Personalized Treatment Strategies Research Articles

Heart disease prediction using machine learning models

Abstract. Heart disease remains a global health threat, making rapid identification crucial. Using the Heart Disease Dataset from Kaggle, this research employs a Random Forest model to analyze 13 clinical variables from 1,025 samples. To improve accuracy and address class imbalance, the dataset was split into training and test sets, utilizing methods such as Z-scores, SMOTE, and feature selection. The Random Forest model, which combines multiple decision trees, achieved high performance with an accuracy of 98.54%, identifying key predictors such as chest pain type, maximum heart rate, and thalassemia. Compared to a single decision tree, the Random Forest model reduces overfitting, improves generalization, and increases predictive accuracy. Factors like cholesterol levels, resting blood pressure, and exercise-induced angina were also considered. By averaging results from multiple trees, the model offers reliable and stable predictions, highlighting its potential in clinical settings for early detection and personalized treatment strategies. This study aims to assist healthcare providers in better allocating resources, planning preventive measures, and tailoring treatment plans to individual patients.

Cognitive Impairments Related to COMT and Neuregulin 1 Phenotypes as Transdiagnostic Markers in Schizophrenia Spectrum Patients.

Background: Research on the interaction between antipsychotic treatment and cognitive dysfunction in schizophrenia spectrum disorders (SSDs) is extensive, yet the role of genetic polymorphisms in catechol-O-methyltransferase (COMT) and neuregulin 1 (NRG1) remains underexplored. Methods: This study evaluates the impact of COMT (rs4680) and NRG1 (rs3924999 and rs35753505) polymorphisms on cognitive functions in SSD patients. A cross-sectional study was conducted with fifty-four patients, assessed using the Positive and Negative Syndrome Scale (PANSS) and the CNS Vital Signs battery. Results: Significant cognitive function differences were observed across SSD diagnostic categories (p < 0.001). The NRG1 rs35753505 TT genotype was significantly associated with better verbal memory performance compared to the CC genotype (p = 0.03), while no significant differences were observed for other genotypes. The NRG1 rs3924999 AA genotype showed superior reasoning performance compared to AG and GG genotypes (p = 0.01), with AG and GG associated with lower scores (p = 0.01 and p = 0.02, respectively). Additionally, the COMT Val158Met genotype significantly influenced processing speed, with patients at the first episode of psychosis showing higher scores than chronic patients (p = 0.01). Conclusions: These findings suggest that NRG1 and COMT polymorphisms may influence cognitive domains in schizophrenia spectrum disorders, potentially informing personalized treatment and cognitive rehabilitation strategies.

Therapeutic advances in hepatocellular carcinoma: an update from the 2024 ASCO annual meeting.

Hepatocellular carcinoma (HCC) remains a leading cause of cancer-related deaths worldwide. Recent advances in immunotherapies, targeted therapies, and combination treatments have significantly improved outcomes for many patients with HCC. This review summarizes key findings from the 2024 ASCO Annual Meeting, focusing on emerging therapies, including immune checkpoint inhibitors (ICIs), CAR-T cell therapies, oncolytic viruses, and locoregional treatments like transarterial chemoembolization (TACE) and hepatic arterial infusion chemotherapy (HAIC). ICIs, particularly when combined with other agents, have shown promising efficacy, though challenges such as immune-related adverse events and resistance mechanisms remain. CAR-T cell therapies and oncolytic viruses offer novel therapeutic avenues for advanced HCC, but their long-term efficacy in solid tumors is still under investigation. Locoregional therapies, especially in combination with systemic treatments, continue to play a critical role in managing unresectable HCC and improving conversion rates to surgical resection. Additionally, the potential of biomarkers, such as hypoxia scores and CTNNB1 mutations, is being explored to better personalize treatment and predict patient responses. These biomarkers could pave the way for more targeted and effective therapeutic strategies. Overall, the recent studies presented at the ASCO meeting highlight progress in HCC treatment, underscoring the importance of continued innovation. Future research should focus on overcoming resistance mechanisms, optimizing combination therapies, and integrating biomarker-driven approaches to improve patient outcomes and enhance personalized treatment strategies.

