 3% at 7 days, and 6% at 30 days. In the testing set, the scoring models demonstrated strong discriminative ability with AUCs of 0.724 for ICU stay, 0.782 for 3-day mortality, 0.755 for 7-day mortality, and 0.767 for 30-day mortality.

CONCLUSION

We derived and validated novel simplified scoring models with good discriminative performance to predict the likelihood of ICU stay, 3-day, 7-day, and 30-day death in AF patients after ED admission.

Multimodal predictive modeling: Scalable imaging informed approaches to predict future brain health

BACKGROUND

Predicting future brain health is a complex endeavor that often requires integrating diverse data sources. The neural patterns and interactions identified through neuroimaging serve as the fundamental basis and early indicators that precede the manifestation of observable behaviors or psychological states.

NEW METHOD

In this work, we introduce a multimodal predictive modeling approach that leverages an imaging-informed methodology to gain insights into future behavioral outcomes. We employed three methodologies for evaluation: an assessment-only approach using support vector regression (SVR), a neuroimaging-only approach using random forest (RF), and an image-assisted method integrating the static functional network connectivity (sFNC) matrix from resting-state functional magnetic resonance imaging (rs-fMRI) alongside assessments. The image-assisted approach utilized a partially conditional variational autoencoder (PCVAE) to predict brain health constructs in future visits from the behavioral data alone.

RESULTS

Our performance evaluation indicates that the image-assisted method excels in handling conditional information to predict brain health constructs in subsequent visits and their longitudinal changes. These results suggest that during the training stage, the PCVAE model effectively captures relevant information from neuroimaging data, thereby potentially improving accuracy in making future predictions using only assessment data.

COMPARISON WITH EXISTING METHODS

The proposed image-assisted method outperforms traditional assessment-only and neuroimaging-only approaches by effectively integrating neuroimaging data with assessment factors.

CONCLUSION

This study underscores the potential of neuroimaging-informed predictive modeling to advance our comprehension of the complex relationships between cognitive performance and neural connectivity.

Machine Learning Prediction for Postdischarge Falls in Older Adults: A Multicenter Prospective Study

OBJECTIVES

The study aimed to develop a machine learning (ML) model to predict early postdischarge falls in older adults using data that are easy to collect in acute care hospitals. This may reduce the burden imposed by complex measures on patients and health care staff.

DESIGN

This prospective multicenter study included patients admitted to and discharged from geriatric wards at 3 university hospitals and 1 national medical center in Japan between October 2019 and July 2023.

SETTING AND PARTICIPANTS

The participants were individuals aged ≥65 years. Of the 1307 individuals enrolled during the study period, 684 were excluded, leaving 706 for inclusion in the analysis.

METHODS

We extracted 19 variables from admission and discharge data, including physical, mental, psychological, and social aspects and in-hospital events, to assess the main outcome measure: falls occurring within 3 months postdischarge. We developed a prediction model using 4 major classifiers, Extra Trees, Bernoulli Naive Bayes, AdaBoost, and Random Forest, which were evaluated using a 5-fold cross-validation. The area under the receiver operating characteristic curve (AUC) was used to evaluate predictive performance.

RESULTS

Among the 706 patients, 114 (16.1%) reported a fall within 3 months postdischarge. The Extra Trees classifier demonstrated the best predictive performance, with an AUC of 0.73 on the test data. Important features included the Lawton Instrumental Activities of Daily Living scale, Clinical Frailty Scale (≥4 points), presence of urinary incontinence, 15-item Geriatric Depression Scale (≥5 points), and preadmission residence, all assessed at admission.

CONCLUSIONS AND IMPLICATIONS

To our knowledge, this is the first study to develop an ML model for predicting early postdischarge falls among older patients in acute care hospitals. The findings suggest that this model could assist in developing fall-prevention strategies to ensure seamless transition of care from hospitals to communities.

Brain connectomes in youth at risk for serious mental illness: a longitudinal perspective

Identifying biomarkers for serious mental illnesses (SMI) has significant implications for prevention and early intervention. In the current study, changes in whole brain structural and functional connectomes were investigated in youth at transdiagnostic risk over a one-year period. Based on clinical assessments, participants were assigned to one of 5 groups: healthy controls (HC; n = 33), familial risk for serious mental illness (stage 0; n = 31), mild symptoms (stage 1a; n = 37), attenuated syndromes (stage 1b; n = 61), or discrete disorder (transition; n = 9). Constrained spherical deconvolution was used to generate whole brain tractography maps, which were then used to calculate connectivity matrices for graph theory analysis. Graph theory was also used to analyze correlations of functional magnetic resonance imaging (fMRI) signal between pairs of brain regions. Linear mixed models revealed structural and functional abnormalities in global metrics of small world lambda, and resting state networks involving the fronto-parietal, default mode, and deep grey matter networks, along with the visual and dorsal attention networks. Machine learning analysis additionally identified changes in nodal metrics of betweenness centrality in the angular gyrus and bilateral temporal gyri as potential features which can discriminate between the groups. Our findings further support the view that abnormalities in large scale networks (particularly those involving fronto-parietal, temporal, default mode, and deep grey matter networks) may underlie transdiagnostic risk for SMIs.

CECT-Based Radiomic Nomogram of Different Machine Learning Models for Differentiating Malignant and Benign Solid-Containing Renal Masses

Objective

This study aimed to explore the value of a radiomic nomogram based on contrast-enhanced computed tomography (CECT) for differentiating benign and malignant solid-containing renal masses.

Materials and Methods

A total of 122 patients with pathologically confirmed benign (n=47) or malignant (n=75) solid-containing renal masses were enrolled in this study. Radiomic features were extracted from the arterial, venous and delayed phases and further analysed by dimensionality reduction and selection. Four mainstream machine learning algorithm training models, namely, support vector machine (SVM), k-nearest neighbour (kNN), light gradient boosting (LightGBM) and logistic regression (LR), were constructed to determine the best classifier model. Univariate and multivariate analyses were used to determine the best clinical characteristics for constructing a clinical model. The radiomic and clinical signatures were integrated to construct a combined radiomic nomogram model. Receiver operating characteristic (ROC) curves and the area under the curve (AUC) were used to evaluate the performance of the radiomic nomogram, radiomic signature, and clinical model.

