Personalized Diagnosis Research Articles

Paraphilias, problematic sexual behaviours and personality disorder-To what extent are they linked?

Since DSM-III, mental disorders have been classified based on overt symptoms and behaviours rather than underlying psychological and personality processes. This study examines the occurrence of personality dysfunction in individuals with paraphilic disorders and problematic sexual behaviours. The Shedler-Westen Assessment Procedure (SWAP-200), a clinician-rated assessment measure of personality disorders, was administered in a sample of 303 patients referred to a specialist forensic psychotherapy clinic. Sixty-six percent (N =200) of the sample were diagnosable with traits of one or more DSM-5 personality disorders, and 35% (N =106) were diagnosable with categorical DSM-5 personality disorders. When an alternative set of empirically derived personality diagnoses was examined, 94% (N =285) had significant traits of the personality syndromes, and 62% (N =188) of the sample met criteria for categorical diagnoses. Paraphilic fantasies and behaviours may be linked to underlying personality pathology, suggesting implications for assessment and treatment.

The impact of a personal cancer diagnosis on adolescent and young adult cancer survivors' social connectedness: A qualitative analysis.

Adolescent/young adult cancer survivors (AYACS) are diagnosed with cancer between 15 and 39 years of age. Improving AYACS' survivorship quality is crucial-including improving social connectedness, a construct describing the quality, structure and function of social relationships. With better understanding of AYACS' social connectedness, network-based interventions can be developed to foster social health. This study explored how a personal cancer diagnosis impacts AYACS' social connectedness among 35 AYACS 15-25 years old. Three themes emerged through thematic analysis: (1) AYACS experience substantial heterogeneity related to social support needs; (2) AYACS leverage multiple relationships and resources when seeking support after a personal cancer diagnosis; (3) AYACS' individual experiences were unique in that some noted positive changes, whereas others noted negative changes in relationships within social networks, specifically with peers. These findings create a foundation to develop social programming, foster peer relationships, and incorporate social science methods to aid intervention development to strengthen AYACS' social connectedness.

Revealing the critical state and identifying individualized dynamic network biomarker for type 2 diabetes through advanced analysis methods on individual basis

Complex diseases may not always progress in a gradual manner. In the early stages of complex diseases, obvious symptoms are usually not observable, but there is a commonality: there is a brief state of predisease between the progression from normal state to disease state, which usually includes three stages: normal state, critical state of predisease, and disease state. Identifying this critical state, especially with a single sample from an individual, remains a difficult task. In this study, we applied three methods, i.e., single-sample Jensen–Shannon Divergence (sJSD), network information gain (NIG), and temporal network flow entropy (TNFE) method, to a simulated dataset and type 2 diabetes (GSE13268 and GSE13269). Three different methods were utilized to create indexes, including the Inconsistency Index (ICI), NIG, and TNFE, to measure the overall disruption caused by individual samples compared to a set of reference samples. Changes in these indexes were used to identify critical states during the progression of the disease. Results from the numerical simulations show the effectiveness of the three methods. All the methods can detect two critical states based on a single sample, which are respectively at 8 weeks and 16 weeks for GSE13268 and at 4 weeks and 16 weeks for GSE13269, indicating the critical states before deterioration can be detected and the dynamic network biomarkers (DNBs) can be identified successfully. But there are differences in the sensitivity of predictive indicators based on the three methods. The identified dynamic network biomarkers are also significantly different. In addition, the computational principles of the three methods are compared. The proposed three methods can effectively detect the critical state and identify the DNB, solely based on a single sample. The three methods are data-driven and model-free on an individual basis. sJSD method is more sensitive to the critical state, while NIG and TNFE methods are more robust and effective. They can therefore not only help future studies of personalized disease diagnosis but also provide a better insight into clinical practice.

Potential value of novel multiparametric MRI radiomics for preoperative prediction of microsatellite instability and Ki-67 expression in endometrial cancer