Can we skip invasive biopsy of sentinel lymph nodes? A preliminary investigation to predict sentinel lymph node status using PET/CT-based radiomics

BackgroundSentinel lymph node (SLN) biopsy (SLNB) is considered the gold standard for detecting SLN metastases in patients with invasive ductal breast cancer (IDC). However, SLNB is invasive and associated with several complications. Thus, this study aimed to evaluate the diagnostic performance of a non-invasive radiomics analysis utilizing 2-deoxy-2-[18F]fluoro-d-glucose positron emission tomography/computed tomography (18F-FDG-PET/CT) for assessing SLN metastasis in IDC patients.MethodsThis retrospective study included 132 patients with biopsy-confirmed IDC, who underwent 18F-FDG PET/CT scans prior to mastectomy or breast-conserving surgery with SLNB. Tumor resection or SLNB was conducted within one-week post-scan. Clinical data and metabolic parameters were analyzed to identify independent SLN metastasis predictors. Radiomic features were extracted from each PET volume of interest (VOI) and CT-VOI. Feature selection involved univariate and multivariate logistic regression analysis, and the least absolute shrinkage and selection operator (LASSO) method. Three models were developed to predict SLN status using the random forest (RF), decision tree (DT), and k-Nearest Neighbors (KNN) classifiers. Model performance was assessed using the area under the receiver operating characteristic curve (AUC).ResultsThe study included 91 cases (32 SLN-positive and 59 SLN-negative patients) in the training cohort and 41 cases (29 SLN-positive and 12 SLN-negative patients) in the validation cohort. Multivariate logistic regression analysis identified Ki 67 and TLG as independent predictors of SLN status. Five PET-derived features, three CT-derived features, and two clinical variables were selected for model development. The AUC values of the RF, KNN, and DT models for the training cohort were 0.887, 0.849, and 0.824, respectively, and for the validation cohort were 0.856, 0.830, and 0.819, respectively. The RF model demonstrated the highest accuracy for the preoperative prediction of SLN metastasis in IDC patients.ConclusionThe PET-CT radiomics approach may offer robust and non-invasive predictors for SLN status in IDC patients, potentially aiding in the planning of personalized treatment strategies for IDC patients.

Evaluation of Circulating Tumor DNA and Carcinoembryonic Antigen Levels and Relationship with Clinicopathological Risk Factors and Prognostic Indices in Colorectal Cancer Patients

Objective: Colorectal cancer (CRC) is a leading cause of cancer-related mortality worldwide. ctDNA has emerged as a promising biomarker for CRC management, offering real-time insights into tumor burden and genetic mutations. This study investigates the correlation between CEA levels, ctDNA, clinicopathological factors, and treatment outcomes in early and advanced CRC patients. Methods: The study retrospectively analyzed data from CRC patients, including early-stage disease and metastatic disease. ctDNA levels, demographic data, and clinical parameters such as CEA, inflammatory indexes, and tumor characteristics were evaluated to determine correlations with treatment outcomes. Results: The study included 20 patients, with 60% diagnosed at the metastatic stage. The study found no statistically significant correlation between ctDNA levels and disease stage, recurrence, or overall survival. While CEA and ctDNA levels were measured, they did not demonstrate a significant relationship with treatment outcomes. Notably, ctDNA levels were higher in metastatic patients, though this was not statistically significant. Conclusion: Despite its potential, the integration of ctDNA as a routine biomarker in CRC care faces challenges, including variability in measurement techniques and cost-effectiveness. However, ctDNA's ability to guide personalized treatment strategies and monitor disease recurrence holds promise. The study's findings align with previous research, suggesting ctDNA as a poor prognostic indicator, though further research is needed. ctDNA represents a significant advance in CRC management, offering non-invasive, real-time insights into tumor dynamics. Ongoing research is expected to solidify its role in personalized treatment planning, potentially leading to more effective and tailored therapies for CRC patients.