Results

Thirteen radiomic features were selected for the development of the radiomic signature. Among the various radiomic models, the LR model demonstrated superior predictive efficiency and robustness, yielding an AUC of 0.952 in the training cohort and 0.887 in the test cohort. The AUC for the clinical model was 0.854 in the training cohort and 0.747 in the test cohort. Furthermore, the radiomic nomogram, which incorporated sex, age, alcohol consumption history, and the radiomic signature, exhibited excellent discriminative performance, yielding an AUC of 0.973 in the training cohort and 0.900 in the test cohort.

Conclusion

The radiomic nomogram based on CECT offers a promising and noninvasive approach for distinguishing malignant from benign solid renal masses. This tool can be used to guide treatment strategies effectively and can provide valuable insights for clinicians.

Identification and validation of the important role of KIF11 in the development and progression of endometrial cancer

BACKGROUND

Human kinesin family member 11 (KIF11) plays a vital role in regulating the cell cycle and is implicated in the tumorigenesis and progression of various cancers, but its role in endometrial cancer (EC) is still unclear. Our current research explored the prognostic value, biological function and targeting strategy of KIF11 in EC through approaches including bioinformatics, machine learning and experimental studies.

METHODS

The GSE17025 dataset from the GEO database was analyzed via the limma package to identify differentially expressed genes (DEGs) in EC. Functional enrichment analysis of the DEGs was conducted using Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses. DEGs were further screened for hub genes through protein-protein interaction (PPI) network analysis and machine learning. The role of the hub gene KIF11 in EC was analyzed using clinical data from the TCGA database. The expression of KIF11 in EC was subsequently validated in clinical samples. In vitro experiments were utilized to evaluate the effects of KIF11 on biological functions such as proliferation, migration, apoptosis, and the cell cycle in endometrial cancer cells.

RESULTS

A total of 877 DEGs, which are widely involved in important biological processes such as cell division, tubulin binding, and the cell cycle, were identified. Through PPI network analysis and machine learning, KIF11 was selected as the hub gene for subsequent analysis and experimental validation. An analysis of TCGA data revealed that KIF11 is highly expressed in EC and is associated with tumor grade, stage, and a low survival rate. The overexpression of KIF11 in tumor tissues was further confirmed in EC patient samples. KIF11 knockdown had inhibitory effects on cell proliferation, migration and invasion. Flow cytometry analysis revealed that KIF11 knockdown induced G2/M phase arrest and promoted apoptosis in EC cells.

CONCLUSION

Our study demonstrated that KIF11 was upregulated in EC and was strongly associated with a poor prognosis. Notably, we found that reduced KIF11 expression inhibited EC cell proliferation, migration and invasion. KIF11 knockdown caused more EC cells to arrest in the G2/M phase and undergo apoptosis. The findings of our study emphasized that KIF11 may be a promising prognostic biomarker and therapeutic target for EC patients.

Explainable artificial intelligence for stroke prediction through comparison of deep learning and machine learning models

Failure to predict stroke promptly may lead to delayed treatment, causing severe consequences like permanent neurological damage or death. Early detection using deep learning (DL) and machine learning (ML) models can enhance patient outcomes and mitigate the long-term effects of strokes. The aim of this study is to compare these models, exploring their efficacy in predicting stroke. This study analyzed a dataset comprising 663 records from patients hospitalized at Hazrat Rasool Akram Hospital in Tehran, Iran, including 401 healthy individuals and 262 stroke patients. A total of eight established ML (SVM, XGB, KNN, RF) and DL (DNN, FNN, LSTM, CNN) models were utilized to predict stroke. Techniques such as 10-fold cross-validation and hyperparameter tuning were implemented to prevent overfitting. The study also focused on interpretability through Shapley Additive Explanations (SHAP). The evaluation of model's performance was based on accuracy, specificity, sensitivity, F1-score, and ROC curve metrics. Among DL models, LSTM showed superior sensitivity at 96.15%, while FNN exhibited better specificity (96.0%), accuracy (96.0%), F1-score (95.0%), and ROC (98.0%) among DL models. For ML models, RF displayed higher sensitivity (99.9%), accuracy (99.0%), specificity (100%), F1-score (99.0%), and ROC (99.9%). Overall, RF outperformed all models, while DL models surpassed ML models in most metrics except for RF. DL models (CNN, LSTM, DNN, FNN) achieved sensitivities from 93.0 to 96.15%, specificities from 80.0 to 96.0%, accuracies from 92.0 to 96.0%, F1-scores from 87.34 to 95.0%, and ROC scores from 95.0 to 98.0%. In contrast, ML models (KNN, XGB, SVM) showed sensitivities between 29.0% and 94.0%, specificities between 89.47% and 96.0%, accuracies between 71.0% and 95.0%, F1-scores between 44.0% and 95.0%, and ROC scores between 64.0% and 95.0%. This study demonstrates the efficacy of DL and ML models in predicting stroke, with the RF models outperforming all others in key metrics. While DL models generally surpassed ML models, RF's exceptional performance highlights the potential of combining these technologies for early stroke detection, significantly improving patient outcomes by preventing severe consequences like permanent neurological damage or death.

Differential risk of Alzheimer's disease in MCI subjects with elevated Abeta

BACKGROUNDS

People with elevated beta amyloid have different risk and progress speed to Alzheimer's disease.

PURPOSE

The research is to validate the risk classification of AD developed in the Shanghai mild cognitive impairment (MCI) cohort study using ADNI data.

METHODS

The risk classification of AD in MCI was based on several optimal cut-off points of a novel parameter Cog_Vol.

RESULTS

In total, 843 subjects with MCI were included, of whom 220 had elevated PET beta amyloid. 273 (32.3 %) and 70 (31.8 %) progressed to AD in all subjects and in those with elevated PET beta amyloid, respectively. The risk of AD in subjects whose Cog_Vol >340 was very low, while the risk for those with Cog_Vol less than 101 indicated a super high within 4 years of follow-up.

DISCUSSION

Risk classification using Cog_Vol at an optimal value was able to detect subjects among those with PET-amyloid-elevated MCI were at greater risk of developing AD and were unlikely to develop AD within 4 years of follow-up.

Combined Quantitative amyloid-β PET and Structural MRI Features Improve Alzheimer's Disease Classification in Random Forest Model - A Multicenter Study

RATIONALE AND OBJECTIVES

Prior to clinical presentations of Alzheimer's Disease (AD), neuropathological changes, such as amyloid-β and brain atrophy, have accumulated at the earlier stages of the disease. The combination of such biomarkers assessed by multiple modalities commonly improves the likelihood of AD etiology. We aimed to explore the discriminative ability of Aβ PET features and whether combining Aβ PET and structural MRI features can improve the classification performance of the machine learning model in older healthy control (OHC) and mild cognitive impairment (MCI) from AD.