Exploring the potential of advanced artificial intelligence technology in predicting microsatellite instability (MSI) and Ki-67 expression of endometrial cancer (EC) is highly significant. This study aimed to develop a novel hybrid radiomics approach integrating multiparametric magnetic resonance imaging (MRI), deep learning, and multichannel image analysis for predicting MSI and Ki-67 status. A retrospective study included 156 EC patients who were subsequently categorized into MSI and Ki-67 groups. The hybrid radiomics model (HMRadSum) was developed by extracting quantitative imaging features and deep learning features from multiparametric MRI using emerging attention mechanism. Tumor markers were subsequently predicted utilizing an XGBoost classifier. Model performance and interpretability were evaluated using standard classification metrics, Gradient-weighted Class Activation Mapping (Grad-CAM), and SHapley Additive exPlanations (SHAP) techniques. For the MSI prediction task, the HMRadSum model achieved area-under-curve (AUC) value of 0.945 (95% CI 0.862-1.000) and accuracy of 0.889. For the Ki-67 prediction task, the AUC and accuracy of HMRadSum model was 0.888 (95% CI 0.743-1.000) and 0.810. This hybrid radiomics model effectively extracted features associated with EC gene expression, providing potential clinical implications for personalized diagnosis, treatment, and treatment strategy optimization.

Tetrahydrocurcumin Alleviates Metabolic Dysfunction-Associated Steatohepatitis in Mice by Regulating Serum Lipids, Bile Acids, and Gut Microbiota

The aim of this study was to investigate the protective effects and potential mechanisms of Tetrahydrocurcumin (THC) on methionine–choline-deficient diet (MCD)-induced MASH in C57BL/6 mice by using multi-omics techniques. The C57BL/6 mice were fed with the MCD for 8 weeks to establish a MASH model, while THC (100 mg·kg−1·d−1) and obeticholic acid (6.5 mg·kg−1·d−1) were administered via gavage to the THC group and the positive control group, respectively. The biochemical indexes of the serum and liver were detected using kits. Liver tissue sections were taken to observe the pathomorphological changes. Serum lipid and bile acid contents were measured via LC-MS, and the changes in ileal intestinal flora were detected by 16S rDNA high-throughput sequencing technology. The results revealed that THC significantly attenuated oxidative stress and lipid accumulation in NCTC-1469 cells and relieved hepatic injury and oxidative stress, reduced hepatic TG content, and improved hepatic steatosis in mice. THC alleviated 34 lipid abnormalities caused by the MCD; increased the abundance and diversity of intestinal flora, the ratio of Firmicutes to Bacteroidota, and the abundance of the probiotic (Verrucomicrobiota, Christensenellaceae, Akkermansiaceae, Lachnospiraceae, Desulfovibrionaceae); and reduced the abundance of obesity-associated pathogenic flora such as Firmicutes. Bile acid analysis showed that THC administration reduced the levels of serum toxic bile acid 7-KDCA and CA. In addition, RT-qPCR studies showed that THC down-regulated the transcript levels of the hepatic lipogenesis-related genes Srebp1c, Acc1, Scd1, and Fas, and up-regulated the transcript levels of the hepatic bile acid secretion-related genes Mrp2 and Bsep. The above results suggest that THC may alleviate MCD-induced MASH by downregulating liver Srebp1c, Acc1, Scd1, and Fas levels to inhibit lipid synthesis, upregulating Mrp2 and Bsep levels to regulate serum toxic BA levels, up-regulating the abundance of intestinal probiotic flora, and down-regulating the abundance of intestinal harmful bacterial flora. The multi-omics findings from the above study identified potential new mechanisms by which THC alleviates MASH, providing new reference targets for the development of anti-MASH drugs. These results also offer a basis for screening clinical diagnostic biomarkers for MASH and provide new directions for personalized diagnosis and treatment.

Predicting factors of ovarian responses in infertile women with polycystic ovary syndrome undergoing IVF/ICSI.

Women with polycystic ovary syndrome (PCOS) show greater heterogeneity in ovarian responses during ovarian stimulation. We aimed to investigate the potential predicting factors among individualized basic parameters that affect poor or hyper ovarian responses in PCOS patients. We retrospectively screened 2058 women with PCOS who underwent their first cycle of in vitro fertilization/intracytoplasmic sperm injection. Spearman correlation analysis and multivariable linear regression model were applied to screen potential variables impacting the number of oocyte retrieved. Further, women with PCOS were divided into poor, sub-optimal, optimal, and hyper responders based on oocyte-retrieved numbers. Logistic regression model and receiver operating characteristic (ROC) curve were used to testify the predicting effect of screened parameters on ovarian response. Multivariable linear regression showed that body mass index (BMI) and follicle-stimulating hormone (FSH) were significantly negatively correlated with oocyte numbers, while luteinizing hormone and anti-Müllerian hormone (AMH) showed a positive correlation. Logistic regression model showed that high BMI (RR: 1.141, 95% CI: 1.090, 1.195) and FSH (RR: 1.161, 95% CI: 1.043, 1.293) were risk factors for poor and sub-optimal ovarian response, but not for hyper response. High AMH level was a risk factor (RR: 1.118, 95% CI: 1.075, 1.163) for hyper ovarian response. The optimal cutoff value was BMI = 23.25kg/cm2, FSH = 6.375IU/L, and AMH = 9.8ng/mL, respectively. Individualized basic parameters including BMI, FSH, and AMH are crucial for predicting ovarian response of women with PCOS, providing valuable information for formulating personalized diagnosis and treatment plans.