Inflammation and resolution in obesity.

Inflammation is an essential physiological defence mechanism, but prolonged or excessive inflammation can cause disease. Indeed, unresolved systemic and adipose tissue inflammation drives obesity-related cardiovascular diseaseand type 2 diabetes mellitus. Drugs targeting pro-inflammatory cytokine pathways or inflammasome activation have been approved for clinical use for the past two decades. However, potentially serious adverse effects, such as drug-induced weight gain and increased susceptibility to infections, prevented their wider clinical implementation. Furthermore, these drugs do not modulate the resolution phase of inflammation. This phase is an active process orchestrated by specialized pro-resolving mediators, such as lipoxins, and other endogenous resolution mechanisms. Pro-resolving mediators mitigate inflammation and development of obesity-related disease, for instance, alleviating insulin resistance and atherosclerosis in experimental disease models, so mechanisms to modulate their activity are, therefore, of great therapeutic interest. Here, we review current clinical attempts to either target pro-inflammatory mediators (IL-1β,NOD-, LRR- and pyrin domain-containing protein 3 (NLRP3)inflammasome,tumour necrosis factor (TNF)and IL-6) or utilize endogenous resolution pathways to reduce obesity-related inflammation and improve cardiometabolic outcomes. A remaining challenge in the field is to establish more precise biomarkers that can differentiate between acute and chronic inflammation and to assess the functionality of individual leukocyte populations. Such advancements would improve the monitoring of drug effects and support personalized treatment strategies that battle obesity-related inflammation and cardiometabolic disease.

Ubiquitin-related gene markers predict immunotherapy response and prognosis in patients with epithelial ovarian carcinoma

Epithelial ovarian carcinoma (EOC) is the most fatal among female reproductive system tumors. The immune tumor microenvironment and ubiquitin-proteasome pathway are closely related to the proliferation, invasion, and response to chemotherapy in EOC. However, their specific roles in EOC have not been fully elucidated. Therefore, we aimed to recognize potential prognostic markers and novel therapeutic targets for EOC. We constructed the ubiquitin-related signature risk model comprising HSP90AB1, FBXO9, SIGMAR1, STAT1, SH3KBP1, EPB41L2, DNAJB6, VPS18, PPM1G, AKAP12, FRK, and PYGB, specifically for patients with EOC. The high-risk model presented a worse prognosis, primarily associated with the B-cell receptor signaling pathway, ECM receptor interaction, focal adhesion, and actin cytoskeleton regulations. Analysis of the immune landscape revealed a higher abundance of B cells, M2 macrophages, neutrophil CD4 T cells, cancer-associated fibroblasts, macrophage neutrophils, and fibroblasts in the high-risk group. It also exhibited lower tumor mutation burden, mRNAsi, and EREG-mRNAsi and reduced sensitivity to other chemotherapy drugs, except dasatinib. These findings serve as a valuable indicator for personalized treatment strategies and clinical stratification in managing patients with EOC. Additionally, our study will serve as a foundation for future mechanistic research to explore the association between the ubiquitin-proteasome pathway and EOC.

Systemic longitudinal immune profiling identifies proliferating Treg cells as predictors of immunotherapy benefit: biomarker analysis from the phase 3 CONTINUUM and DIPPER trials