MATERIAL AND METHODS

We collected 94 AD patients, 82 MCI patients, and 85 OHC from three different cohorts. 17 global/regional Aβ features in Centiloid, 122 regional volume, and 68 regional cortical thickness were extracted as imaging features. Single or combined modality features were used to train the random forest model on the testing set. The top 10 features were sorted based on the Gini index in each binary classification.

RESULTS

The results showed that AUC scores were 0.81/0.86 and 0.69/0.68 using sMRI/Aβ PET features on the testing set in differentiating OHC and MCI from AD. The performance was improved while combining two-modality features with an AUC of 0.89 and an AUC of 0.71 in two classifications. Compared to sMRI features, particular Aβ PET features contributed more to differentiating AD from others.

CONCLUSION

Our study demonstrated the discriminative ability of Aβ PET features in differentiating AD from OHC and MCI. A combination of Aβ PET and structural MRI features can improve the RF model performance.

Unlocking therapeutic frontiers: harnessing artificial intelligence in drug discovery for neurodegenerative diseases

Neurodegenerative diseases (NDs) pose serious healthcare challenges with limited therapeutic treatments and high social burdens. The integration of artificial intelligence (AI) into drug discovery has emerged as a promising approach to address these challenges. This review explores the application of AI techniques to unravel therapeutic frontiers for NDs. We examine the current landscape of AI-driven drug discovery and discuss the potentials of AI in accelerating the identification of novel therapeutic targets on ND research and drug development, optimization of drug candidates, and expediating personalized medicine approaches. Finally, we outline future directions and challenges in harnessing AI for the advancement of therapeutics in this critical area by emphasizing the importance of interdisciplinary collaboration and ethical considerations.

RGX Ensemble Model for Advanced Prediction of Mortality Outcomes in Stroke Patients

Objective: This paper aims to address the clinical challenge of predicting the outcomes of stroke patients and proposes a comprehensive model called RGX to help clinicians adopt more personalized treatment plans. Impact Statement: The comprehensive model is first proposed and applied to clinical datasets with missing data. The introduction of the Shapley additive explanations (SHAP) model to explain the impact of patient indicators on prognosis improves the accuracy of stroke patient mortality prediction. Introduction: At present, the prediction of stroke treatment outcomes faces many challenges, including the lack of models to quantify which clinical variables are closely related to patient survival. Methods: We developed a series of machine learning models to systematically predict the mortality of stroke patients. Additionally, by introducing the SHAP model, we revealed the contribution of risk factors to the prediction results. The performance of the models was evaluated using multiple metrics, including the area under the curve, accuracy, and specificity, to comprehensively measure the effectiveness and stability of the models. Results: The RGX model achieved an accuracy of 92.18% on the complete dataset, an improvement of 11.38% compared to that of the most advanced state-of-the-art model. Most importantly, the RGX model maintained excellent predictive ability even when faced with a dataset containing a large number of missing values, achieving an accuracy of 84.62%. Conclusion: In summary, the RGX ensemble model not only provides clinicians with a highly accurate predictive tool but also promotes the understanding of stroke patient survival prediction, laying a solid foundation for the development of precision medicine.

Volumetric Integrated Classification Index: An Integrated Voxel-Based Morphometry and Machine Learning Interpretable Biomarker for Post-Traumatic Stress Disorder

PTSD is a complex mental health condition triggered by individuals' traumatic experiences, with long-term and broad impacts on sufferers' psychological health and quality of life. Despite decades of research providing partial understanding of the pathobiological aspects of PTSD, precise neurobiological markers and imaging indicators remain challenging to pinpoint. This study employed VBM analysis and machine learning algorithms to investigate structural brain changes in PTSD patients. Data were sourced ADNI-DoD database for PTSD cases and from the ADNI database for healthy controls. Various machine learning models, including SVM, RF, and LR, were utilized for classification. Additionally, the VICI was proposed to enhance model interpretability, incorporating SHAP analysis. The association between PTSD risk genes and VICI values was also explored through gene expression data analysis. Among the tested machine learning algorithms, RF emerged as the top performer, achieving high accuracy in classifying PTSD patients. Structural brain abnormalities in PTSD patients were predominantly observed in prefrontal areas compared to healthy controls. The proposed VICI demonstrated classification efficacy comparable to the optimized RF model, indicating its potential as a simplified diagnostic tool. Analysis of gene expression data revealed significant associations between PTSD risk genes and VICI values, implicating synaptic integrity and neural development regulation. This study reveals neuroimaging and genetic characteristics of PTSD, highlighting the potential of VBM analysis and machine learning models in diagnosis and prognosis. The VICI offers a promising approach to enhance model interpretability and guide clinical decision-making. These findings contribute to a better understanding of the pathophysiological mechanisms of PTSD and provide new avenues for future diagnosis and treatment.

Phenotypic profiling based on body fluid traces discovered at the scene of crime: Raman spectroscopy of urine stains for race differentiation

Modern criminal investigations heavily rely on trace bodily fluid evidence as a rich source of DNA. DNA profiling of such evidence can result in the identification of an individual if a matching DNA profile is available. Alternatively, phenotypic profiling based on the analysis of body fluid traces can significantly narrow down the pool of suspects in a criminal investigation. Urine stain is a frequently encountered specimen at the scene of crime. Raman spectroscopy offers great potential as a universal confirmatory method for the identification of all main body fluids, including urine. In this proof-of-concept study, Raman spectroscopy combined with advanced statistics was used for race differentiation based on the analysis of urine stains. Specifically, a Random Forest (RF) model was built, which allowed for differentiating Caucasian (CA) and African American (AA) descent donors with 90% accuracy based on Raman spectra of dried urine samples. Raman spectra were collected from samples of 28 donors varying in age and sex. This novel technology offers great potential as a universal forensic tool for phenotypic profiling of a potential suspect immediately at the scene of a crime, providing invaluable information for a criminal investigation.

Translational Connectomics: overview of machine learning in macroscale Connectomics for clinical insights

Connectomics is a neuroscience paradigm focused on noninvasively mapping highly intricate and organized networks of neurons. The advent of neuroimaging has led to extensive mapping of the brain functional and structural connectome on a macroscale level through modalities such as functional and diffusion MRI. In parallel, the healthcare field has witnessed a surge in the application of machine learning and artificial intelligence for diagnostics, especially in imaging. While reviews covering machine learn ing and macroscale connectomics exist for specific disorders, none provide an overview that captures their evolving role, especially through the lens of clinical application and translation. The applications include understanding disorders, classification, identifying neuroimaging biomarkers, assessing severity, predicting outcomes and intervention response, identifying potential targets for brain stimulation, and evaluating the effects of stimulation intervention on the brain and connectome mapping in patients before neurosurgery. The covered studies span neurodegenerative, neurodevelopmental, neuropsychiatric, and neurological disorders. Along with applications, the review provides a brief of common ML methods to set context. Conjointly, limitations in ML studies within connectomics and strategies to mitigate them have been covered.