Plug-In Design of the Microneedle Electrode Array for Multi-Parameter Biochemical Sensing in Gouty Arthritis.

Gouty arthritis is one of the most common forms of inflammatory arthritis and has brought a significant burden on patients and society. Current strategies for managing gout primarily focus on long-term urate-lowering therapy. With the rapid advancement of point-of-care testing (POCT) technology, continuous monitoring of gout-related biomarkers like uric acid (UA) or inflammatory cytokines can provide rapid and personalized diagnosis for gout management. In this study, a plug-in design of a microneedle electrode array (PIMNA) was developed and integrated into a multi-parameter sensing portable system in combination with embedded circuits and a mobile application. The system enabled real-time, in situ, and dynamic monitoring of biomarkers, including UA, reactive oxygen species (ROS), and pH at gouty joints. The multi-parameter monitoring system demonstrated a wide linear response range, excellent selectivity, stability, reproducibility, and reliable signal transmission performance. In vivo experiments demonstrated the real-time monitoring capability of PIMNA for UA, ROS, and pH, showing the potential to facilitate urate-lowering management and inflammation assessment. Prospectively, the system enables quantitative analysis of the complexity and diversity of gout, presenting promising applications in clinical practice. This work provides a unique strategy with potential for broader applications in gout management and arthritic disease treatment.

A novel deep learning-based 1D-CNN-optimized GRU approach for heart disease prediction

Cardiac data modeling remains challenging in emerging nations across Asia and Africa. This research proposes an ensemble classification method leveraging machine learning (ML) to predict cardiac problems, providing physicians with actionable insights for personalized diagnoses and treatments. An ensemble classification method for modelling cardiac temporal data is presented in this research. The minimax scalar transform is applied to first denoise the input data, and then the ENN-smote approach is applied to address the issue of an imbalanced dataset. Secondly, we employ a standard deep learning (DL) methodology. To identify the irregularities in the cardiac data pattern, a gated recurrent unit (GRU) classifier and a one-dimensional convolutional neural network (1D-CNN) are introduced. A typical genetic algorithm (GA) is used to optimize the suggested GRU network in order to pass over the local minima. This aids with 1D-CNN weight training. GA methodically optimizes the model’s GRU parameters. The data processed were finally used by the hybrid 1D-CNN-Optimized GRU network to predict cardiovascular illness. The suggested method attained a training accuracy of over 97% and a test accuracy of over 96% on the dataset. The proposed model’s overall accuracy is 99%. This is completely evaluated against other deep learning algorithms.

Investigation of a hemophilia family with one female hemophilia A patient and 12 male hemophilia A patients.

Hemophilia A (HA) is an X-chromosome-linked recessive genetic disorder. Female carriers may have bleeding symptoms, but rarely have moderate or severe disease. We identified a female patient with moderate HA by pedigree tracking and genetic testing in a HA family involving consanguineous marriage. To investigate the clinical and laboratory data, as well as F8 genetic variant affecting members in her family. We constructed a detailed pedigree diagram and performed coagulation analyses, including factor VIII activity (FVIII:C), FVIII inhibitor, and von Willebrand factor antigen (VWF: Ag) on 20 family members. The genomic DNA of 11 members was screened for intron 1 and intron 22 inversions using long-distance real-time polymerase chain reaction (RT-PCR). Their F8 coding genes were sequenced with an automatic next-generation sequencing. Thirteen HA persons with hemophilia (12 males, one female) and 18 female carriers were identified in the family. VWF: Ag level was normal in all 13 persons with hemophilia and 7 carriers tested. The female HA patient had FVIII:C 1.9 IU/dL and was homozygous for F8:c.1918G > T:p.V640F. Genetic testing is conducive to the diagnosis of hemophilia carriers and persons with hemophilia. F8: c.1918G > T:p.V640F is the pathogenic HA variant in this family. In any hemophilia family, we need to pay more attention to female carriers and patients.