The identification of predictors for immunotherapy is often hampered by the absence of control groups in many studies, making it difficult to distinguish between prognostic and predictive biomarkers. This study presents biomarker analyses from the phase 3 CONTINUUM trial (NCT03700476), the first to show that adding anti-PD-1 (aPD1) to chemoradiotherapy (CRT) improves event-free survival (EFS) in patients with locoregionally advanced nasopharyngeal carcinoma. A dynamic single-cell atlas was profiled using mass cytometry on peripheral blood mononuclear cell samples from 12 pairs of matched relapsing and non-relapsing patients in the aPD1-CRT arm. Using a supervised representation learning algorithm, we identified a Ki67+ proliferating regulatory T cells (Tregs) population expressing high levels of activated and immunosuppressive molecules including FOXP3, CD38, HLA-DR, CD39, and PD-1, whose abundance correlated with treatment outcome. The frequency of these Ki67+ Tregs was significantly higher at baseline and increased during treatment in patients who relapsed compared to non-relapsers. Further validation through flow cytometry (n = 120) confirmed the predictive value of this Treg subset. Multiplex immunohistochemistry (n = 249) demonstrated that Ki67+ Tregs in tumors could predict immunotherapy benefit, with aPD1 improving EFS only in patients with low baseline levels of Ki67+ Tregs. These findings were further validated in the multicenter phase 3 DIPPER trial (n = 262, NCT03427827) and the phase 3 OAK trial of anti-PD-L1 immunotherapy in NSCLC, underscoring the predictive value of Ki67+ Treg frequency in identifying the beneficiaries of immunotherapy and potentially guiding personalized treatment strategies.

Exploring the Frontier: The Human Microbiome's Role in Rare Childhood Neurological Diseases and Epilepsy.

Emerging research into the human microbiome, an intricate ecosystem of microorganisms residing in and on our bodies, reveals that it plays a pivotal role in maintaining our health, highlighting the potential for microbiome-based interventions to prevent, diagnose, treat, and manage a myriad of diseases. The objective of this review is to highlight the importance of microbiome studies in enhancing our understanding of rare genetic epilepsy and related neurological disorders. Studies suggest that the gut microbiome, acting through the gut-brain axis, impacts the development and severity of epileptic conditions in children. Disruptions in microbial composition can affect neurotransmitter systems, inflammatory responses, and immune regulation, which are all critical factors in the pathogenesis of epilepsy. This growing body of evidence points to the potential of microbiome-targeted therapies, such as probiotics or dietary modifications, as innovative approaches to managing epilepsy. By harnessing the power of the microbiome, we stand to develop more effective and personalized treatment strategies for children affected by this disease and other rare neurological diseases.

Guiding treatment decisions in renal cell carcinoma: the role of biomarkers and clinical factors.

Immune checkpoint inhibitors (ICIs) have transformed the treatment landscape for metastatic renal cell carcinoma (mRCC), significantly improving overall survival and achieving durable responses. This review is timely due to the increasing number of ICI-based regimens now considered standard care for RCC. There is an urgent need to identify reliable biomarkers that can predict therapeutic responses and resistance, a key challenge in current research. While tumor-specific factors such as pathological characteristics, genomic mutations, and transcriptional profiles have been extensively studied, no definitive predictive biomarker has yet emerged. Additionally, advanced technologies are being explored to address tumor heterogeneity. Recent research has focused on novel areas such as the microbiome, radiomics, and spatial transcriptomics, which show promise as potential biomarkers. The translation of these emerging biomarker findings into clinical practice is essential to improving personalized treatment strategies for RCC. Until reliable biomarkers are clinically available, clinical factors may play a pivotal role in guiding individualized treatment decisions to optimize patient outcomes.

A new prognostic scoring system for newly diagnosed multiple myeloma in the era of new drugs.