Development of an AI-Based Predictive Algorithm for Early Diagnosis of High-Risk Dementia Groups among the Elderly: Utilizing Health Lifelog Data

BACKGROUND/OBJECTIVES

This study aimed to develop a predictive algorithm for the early diagnosis of dementia in the high-risk group of older adults using artificial intelligence technologies. The objective is to create an accessible diagnostic method that does not rely on traditional medical equipment, thereby improving the early detection and management of dementia.

METHODS

Lifelog data from wearable devices targeting this high-risk group were collected from the AI Hub platform. Various indicators from these data were analyzed to develop a dementia diagnostic model. Machine learning techniques such as Logistic Regression, Random Forest, LightGBM, and Support Vector Machine were employed. Data augmentation techniques were applied to address data imbalance, thereby enhancing the model performance.

RESULTS

Data augmentation significantly improved the model's accuracy in classifying dementia cases. Specifically, in gait data, the SVM model performed with an accuracy of 0.879. In sleep data, a Logistic Regression was performed, yielding an accuracy of 0.818. This indicates that the lifelog data can effectively contribute to the early diagnosis of dementia, providing a practical solution that can be easily integrated into healthcare systems.

CONCLUSIONS

This study demonstrates that lifelog data, which are easily collected in daily life, can significantly enhance the accessibility and efficiency of dementia diagnosis, aiding in the effective use of medical resources and potentially delaying disease progression.

Predicting invasion in early-stage ground-glass opacity pulmonary adenocarcinoma: a radiomics-based machine learning approach

BACKGROUND

To design a pulmonary ground-glass nodules (GGN) classification method based on computed tomography (CT) radiomics and machine learning for prediction of invasion in early-stage ground-glass opacity (GGO) pulmonary adenocarcinoma.

METHODS

This retrospective study included pulmonary GGN patients who were histologically confirmed to have adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), or invasive adenocarcinoma cancer (IAC) from 2020 to 2023. CT images of all patients were automatically segmented and 107 radiomic features were obtained for each patient. Classification models were developed using random forest (RF) and cross-validation, including three one-versus-others models and one three-class model. For each model, features were ranked by normalized Gini importance, and a minimal subset was selected with a cumulative importance exceeding 0.9. These selected features were then used to train the final models. The models' performance metrics, including area under the curve (AUC), accuracy, sensitivity, and specificity, were computed. AUC and accuracy were compared to determine the final optimal method.

RESULTS

The study comprised 193 patients (mean age 54 ± 11 years, 65 men), including 65 AIS, 54 MIA, and 74 IAC, divided into one training cohort (N = 154) and one test cohort (N = 39). The final three-class RF model outperformed three individual one-versus-others models in distinguishing each class from the other two. For the multiclass classification model, the AUC, accuracy, sensitivity, and specificity were 0.87, 0.79, 0.62, and 0.88 for AIS; 0.90, 0.79, 0.54, and 0.89 for MIA; and 0.87, 0.69, 0.73, and 0.67 for IAC, respectively.

CONCLUSIONS

A radiomics-based multiclass RF model could effectively differentiate three types of pulmonary GGN, which enabled early diagnosis of GGO pulmonary adenocarcinoma.

Comparison of machine learning algorithms for predicting cognitive impairment using neuropsychological tests

OBJECTIVES

Neuropsychological tests (NPTs) are standard tools for assessing cognitive function. These tools can evaluate the cognitive status of a subject, which can be time-consuming and expensive for interpretation. Therefore, this paper aimed to optimize the systematic NPTs by machine learning and develop new classification models for differentiating healthy controls (HC), mild cognitive impairment, and Alzheimer's disease dementia (ADD) among groups of subjects.

PATIENTS AND METHODS

A total dataset of 14,926 subjects was obtained from the formal 46 NPTs based on the Seoul Neuropsychological Screening Battery (SNSB). The statistical values of the dataset included an age of 70.18 ± 7.13 with an education level of 8.18 ± 5.50 and a diagnosis group of three; HC, MCI, and ADD. The dataset was preprocessed and classified in two- and three-way machine-learning classification from scikit-learn (www.scikit-learn.org) to differentiate between HC versus MCI, HC versus ADD, HC versus Cognitive Impairment (CI) (MCI + ADD), and HC versus MCI versus ADD. We compared the performance of seven machine learning algorithms, including Naïve Bayes (NB), random forest (RF), decision tree (DT), k-nearest neighbors (KNN), support vector machine (SVM), AdaBoost, and linear discriminant analysis (LDA). The accuracy, sensitivity, specificity, positive predicted value (PPV), negative predictive value (NPV), area under the curve (AUC), confusion matrixes, and receiver operating characteristic (ROC) were obtained from each model based on the test dataset.

RESULTS

The trained models based on 29 best-selected NPT features were evaluated, the model with the RF algorithm yielded the best accuracy, sensitivity, specificity, PPV, NPV, and AUC in all four models: HC versus MCI was 98%, 98%, 97%, 98%, 97%, and 99%; HC versus ADD was 98%, 99%, 96%, 97%, 98%, and 99%; HC versus CI was 97%, 99%, 92%, 97%, 97%, and 99% and HC versus MCI versus ADD was 97%, 96%, 98%, 97%, 98%, and 99%, respectively, in predicting of cognitive impairment among subjects.

CONCLUSION

According to the results, the RF algorithm was the best classification model for both two- and three-way classification among the seven algorithms trained on an imbalanced NPTs SNSB dataset. The trained models proved useful for diagnosing MCI and ADD in patients with normal NPTs. These models can optimize cognitive evaluation, enhance diagnostic accuracy, and reduce missed diagnoses.