Pop-Up Paper-Based Biosensor for a Dual-Mode Lung Cancer ctDNA Assay Based on Novel CoB Nanosheets with Dual-Enzyme Activities and a Portable Smartphone/Barometer for Readout.

Timely monitoring of circulating tumor DNA (ctDNA) in serum is meaningful for personalized diagnosis and treatment for lung cancer. Cheap and efficient point-of-care testing (POCT) has emerged as a promising method, especially in a low-resource setting. Herein, (i) a 3D pop-up paper-based POCT device was designed and manufactured via a cheap method; it was used for saving time and efficiently building a biosensor; (ii) a novel cobalt boride nanosheet (CoB NS) nanozyme with abundant groups was used for POCT dual-mode signal transduction and then a portable smartphone/pressure meter to readout; (iii) a user-friendly smartphone app was fabricated for achieving more convenient POCT. Detailly, the dual-mode signal generated was based on the CoB NS with peroxidase activity to catalyze a chromogenic agent to develop color and with catalase activity to catalyze decomposition of H2O2 to O2. Density functional theory (DFT) and experimental results showed a good catalysis performance of the CoB NS via studying its five possible catalytic pathways, in which the metal Co is the catalytic active site center that acts as the electron donor and promotes electron transfer between the CoB NS and the adsorbed substrates. Benefiting from that, the proposed method showed good analytical ability in detecting ctDNA. Besides, its accuracy was valued by comparing it with the standard qPCR method to detect real samples from tumor cells and tumor-bearing mice, which showed a consistent result and potential practical applicability of the proposed method for POCT ctDNA. In general, this work not only provided a dual-mode POCT platform that could also be applied for other analytes but also first revealed the nanozyme properties of the CoB NS and inspired its new application from electrocatalysis, energy, etc. to biomedicine.

Role of radiation emergency medicine: historical view-a perspective on the past, present, and future.

The more science progresses, the more life and society change. Medicine also changes with the times and the culture. This is also true for radiation emergency medicine, which includes dose-assessment leading to diagnosis, treatment, medical follow-up and prognosis of persons who have developed acute injury or illness due to radioactive contamination or radiation exposure. Before the report of X-rays by Roentgen, there was evidence that X-rays had been emitted from the electrically excited Crookes tube and that skin injury had been caused by the X-rays. Thus, the history of radiation and its exposure started before Roentgen. During the early stage of radiation use, people were simply exposed to radiation but were unaware of any danger. Radioactive materials were found soon after Roentgen's report, and contamination with these materials occurred. Together with the development of science and technology, sophisticated radiation devices were produced, and the use and application of radiation became much enhanced. New radionuclides were found one after another, leading to identification of different qualities of radiation. Development of nuclear physics allowed people to artificially produce radionuclides and to construct a nuclear reactor. After World War II, nuclear power plants were constructed, and related facilities such as nuclear fuel processing, reprocessing and spent fuel storage facilities were built. If radiation accidents or events occur at such facilities, radiation exposure with thermal or chemical burns could occur. Together with the expansion of globalism in the world and division in the society, there are now increasing concerns regarding the malicious usage of radiation by radiological dispersal devices (RDDs) including a dirty bomb. Upon detonation of RDDs, blast and thermal injuries with radiation exposure could be caused. In the present society, the natures of exposure to radiation and contamination with radioactive materials have become much more complicated. Not even mentioning the atomic bomb, the detonation of RDDs also necessitates scenarios of medical responses to complicated injuries and the involvement of numbers of people. This article looks back at the history of radiation and addresses the medical responses to radiation injuries that change with the times.

Advances and prospects of precision nanomedicine in personalized tumor theranostics.

Tumor, as the second leading cause of death globally, following closely behind cardiovascular diseases, remains a significant health challenge worldwide. Despite the existence of various cancer treatment methods, their efficacy is still suboptimal, necessitating the development of safer and more efficient treatment strategies. Additionally, the advancement of personalized therapy offers further possibilities in cancer treatment. Nanomedicine, as a promising interdisciplinary field, has shown tremendous potential and prospects in the diagnosis and treatment of cancer. As an emerging approach in oncology, the application of nanomedicine in personalized cancer therapy primarily focuses on targeted drug delivery systems such as passive targeting drug delivery, active targeting drug delivery, and environmentally responsive targeting drug delivery, as well as imaging diagnostics such as tumor biomarker detection, tumor cell detection, and in vivo imaging. However, it still faces challenges regarding safety, biocompatibility, and other issues. This review aims to explore the advances in the use of nanomaterials in the field of personalized cancer diagnosis and treatment and to investigate the prospects and challenges of developing personalized therapies in cancer care, providing direction for the clinical translation and application.