We developed a new predictive staging system to explore the heterogeneity of survival in newly diagnosed multiple myeloma (NDMM) patients in the real world. In this retrospective study, we evaluated the predictive value of cytogenetic abnormal and clinical data in 375 patients with NDMM at our center. Established a weighted MM prognostic scoring system risk model and validated its predicted PFS and OS by external cohort. Elevated lactate dehydrogenase levels (1 point), international staging system stage II/III (1 point), 1q21+ ≥ 52.75% (0.5 point), del (17p) ≥ 3.5% (0.5 point), and t (14;16) ≥ 35.25% (1 point) had independent prognostic significance. Patients were further divided into three risk groups: low (I) (score 0-0.5, 16.5%), intermediate (II) (score 1, 46.7%), and high (III) (score 1.5-3, 36.8%). In the training cohort, the 3-year PFS was 79.5% vs. 65.3% vs. 40.3% (p < 0.001), and the 3-year OS was 87.7% vs.70.1% vs. 55% (p < 0.001) for the three risk groups. In the external validation cohort, the 3-year PFS was 85.5% vs.61.2% vs. 43.1% (p < 0.001) and the 3-year OS was 91.4% vs.83.5% vs. 56.9% (p < 0.001) for the three risk groups. The risk stratification of this model shows good discrimination and calibration, and its application in clinical practice can improve the risk assessment of patients with NDMM and guide personalized treatment strategies.

Integrated immunogenomic analyses of single-cell and bulk profiling construct a T cell-related signature for predicting prognosis and treatment response in osteosarcoma

PurposesT cells play a crucial role as regulators of anti-tumor activity within the tumor microenvironment (TME) and are closely associated with the progression of osteosarcoma (OS). Nevertheless, the specific role of T cell-related genes (TCRGs) in the pathogenesis of OS remains unclear.MethodsFirst, we processed single-cell RNA sequencing (scRNA-seq) data of OS from the public databases and performed cell annotation. We identified highly variable genes in each cell type using the "FindAllMarkers" function, explored the distribution of different clusters, and investigated inter-cellular communication patterns via the "CellChat" framework. Then, we used multivariate Cox analysis to construct a TCRG and developed a nomogram to predict survival probabilities for OS patients. Finally, we validated the aforementioned results using various cell lines and investigated the immune cell infiltration, expression of immune checkpoints, chemotherapy sensitivity, and the efficacy of targeted therapies across different risk groups.ResultsFrom the scRNA-seq data, we identified 3,000 highly variable genes, presented the top 10 genes, and validated the expression of core genes across different cell lines.Moreover, our analysis delved into interactions between T cells and other cell types. Our analyses constructed a predictive T cell-related signature (TCRS) that incorporated these prognostic TCRGs, showing a clear prognostic separation between the high-risk and low-risk OS patient groups in multiple cohorts. Survival analysis indicated better outcomes for patients classified in the high-risk group. The low-risk group exhibited elevated levels of CD4 memory resting T cells, contrasting with the higher levels of macrophage M0 observed in the high-risk group via the CIBERSORT algorithm. Furthermore, we observed that the low-risk group exhibitedAQ1 significant up-regulation of immune checkpoint genes (ICGs) and lower Tumour Immune Dysfunction and Exclusion (TIDE) scores, suggesting that they may be suitable for immunotherapy. Conversely, the high-risk group appeared more responsive to chemotherapy and targeted therapies, according to our drug sensitivity analysis.ConclusionIn conclusion, our study identified TCRGs, constructed and validated a TCRS for OS, and assessed immune response and drug sensitivity in different risk groups of OS patients. These findings provide novel insights into personalized treatment strategies for OS, potentially guiding more effective therapeutic interventions.

The Adductor–Rectus Angle: A Novel Magnetic Resonance Imaging Measurement in Healthy Adult Individuals

Abstract Background: Groin pain is a complex musculoskeletal condition, causing significant difficulty in its diagnosis and management. The stability of the anterior pelvis is maintained by the formation of a complex fibrous aponeurotic plate by the rectus abdominis and adductor longus tendons. It is, therefore, vital to have a comprehensive understanding of this condition to guide appropriate management. We aimed to measure the adductor–rectus angle (ARA), which is the angle between the rectus abdominis and adductor longus tendon to establish a normal range in a diverse group of healthy individuals on magnetic resonance imaging (MRI) with the aim of investigating its possible association with the occurrence of athletic pubalgia. Materials and Methods: A retrospective cross-sectional study assessed the ARA in 100 asymptomatic normal healthy individuals who had undergone an MRI of the pelvis. The participants were categorized based on gender and divided into three age groups: under 40, between 40 and 60, and above 60 years. Descriptive statistics were calculated for each group and were followed by a one-way analysis of variance to identify any significant differences between these groups. Results: The mean ARA in the entire study cohort was 135.543° +6.4814°. The ARA did not differ significantly among different age groups or genders. Conclusion: The ARA helps to evaluate pelvic muscles’ alignment and offers valuable insights into the force applied to the fibrous aponeurotic plate. This information could potentially aid in identifying athletes at risk of sports hernias and inform the development of personalized treatment strategies.