Artificial intelligence: illuminating the depths of the tumor microenvironment

Artificial intelligence (AI) can acquire characteristics that are not yet known to humans through extensive learning, enabling to handle large amounts of pathology image data. Divided into machine learning and deep learning, AI has the advantage of handling large amounts of data and processing image analysis, consequently it also has a great potential in accurately assessing tumour microenvironment (TME) models. With the complex composition of the TME, in-depth study of TME contributes to new ideas for treatment, assessment of patient response to postoperative therapy and prognostic prediction. This leads to a review of the development of AI's application in TME assessment in this study, provides an overview of AI techniques applied to medicine, delves into the application of AI in analysing the quantitative and spatial location characteristics of various cells (tumour cells, immune and non-immune cells) in the TME, reveals the predictive prognostic value of TME and provides new ideas for tumour therapy, highlights the great potential for clinical applications. In addition, a discussion of its limitations and encouraging future directions for its practical clinical application is presented.

Surface-Enhanced Raman Scattering Nanosensing and Imaging in Neuroscience

Monitoring neurochemicals and imaging the molecular content of brain tissues in vitro, ex vivo, and in vivo is essential for enhancing our understanding of neurochemistry and the causes of brain disorders. This review explores the potential applications of surface-enhanced Raman scattering (SERS) nanosensors in neurosciences, where their adoption could lead to significant progress in the field. These applications encompass detecting neurotransmitters or brain disorders biomarkers in biofluids with SERS nanosensors, and imaging normal and pathological brain tissues with SERS labeling. Specific studies highlighting in vitro, ex vivo, and in vivo analysis of brain disorders using fit-for-purpose SERS nanosensors will be detailed, with an emphasis on the ability of SERS to detect clinically pertinent levels of neurochemicals. Recent advancements in designing SERS-active nanomaterials, improving experimentation in biofluids, and increasing the usage of machine learning for interpreting SERS spectra will also be discussed. Furthermore, we will address the tagging of tissues presenting pathologies with nanoparticles for SERS imaging, a burgeoning domain of neuroscience that has been demonstrated to be effective in guiding tumor removal during brain surgery. The review also explores future research applications for SERS nanosensors in neuroscience, including monitoring neurochemistry in vivo with greater penetration using surface-enhanced spatially offset Raman scattering (SESORS), near-infrared lasers, and 2-photon techniques. The article concludes by discussing the potential of SERS for investigating the effectiveness of therapies for brain disorders and for integrating conventional neurochemistry techniques with SERS sensing.

Enhancing dementia risk screening with GAN-synthesized periodontal examination and general blood test data

Introduction

This study aimed to investigate the effectiveness of data augmentation to improve dementia risk prediction using machine learning models. Recent studies have shown that basic blood tests are cost-effective in predicting cognitive function. However, developing models that address various conditions poses challenges due to constraints associated with blood test results and cognitive assessments, including high costs, limited sample sizes, and missing data from tests not performed in certain facilities. Despite being often limited by small sample sizes, periodontal examination data have also emerged as a cost-effective screening tool.

Methods

To address these challenges, this study explored the effectiveness of data augmentation using the Synthetic Minority Over-sampling Technique for Regression with Gaussian noise (SMOGN), a Generative Adversarial Network (GAN), and a Conditional Tabular GAN (CTGAN) on periodontal examination and blood test data. The datasets included parameters such as cognitive assessment results from the Mini-Mental State Examination (MMSE), demographic characteristics, periodontal examination data, and blood test results. Linear regression models, random forests, and deep neural networks were used to evaluate the effectiveness of the synthesized data.

Results

This study used measured data from 108 participants and the synthesized data generated from the measured data. External validity was evaluated using a different dataset of 41 participants with missing items. The results suggested that normal GANs have the advantage of investigating models in data diversity, whereas CTGANs preserve the data structure and linear relationships in tabular data from the measured data, which drastically improves linear regression models.

Discussion

Importantly, by interpolating sparse areas in the distribution, such as age, the synthesized models maintained prediction accuracy for test data with extreme inputs. These findings suggest that GAN-synthesized data can effectively address regression problems and improve dementia risk prediction.

Mining Alzheimer's disease clinical data: reducing effects of natural aging for predicting progression and identifying subtypes

Introduction

Because Alzheimer's disease (AD) has significant heterogeneity in encephalatrophy and clinical manifestations, AD research faces two critical challenges: eliminating the impact of natural aging and extracting valuable clinical data for patients with AD.

Methods

This study attempted to address these challenges by developing a novel machine-learning model called tensorized contrastive principal component analysis (T-cPCA). The objectives of this study were to predict AD progression and identify clinical subtypes while minimizing the influence of natural aging.

Results

We leveraged a clinical variable space of 872 features, including almost all AD clinical examinations, which is the most comprehensive AD feature description in current research. T-cPCA yielded the highest accuracy in predicting AD progression by effectively minimizing the confounding effects of natural aging.

Discussion

The representative features and pathogenic circuits of the four primary AD clinical subtypes were discovered. Confirmed by clinical doctors in Tangdu Hospital, the plaques (18F-AV45) distribution of typical patients in the four clinical subtypes are consistent with representative brain regions found in four AD subtypes, which further offers novel insights into the underlying mechanisms of AD pathogenesis.

A novel multitask learning algorithm for tasks with distinct chemical space: zebrafish toxicity prediction as an example

Data scarcity is one of the most critical issues impeding the development of prediction models for chemical effects. Multitask learning algorithms leveraging knowledge from relevant tasks showed potential for dealing with tasks with limited data. However, current multitask methods mainly focus on learning from datasets whose task labels are available for most of the training samples. Since datasets were generated for different purposes with distinct chemical spaces, the conventional multitask learning methods may not be suitable. This study presents a novel multitask learning method MTForestNet that can deal with data scarcity problems and learn from tasks with distinct chemical space. The MTForestNet consists of nodes of random forest classifiers organized in the form of a progressive network, where each node represents a random forest model learned from a specific task. To demonstrate the effectiveness of the MTForestNet, 48 zebrafish toxicity datasets were collected and utilized as an example. Among them, two tasks are very different from other tasks with only 1.3% common chemicals shared with other tasks. In an independent test, MTForestNet with a high area under the receiver operating characteristic curve (AUC) value of 0.911 provided superior performance over compared single-task and multitask methods. The overall toxicity derived from the developed models of zebrafish toxicity is well correlated with the experimentally determined overall toxicity. In addition, the outputs from the developed models of zebrafish toxicity can be utilized as features to boost the prediction of developmental toxicity. The developed models are effective for predicting zebrafish toxicity and the proposed MTForestNet is expected to be useful for tasks with distinct chemical space that can be applied in other tasks.Scieific contributionA novel multitask learning algorithm MTForestNet was proposed to address the challenges of developing models using datasets with distinct chemical space that is a common issue of cheminformatics tasks. As an example, zebrafish toxicity prediction models were developed using the proposed MTForestNet which provide superior performance over conventional single-task and multitask learning methods. In addition, the developed zebrafish toxicity prediction models can reduce animal testing.