Gene expression ranking change based single sample pre-disease state detection.

To prevent disease, it is of great importance to detect the critical point (pre-disease state) when the biological system abruptly transforms from normal to disease state. However, rapid and accurate pre-disease state detection is still a challenge when there is only a single sample available. The state transition of the biological system is driven by the variation in regulations between genes. In this study, we propose a rapid single-sample pre-disease state-identifying method based on the change in gene expression ranking, which can reflect the coordinated shifts between genes, that is, S-PCR. The R codes of S-PCR can be accessed at https://github.com/ZhenshenBao/S-PCR. This model-free method is validated by the successful identification of pre-disease state for both simulated and five real datasets. The functional analyses of the pre-disease state-related genes identified by S-PCR also demonstrate the effectiveness of this computational approach. Furthermore, the time efficiency of S-PCR is much better than that of its peers. Hence, the proposed S-PCR approach holds immense potential for clinical applications in personalized disease diagnosis.

"…but I know something's not right here": Exploring the diagnosis and disclosure experiences of persons living with ALS.

Amyotrophic Lateral Sclerosis (ALS), an incurable motor neuron disease, primarily affects those between the ages of 60-79, and has an approximate post-diagnosis life-expectancy of only two to five years. The condition has an unpredictable but ultimately terminal trajectory that poses challenges for patients, caregivers and healthcare providers. While the diagnosis and disclosure are critical periods for intervention and support, knowledge regarding the relational, communicational and psychodynamic forces that occur within the process of diagnostic disclosure is relatively limited. The purpose of this study was to explore the experiences of persons living with ALS in the diagnosis and disclosure of the condition, with the support of their caregivers. We conducted a focus group and in-depth individual interviews with people living with ALS (n = 9), and caregivers (n = 9). The interviews were transcribed, cleaned, and anonymized, and then entered into NVivo 11 for thematic analysis. Participants discussed the diagnostic process, including inklings and subtle changes prior to diagnosis, attempts at self-diagnosis, and the lengthy assessment process. Time was also a consideration in the diagnostic disclosure process, in which participants shared how the disclosure was the product of longstanding conversations with their care providers. It was described as rarely a shock to finally have confirmation. Participants shared their information seeking strategies and needs for a diagnosis that, for them, typically came with insufficient information on the disease, prognosis, and next steps. This project serves as a step in bridging the relevant gaps in our knowledge and understanding towards improved person-centered care practices in the diagnosis and disclosure of ALS.

Accurate prediction of colorectal cancer diagnosis using machine learning based on immunohistochemistry pathological images

Colorectal cancer (CRC) ranks as the third most prevalent tumor and the second leading cause of mortality. Early and accurate diagnosis holds significant importance in enhancing patient treatment and prognosis. Machine learning technology and bioinformatics have provided novel approaches for cancer diagnosis. This study aims to develop a CRC diagnostic model based on immunohistochemical staining image features using machine learning methods. Initially, CRC disease-specific genes were identified through bioinformatics analysis, SVM-RFE and Random Forest algorithm utilizing RNA-seq data from both GEO and TCGA databases. Subsequently, verification of these genes was performed using proteomics data from CPTAC and HPA database, resulting in identification of target proteins (AKR1B10, CA2, DHRS9, and ZG16) for further investigation. SVM and CNN were then employed to analyze and integrate the characteristics of immunohistochemical images to construct a reliable CRC diagnostic model. During the training and validation process of this model, cross-validation along with external validation methods were implemented to ensure accuracy and reliability. The results demonstrate that the established diagnostic model exhibits excellent performance in distinguishing between CRC and normal controls (accuracy rate: 0.999), thereby presenting potential prospects for clinical application. These findings are expected to provide innovative perspectives as well as methodologies for personalized diagnosis of CRC while offering more precise references for promising treatment.