IRF4: A potential prognostic biomarker for immunotherapy in NSCLC

BackgroundImmunotherapy is revolutionizing the management of advanced non-small cell lung cancer (NSCLC). However, sustained responses are observed in only a minority of patients. Reliable biomarkers are required to identify potential beneficiaries. Interferon regulatory factor 4 (IRF4) plays a crucial role in immune regulation, suggesting its potential as a prognostic biomarker in NSCLC immunotherapy. This study aimed to investigate the predictive role of IRF4 expression in patients with NSCLC receiving immunotherapy. MethodsData from three NSCLC cohorts treated with immune checkpoint inhibitors were collected from the Gene Expression Omnibus (GEO) database. The prognostic significance of IRF4 was assessed across these cohorts, and gene set enrichment analysis (GSEA) was performed. IRF4-based nomograms were developed to predict the outcomes of immunotherapy. Correlations among IRF4 expression, immune cell infiltration, and immunotherapy prognosis were evaluated in our cohort. ResultsElevated IRF4 expression was associated with improved prognosis in patients with NSCLC undergoing immunotherapy, consistent with both GEO dataset and our cohort. IRF4 emerged as an independent predictor for progression-free survival (PFS) and overall survival (OS) in multivariable Cox regression analysis. GSEA analysis highlighted links between IRF4 expression and immune activation pathways such as Chemokine_Signaling_Pathway, Natural_Killer_Cell_Mediated_Cytotoxicity, B_Cell_Receptor_Signaling_Pathway, and T_Cell_Receptor_Signaling_Pathway. In our cohort, immunohistochemistry demonstrated correlations between IRF4 expression and the infiltration of CD8+ T cells, CD20+ B cells, and PD-L1 expression in the tumor microenvironment. ConclusionHigh IRF4 expression in baseline tumor tissue could serve as a favorable predictor of NSCLC immunotherapy outcomes, aiding in personalized treatment strategies.

Examining cardiac toxicity in HER2-positive breast cancer patients using trastuzumab and its influencing factors at Iran Hospital.

Trastuzumab is primarily utilized in the treatment of patients with human epidermal growth factor receptor 2 (HER2) positive breast cancer. This study aimed to investigate the incidence of cardiac toxicity associated with trastuzumab in HER2-positive breast cancer patients at Iran Hospital in 2023, as well as the factors influencing this toxicity. In this cross-sectional study, 200 patients diagnosed with HER2-positive breast cancer and receiving trastuzumab were included. The criteria for heart failure in this study were defined as an ejection fraction (EF) of less than 50% or a decrease of greater than 10% in EF. Descriptive statistics, the chi-square statistical test, Fisher's exact test, and logistic regression analyses were employed to assess the variables. A p-value of less than 0.05 was deemed statistically significant. The mean age of the participants was 51.5 ± 2.5 years. The odds ratio (OR) for the variable of anthracyclines was 1.3 (95% CI: 1.2-1.4); for opium use, the OR was 2.7 (95% CI: 0.9-8.5); for diabetes, the OR was 2.7 (95% CI: 1.2-5.9); for ischemic heart disease, the OR was 3.5 (95% CI: 1.6-7.7); and for hypertension, the OR was 4.8 (95% CI: 2.1-10.7). The OR for obesity was 1.45 (95% CI: 1.01-2.18), and the OR for age was 1.10 (95% CI: 1.01-1.12). No statistically significant association was found between opium use and cardiotoxicity (p = 0.07). This research contributes to the identification of factors that may predict responses to anthracyclines and the potential for cardiotoxicities. Ultimately, this information could inform the development of more personalized treatment strategies.