Performance Evaluation of Deep, Shallow and Ensemble Machine Learning Methods for the Automated Classification of Alzheimer's Disease

Artificial intelligence (AI)-based approaches are crucial in computer-aided diagnosis (CAD) for various medical applications. Their ability to quickly and accurately learn from complex data is remarkable. Deep learning (DL) models have shown promising results in accurately classifying Alzheimer's disease (AD) and its related cognitive states, Early Mild Cognitive Impairment (EMCI) and Late Mild Cognitive Impairment (LMCI), along with the healthy conditions known as Cognitively Normal (CN). This offers valuable insights into disease progression and diagnosis. However, certain traditional machine learning (ML) classifiers perform equally well or even better than DL models, requiring less training data. This is particularly valuable in CAD in situations with limited labeled datasets. In this paper, we propose an ensemble classifier based on ML models for magnetic resonance imaging (MRI) data, which achieved an impressive accuracy of 96.52%. This represents a 3-5% improvement over the best individual classifier. We evaluated popular ML classifiers for AD classification under both data-scarce and data-rich conditions using the Alzheimer's Disease Neuroimaging Initiative and Open Access Series of Imaging Studies datasets. By comparing the results to state-of-the-art CNN-centric DL algorithms, we gain insights into the strengths and weaknesses of each approach. This work will help users to select the most suitable algorithm for AD classification based on data availability.

CT-Based Radiomics Analysis of Different Machine Learning Models for Discriminating the Risk Stratification of Pheochromocytoma and Paraganglioma: A Multicenter Study

RATIONALE AND OBJECTIVES

Using different machine learning models CT-based radiomics to integrate clinical radiological features to discriminating the risk stratification of pheochromocytoma/paragangliomas (PPGLs).

MATERIALS AND METHODS

The present study included 201 patients with PPGLs from three hospitals (training set: n = 125; external validation set: n = 45; external test set: n = 31). Patients were divided into low-risk and high-risk groups using a staging system for adrenal pheochromocytoma and paraganglioma (GAPP). We extracted and selected CT radiomics features, and built radiomics models using support vector machines (SVM), k-nearest neighbors, random forests, and multilayer perceptrons. Using receiver operating characteristic curve analysis to select the optimal radiomics model, a combined model was built using the output of the optimal radiomics model and clinical radiological features, and its accuracy and clinical applicability were evaluated using calibration curves and clinical decision curve analysis (DCA).

RESULTS

Finally, 13 radiomics features were selected to construct machine learning models. In the radiomics model, the SVM model demonstrated higher accuracy and stability, with an AUC value of 0.915 in the training set, 0.846 in external validation set, and 0.857 in external test set. Combining the outputs of SVM models with two clinical radiological features, a combined model constructed has demonstrated optimal risk stratification ability for PPGLs with an AUC of 0.926 for the training set, 0.883 for the external validation set, and 0.899 for the external test set. The calibration curve and DCA show good calibration accuracy and clinical effectiveness for the combined model.

CONCLUSION

Combined model that integrates radiomics and clinical radiological features can discriminate the risk stratification of PPGLs.

Autophagy-related molecular clusters identified as indicators for distinguishing active and latent TB infection in pediatric patients

BACKGROUND

Autophagy is crucial for controlling the manifestation of tuberculosis. This study intends to discover autophagy-related molecular clusters as biomarkers for discriminating between latent tuberculosis (LTBI) and active tuberculosis (ATB) in children through gene expression profile analysis.

METHODS

The expression of autophagy modulators was examined in pediatric patients with LTBI and ATB utilizing public datasets from the Gene Expression Omnibus (GEO) collection (GSE39939 and GSE39940).

RESULTS

In a training dataset (GSE39939), patients with LTBI and ATB exhibited the expression of autophagy-related genes connected with their active immune responses. Two molecular clusters associated with autophagy were identified. Compared to Cluster 1, Cluster 2 was distinguished through decreased adaptive cellular immune response and enhanced inflammatory activation, according to single-sample gene set enrichment analysis (ssGSEA). Per the study of gene set variation, Cluster 2's differentially expressed genes (DEGs) played a role in synthesizing transfer RNA, DNA repair and recombination, and primary immunodeficiency. The peak variation efficiency, root mean square error, and area under the curve (AUC) (AUC = 0.950) were all lowered in random forest models. Finally, a seven-gene-dependent random forest profile was created utilizing the CD247, MAN1C1, FAM84B, HSZFP36, SLC16A10, DTX3, and SIRT4 genes, which performed well against the validation dataset GSE139940 (AUC = 0.888). The nomogram calibration and decision curves performed well in identifying ATB from LTBI.

CONCLUSIONS

In summary, according to the present investigation, autophagy and the immunopathology of TB might be correlated. Furthermore, this investigation established a compelling prediction expression profile for measuring autophagy subtype development risks, which might be employed as possible biomarkers in children to differentiate ATB from LTBI.

Performance Drift in Machine Learning Models for Cardiac Surgery Risk Prediction: Retrospective Analysis

Background

The Society of Thoracic Surgeons and European System for Cardiac Operative Risk Evaluation (EuroSCORE) II risk scores are the most commonly used risk prediction models for in-hospital mortality after adult cardiac surgery. However, they are prone to miscalibration over time and poor generalization across data sets; thus, their use remains controversial. Despite increased interest, a gap in understanding the effect of data set drift on the performance of machine learning (ML) over time remains a barrier to its wider use in clinical practice. Data set drift occurs when an ML system underperforms because of a mismatch between the data it was developed from and the data on which it is deployed.

Objective

In this study, we analyzed the extent of performance drift using models built on a large UK cardiac surgery database. The objectives were to (1) rank and assess the extent of performance drift in cardiac surgery risk ML models over time and (2) investigate any potential influence of data set drift and variable importance drift on performance drift.

Methods

We conducted a retrospective analysis of prospectively, routinely gathered data on adult patients undergoing cardiac surgery in the United Kingdom between 2012 and 2019. We temporally split the data 70:30 into a training and validation set and a holdout set. Five novel ML mortality prediction models were developed and assessed, along with EuroSCORE II, for relationships between and within variable importance drift, performance drift, and actual data set drift. Performance was assessed using a consensus metric.