Revolutionizing Influenza Treatment: A Deep Dive into Targeted Drug Delivery Systems.

Influenza, a highly transmissible respiratory infection caused by influenza viruses A and B, poses a persistent threat to global public health due to its high mutation rate, ability to develop resistance to existing antiviral drugs, and capacity for rapid spread. Current treatment options, including four main classes of antiviral agents-adamantanes, neuraminidase inhibitors, RNA-dependent RNA polymerase inhibitors, and polymerase acidic endonuclease inhibitors- are limited by the emergence of drug-resistant viral strains, non-specific drug distribution, and adverse side effects. Moreover, the effectiveness of traditional vaccines is often compromised by antigenic drift and shift, necessitating the development of alternative therapeutic strategies. This review comprehensively explores the potential of novel targeted drug delivery systems to address these limitations and improve influenza management. Nanotechnology-based platforms, including lipid-based, polymer-based, inorganic, and hybrid nanoparticles, offer enhanced drug delivery through improved bioavailability, targeted action, and controlled release, thus minimizing systemic toxicity and optimizing therapeutic outcomes. Inhalation delivery systems such as dry powder inhalers (DPIs), nebulizers, and nanotechnology-based inhalation formulations provide direct delivery of antiviral agents to the respiratory tract, ensuring rapid onset of action with reduced systemic side effects. Transdermal delivery methods, including microneedle patches and hydrogel-based systems, offer non-invasive alternatives that enhance patient compliance and allow for sustained drug release. Furthermore, this review discusses recent innovations, such as responsive drug delivery systems and multifunctional nanoparticles capable of simultaneous delivery of multiple therapeutic agents, representing a significant advancement in the fight against influenza. These novel approaches promise improved targeting and efficacy and enable personalized treatment strategies, enhancing patient outcomes in both seasonal flu and pandemic scenarios. Integrating these advanced drug delivery systems into clinical practice could revolutionize the management of influenza, offering a promising pathway toward more effective and safer therapies.

A Scoping Review on the Application of Artificial Intelligence in Treating Rare Diseases

Rare diseases affect a small percentage of the population but often present significant challenges in diagnosis, treatment, and management due to their complex and heterogeneous nature. Recent advancements in artificial intelligence (AI) have shown promising potential to address these challenges by improving early diagnosis, personalized treatment strategies, and drug discovery. This scoping review explores the current landscape of AI applications in rare disease treatment. We examine the role of AI-driven tools in enhancing diagnostic accuracy, optimizing treatment pathways, and facilitating drug repurposing for rare conditions. Additionally, we highlight the limitations and ethical concerns associated with AI implementation, such as data privacy, the need for high-quality datasets, and algorithmic transparency. The findings suggest that while AI holds transformative potential, its integration into clinical practice for rare diseases requires multidisciplinary collaboration, ongoing research, and regulatory oversight.

Multimodal radiomics and deep learning models for predicting early femoral head deformity in LCPD

PurposeTo develop a predictive model combining clinical, radiomic, and deep learning features based on X-ray and MRI to identify risk factors for early femoral head deformity in Legg-Calvé-Perthes disease (LCPD). MethodsThis study involved 152 patients diagnosed with early unilateral LCPD across two centers between January 2013 and December 2023, and included an independent external validation set to assess generalizability. Four machine learning methods, including logistic regression (LR), random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGBoost), were employed to develop radiomics deep learning signatures. The clinical-radiomics model (Clinic + Rad), clinical-deep learning model (Clinic + DL), and clinical-radiomics-deep learning model (Clinic + Rad + DL) were developed by integrating radiomics deep learning signatures with clinical variables. The best model, integrated into a nomogram for clinical application, was evaluated using the area under the receiver operating characteristic curve (AUC). ResultsAmong the four machine learning methods, XGBoost demonstrated superior performance in our patient dataset: radiomic (Rad) model (AUC, 0.786) and deep learning (DL) model (AUC, 0.803). Clinical variables such as age at onset and JIC classification were associated with early femoral head deformity (p < 0.05). The combined model incorporating clinical, radiomic, and deep learning signatures demonstrated better predictive ability (AUC, 0.853). The nomogram can assist clinicians in effectively assessing the risk of early femoral head deformity. ConclusionThe Clinic + Rad + DL integrated model may be beneficial for prognostic assessment of early LCPD femoral head deformity, which is crucial for tailoring personalized treatment strategies for individual patients.