Results

A total of 227,087 adults underwent cardiac surgery during the study period, with a mortality rate of 2.76% (n=6258). There was strong evidence of a decrease in overall performance across all models (P<.0001). Extreme gradient boosting (clinical effectiveness metric [CEM] 0.728, 95% CI 0.728-0.729) and random forest (CEM 0.727, 95% CI 0.727-0.728) were the overall best-performing models, both temporally and nontemporally. EuroSCORE II performed the worst across all comparisons. Sharp changes in variable importance and data set drift from October to December 2017, from June to July 2018, and from December 2018 to February 2019 mirrored the effects of performance decrease across models.

Conclusions

All models show a decrease in at least 3 of the 5 individual metrics. CEM and variable importance drift detection demonstrate the limitation of logistic regression methods used for cardiac surgery risk prediction and the effects of data set drift. Future work will be required to determine the interplay between ML models and whether ensemble models could improve on their respective performance advantages.

Narcissus reflected: Grey and white matter features joint contribution to the default mode network in predicting narcissistic personality traits

Despite the clinical significance of narcissistic personality, its neural bases have not been clarified yet, primarily because of methodological limitations of the previous studies, such as the low sample size, the use of univariate techniques and the focus on only one brain modality. In this study, we employed for the first time a combination of unsupervised and supervised machine learning methods, to identify the joint contributions of grey matter (GM) and white matter (WM) to narcissistic personality traits (NPT). After preprocessing, the brain scans of 135 participants were decomposed into eight independent networks of covarying GM and WM via parallel ICA. Subsequently, stepwise regression and Random Forest were used to predict NPT. We hypothesized that a fronto-temporo parietal network, mainly related to the default mode network, may be involved in NPT and associated WM regions. Results demonstrated a distributed network that included GM alterations in fronto-temporal regions, the insula and the cingulate cortex, along with WM alterations in cerebellar and thalamic regions. To assess the specificity of our findings, we also examined whether the brain network predicting narcissism could also predict other personality traits (i.e., histrionic, paranoid and avoidant personalities). Notably, this network did not predict such personality traits. Additionally, a supervised machine learning model (Random Forest) was used to extract a predictive model for generalization to new cases. Results confirmed that the same network could predict new cases. These findings hold promise for advancing our understanding of personality traits and potentially uncovering brain biomarkers associated with narcissism.

Identification of neurological complications in childhood influenza: a random forest model

BACKGROUND

Among the neurological complications of influenza in children, the most severe is acute necrotizing encephalopathy (ANE), with a high mortality rate and neurological sequelae. ANE is characterized by rapid progression to death within 1-2 days from onset. However, the knowledge about the early diagnosis of ANE is limited, which is often misdiagnosed as simple seizures/convulsions or mild acute influenza-associated encephalopathy (IAE).

OBJECTIVE

To develop and validate an early prediction model to discriminate the ANE from two common neurological complications, seizures/convulsions and mild IAE in children with influenza.

METHODS

This retrospective case-control study included patients with ANE (median age 3.8 (2.3,5.4) years), seizures/convulsions alone (median age 2.6 (1.7,4.3) years), or mild IAE (median age 2.8 (1.5,6.1) years) at a tertiary pediatric medical center in China between November 2012 to January 2020. The random forest algorithm was used to screen the characteristics and construct a prediction model.

RESULTS

Of the 433 patients, 278 (64.2%) had seizures/convulsions alone, 106 (24.5%) had mild IAE, and 49 (11.3%) had ANE. The discrimination performance of the model was satisfactory, with an accuracy above 0.80 from both model development (84.2%) and internal validation (88.2%). Seizures/convulsions were less likely to be wrongly classified (3.7%, 2/54), but mild IAE (22.7%, 5/22) was prone to be misdiagnosed as seizures/convulsions, and a small proportion (4.5%, 1/22) of them was prone to be misdiagnosed as ANE. Of the children with ANE, 22.2% (2/9) were misdiagnosed as mild IAE, and none were misdiagnosed as seizures/convulsions.

CONCLUSION

This model can distinguish the ANE from seizures/convulsions with high accuracy and from mild IAE close to 80% accuracy, providing valuable information for the early management of children with influenza.

Predicting Postoperative Pain and Opioid Use with Machine Learning Applied to Longitudinal Electronic Health Record and Wearable Data

BACKGROUND

 Managing acute postoperative pain and minimizing chronic opioid use are crucial for patient recovery and long-term well-being.

OBJECTIVES

 This study explored using preoperative electronic health record (EHR) and wearable device data for machine-learning models that predict postoperative acute pain and chronic opioid use.

METHODS

 The study cohort consisted of approximately 347 All of Us Research Program participants who underwent one of eight surgical procedures and shared EHR and wearable device data. We developed four machine learning models and used the Shapley additive explanations (SHAP) technique to identify the most relevant predictors of acute pain and chronic opioid use.

RESULTS

 The stacking ensemble model achieved the highest accuracy in predicting acute pain (0.68) and chronic opioid use (0.89). The area under the curve score for severe pain versus other pain was highest (0.88) when predicting acute postoperative pain. Values of logistic regression, random forest, extreme gradient boosting, and stacking ensemble ranged from 0.74 to 0.90 when predicting postoperative chronic opioid use. Variables from wearable devices played a prominent role in predicting both outcomes.

CONCLUSION

 SHAP detection of individual risk factors for severe pain can help health care providers tailor pain management plans. Accurate prediction of postoperative chronic opioid use before surgery can help mitigate the risk for the outcomes we studied. Prediction can also reduce the chances of opioid overuse and dependence. Such mitigation can promote safer and more effective pain control for patients during their recovery.

Experimental validation and comprehensive analysis of m6A methylation regulators in intervertebral disc degeneration subpopulation classification

Intervertebral disc degeneration (IVDD) is one of the most prevalent causes of chronic low back pain. The role of m6A methylation modification in disc degeneration (IVDD) remains unclear. We investigated immune-related m6A methylation regulators as IVDD biomarkers through comprehensive analysis and experimental validation of m6A methylation regulators in disc degeneration. The training dataset was downloaded from the GEO database and analysed for differentially expressed m6A methylation regulators and immunological features, the differentially regulators were subsequently validated by a rat IVDD model and RT-qPCR. Further screening of key m6A methylation regulators based on machine learning and LASSO regression analysis. Thereafter, a predictive model based on key m6A methylation regulators was constructed for training sets, which was validated by validation set. IVDD patients were then clustered based on the expression of key m6A regulators, and the expression of key m6A regulators and immune infiltrates between clusters was investigated to determine immune markers in IVDD. Finally, we investigated the potential role of the immune marker in IVDD through enrichment analysis, protein-to-protein network analysis, and molecular prediction. By analysising of the training set, we revealed significant differences in gene expression of five methylation regulators including RBM15, YTHDC1, YTHDF3, HNRNPA2B1 and ALKBH5, while finding characteristic immune infiltration of differentially expressed genes, the result was validated by PCR. We then screen the differential m6A regulators in the training set and identified RBM15 and YTHDC1 as key m6A regulators. We then used RBM15 and YTHDC1 to construct a predictive model for IVDD and successfully validated it in the training set. Next, we clustered IVDD patients based on the expression of RBM15 and YTHDC1 and explored the immune infiltration characteristics between clusters as well as the expression of RBM15 and YTHDC1 in the clusters. YTHDC1 was finally identified as an immune biomarker for IVDD. We finally found that YTHDC1 may influence the immune microenvironment of IVDD through ABL1 and TXK. In summary, our results suggest that YTHDC1 is a potential biomarker for the development of IVDD and may provide new insights for the precise prevention and treatment of IVDD.

Construction and experimental validation of a novel ferroptosis-related gene signature for myelodysplastic syndromes

BACKGROUND

Myelodysplastic syndromes (MDS) are clonal hematopoietic disorders characterized by morphological abnormalities and peripheral blood cytopenias, carrying a risk of progression to acute myeloid leukemia. Although ferroptosis is a promising target for MDS treatment, the specific roles of ferroptosis-related genes (FRGs) in MDS diagnosis have not been elucidated.

METHODS

MDS-related microarray data were obtained from the Gene Expression Omnibus database. A comprehensive analysis of FRG expression levels in patients with MDS and controls was conducted, followed by the use of multiple machine learning methods to establish prediction models. The predictive ability of the optimal model was evaluated using nomogram analysis and an external data set. Functional analysis was applied to explore the underlying mechanisms. The mRNA levels of the model genes were verified in MDS clinical samples by quantitative real-time polymerase chain reaction (qRT-PCR).

RESULTS

The extreme gradient boosting model demonstrated the best performance, leading to the identification of a panel of six signature genes: SREBF1, PTPN6, PARP9, MAP3K11, MDM4, and EZH2. Receiver operating characteristic curves indicated that the model exhibited high accuracy in predicting MDS diagnosis, with area under the curve values of 0.989 and 0.962 for the training and validation cohorts, respectively. Functional analysis revealed significant associations between these genes and the infiltrating immune cells. The expression levels of these genes were successfully verified in MDS clinical samples.

CONCLUSION

Our study is the first to identify a novel model using FRGs to predict the risk of developing MDS. FRGs may be implicated in MDS pathogenesis through immune-related pathways. These findings highlight the intricate correlation between ferroptosis and MDS, offering insights that may aid in identifying potential therapeutic targets for this debilitating disorder.

Differentiation of testicular seminomas from nonseminomas based on multiphase CT radiomics combined with machine learning: A multicenter study

BACKGROUND

Differentiating seminomas from nonseminomas is crucial for formulating optimal treatment strategies for testicular germ cell tumors (TGCTs). Therefore, our study aimed to develop and validate a clinical-radiomics model for this purpose.

METHODS

In this study, 221 patients with TGCTs confirmed by pathology from four hospitals were enrolled and classified into training (n = 126), internal validation (n = 55) and external test (n = 40) cohorts. Radiomics features were extracted from the CT images. After feature selection, we constructed a clinical model, radiomics models and clinical-radiomics model with different machine learning algorithms. The top-performing model was chosen utilizing receiver operating characteristic (ROC) curve analysis. Decision curve analysis (DCA) was also conducted to assess its practical utility.

RESULTS

Compared with those of the clinical and radiomics models, the clinical-radiomics model demonstrated the highest discriminatory ability, with AUCs of 0.918 (95 % CI: 0.870 - 0.966), 0.909 (95 % CI: 0.829 - 0.988) and 0.839 (95 % CI: 0.709 - 0.968) in the training, validation and test cohorts, respectively. Moreover, DCA confirmed that the combined model had a greater net benefit in predicting seminomas and nonseminomas.

CONCLUSION

The clinical-radiomics model serves as a potential tool for noninvasive differentiation between testicular seminomas and nonseminomas, offering valuable guidance for clinical treatment.

Bioinformatics analysis identifies a key gene HLA_DPA1 in severe influenza-associated immune infiltration

BACKGROUND

Severe influenza is a serious global health issue that leads to prolonged hospitalization and mortality on a significant scale. The pathogenesis of this infectious disease is poorly understood. Therefore, this study aimed to identify the key genes associated with severe influenza patients necessitating invasive mechanical ventilation.

METHODS

The current study utilized two publicly accessible gene expression profiles (GSE111368 and GSE21802) from the Gene Expression Omnibus database. The research focused on identifying the genes exhibiting differential expression between severe and non-severe influenza patients. We employed three machine learning algorithms, namely the Least Absolute Shrinkage and Selection Operator regression model, Random Forest, and Support Vector Machine-Recursive Feature Elimination, to detect potential key genes. The key gene was further selected based on the diagnostic performance of the target genes substantiated in the dataset GSE101702. A single-sample gene set enrichment analysis algorithm was applied to evaluate the participation of immune cell infiltration and their associations with key genes.

RESULTS

A total of 44 differentially expressed genes were recognized; among them, we focused on 10 common genes, namely PCOLCE2, HLA_DPA1, LOC653061, TDRD9, MPO, HLA_DQA1, MAOA, S100P, RAP1GAP, and CA1. To ensure the robustness of our findings, we employed overlapping LASSO regression, Random Forest, and SVM-RFE algorithms. By utilizing these algorithms, we were able to pinpoint the aforementioned 10 genes as potential biomarkers for distinguishing between both cases of influenza (severe and non-severe). However, the gene HLA_DPA1 has been recognized as a crucial factor in the pathological condition of severe influenza. Notably, the validation dataset revealed that this gene exhibited the highest area under the receiver operating characteristic curve, with a value of 0.891. The use of single-sample gene set enrichment analysis has provided valuable insights into the immune responses of patients afflicted with severe influenza that have further revealed a categorical correlation between the expression of HLA_DPA1 and lymphocytes.

CONCLUSION

The findings indicated that the HLA_DPA1 gene may play a crucial role in the immune-pathological condition of severe influenza and could serve as a promising therapeutic target for patients infected with severe influenza.