Tumor-infiltrating B cell-related lncRNA crosstalk reveals clinical outcomes and tumor immune microenvironment in ovarian cancer based on single-cell and bulk RNA-sequencing

BackgroundThe tumor immune microenvironment (TIME) plays a pivotal role in determining ovarian cancer (OC) prognosis. Long non-coding RNAs (lncRNAs) are key regulators of immune response and tumor progression in OC. Among these, tumor-infiltrating B cells represent an emerging target in immune response pathways. However, the specific involvement of B cell-related lncRNAs (BCRLs) in OC remains unclarified. MethodsLeveraging single-cell and bulk RNA-sequencing data, correlation analysis identified BCRLs in ovarian serous cystadenocarcinoma (OV) from the TCGA database. Subsequently, BCRLIs were filtered through COX survival analysis and the LASSO algorithm, leading to the development of a B cell-related lncRNA scoring system (BCRLss). The predictive accuracy of BCRLss for prognosis in TCGA-OV was assessed and externally validated in an independent cohort. Functional enrichment analyses were conducted to elucidate biological pathways associated with risk subgroups. Additionally, the relationship between BCRLss and TIME was investigated through multiple algorithms and consensus clustering, uncovering potential immune response targets. Drug sensitivity analyses further identified potential therapeutic options tailored to risk subgroups. The highest risk score lncRNA was selected for in vitro validation. ResultsThe BCRLss was constructed using six BCRLIs. Survival analysis revealed an improved prognosis in the low-risk group, with results corroborated by external validation in the ICGC-OV cohort. ROC analysis and nomogram construction confirmed the strong prognostic accuracy of BCRLss. Enrichment analysis highlighted associations between risk subgroups and tumor immune pathways, with the low-risk group demonstrating a more robust immune response and elevated expression of immune checkpoint-related genes. Drug sensitivity tests revealed notable differences across risk subgroups. In vitro experiments confirmed elevated LINC01150 expression in OC cells, and LINC01150 knockdown significantly inhibited the proliferation, invasion, and migration of SKOV3 cells. ConclusionsIn conclusion, BCRLss provides a reliable prognostic tool for predicting clinical outcomes and the immune landscape of patients with OC, offering valuable guidance for immunotherapy target selection and personalized treatment strategies.

Neurophysiological markers of early cognitive decline in older adults: a mini-review of electroencephalography studies for precursors of dementia.

The early detection of cognitive decline in older adults is crucial for preventing dementia. This mini-review focuses on electroencephalography (EEG) markers of early dementia-related precursors, including subjective cognitive decline, subjective memory complaints, and cognitive frailty. We present recent findings from EEG analyses identifying high dementia risk in older adults, with an emphasis on conditions that precede mild cognitive impairment. We also cover event-related potentials, quantitative EEG markers, microstate analysis, and functional connectivity approaches. Moreover, we discuss the potential of these neurophysiological markers for the early detection of cognitive decline as well as their correlations with related biomarkers. The integration of EEG data with advanced artificial intelligence technologies also shows promise for predicting the trajectory of cognitive decline in neurodegenerative disorders. Although challenges remain in its standardization and clinical application, EEG-based approaches offer non-invasive, cost-effective methods for identifying individuals at risk of dementia, which may enable earlier interventions and personalized treatment strategies.