Brief Report: Aging With HIV: An Epidemiological Profile of Persons With Diagnosed HIV Aged 50 Years and Older in New York State, 2012–2021

Background: Advanced antiretroviral treatment has led to a growing population of older persons with HIV. To understand the characteristics of persons aging with HIV, this analysis examines epidemiological profiles of persons with diagnosed HIV through 2021 aged 50 years and older in New York State. Methods: Persons diagnosed with HIV and reported to the NYS HIV registry by December 31, 2021, were included in the analysis. Characteristics of persons aged 50 years and older were compared with persons younger than 50 years. Results: Persons diagnosed with HIV and aged 50 years and older more often reported heterosexual transmission risk and were more often females than individuals diagnosed with HIV younger than 50 years. Among new diagnoses in 2021, persons aged 50 years and older were more likely to have a stage 3 HIV diagnosis. By the end of 2021, 57% of persons living with diagnosed HIV were aged 50 years and older. There was an upward trend of deaths with cardiovascular disease as an underlying cause of death among persons aged 50 years and older. Conclusions: More females diagnosed with HIV and a higher percentage of persons who reported heterosexual transmission risk among persons aged 50 years and older suggest a need for enhanced clinician education and sexual health discussions with this adult population. A greater rate of stage 3 HIV diagnoses in persons aged 50 years and older emphasizes the need for specialized HIV testing and treatment, care for comorbidities, and social supports for this aging population.

The surgical case reports of Hippocrates of Cos. Medical Practice in Ancient Greece

Which theoretical and practical competences do the surgical case histories of the Hippocratic Corpus convey? The 431 Hippocratic case histories have been studied for reports and communication on diagnosis, therapy and prognosis of single persons and groups of patients suffering from surgical diseases. Within the 7 books of the Hippocratic "Epidemics", a total of 18 patients with general and visceral surgical diseases are described. The main signs of the disorders were fever, pain, looseness, constipation, colic, swelling and bleeding, the most common affections abscesses, ruptures, ulcers and necroses. In addition, breast cancer can be reliably identified. Seven men are facing six women. Moreover, four children and one group are described. The patients' information about the course of their disease is sparse. Diagnostics were limited to inspection and palpation. In many cases, the treating physician confined to conservative measures. Among the surgical interventions incision, cauterization and bloodletting dominated. 11 of 18 patients succumbed to their diseases. The Hippocratic doctor diagnosed and treated a limited number of general and visceral surgical diseases. The symptoms of inflammation and traumatic lesions are narrated in detail. The observer describes the bloody secretion in two women with breast cancer as briefly as impressively. In two thirds of the cases, neither conservative measures alone nor in combination with invasive treatment led to enduring success. Complete recovery is reported of only three persons. The unfavourable balance of treatment for the involved physicians is an important reason for the confidence of scientists in the credibility of the Hippocratic case histories.

Advances in deep learning for personalized ECG diagnostics: A systematic review addressing inter-patient variability and generalization constraints.

The Electrocardiogram (ECG) remains a fundamental tool in cardiac diagnostics, yet its interpretation has traditionally relied on cardiologists' expertise. Deep learning has revolutionized medical data analysis, especially within ECG diagnostics. However, the challenge of inter-patient variability limits the generalizability of ECG-AI models trained on population datasets, often reducing accuracy for specific patients or groups. While prior studies have developed various deep-learning techniques to address this issue, these advancements largely focus on universal models without tailoring to individual patient needs. A systematic review methodology was employed, comprehensively searching four major databases (PubMed, IEEE Xplore, Web of Science, and Google Scholar), meticulously screening and analyzing studies from 2020 to 2024 using a rigorous two-step selection process to ensure methodological quality and relevance, ultimately yielding 112 studies for comprehensive analysis. This review offers a unique perspective by systematically examining recent deep-learning approaches designed explicitly for personalized ECG diagnosis, emphasizing models that address patient-specific variability. Using a rigorous methodology for selecting and analyzing relevant studies, we provide an in-depth overview of advanced techniques, including transfer learning, generative adversarial networks, meta-learning, and domain adaptation. The review also investigates the limitations of these methods, such as balancing generalization with patient specificity and addressing data privacy concerns. By identifying these challenges and outlining future directions, this review highlights the transformative potential of deep learning for ECG diag-nostics in clinical practice. Our findings underscore a pathway toward more accurate, efficient, and patient-centered cardiac diagnostics, setting a foundation for future personalized care innovations.

Highly stretchable, self-healing, adhesive, 3D-printable and antibacterial double-network hydrogels for multifunctional wearable sensors.

Conductive hydrogels based on sodium alginate (SA) have potential applications in human activity monitoring and personal medical diagnosis due to their good conductivity and flexibility. However, most sensing SA-hydrogels exhibit poor mechanical properties and lack of self-healing, self-adhesive, and antibacterial properties, greatly limiting their practical applications. Therefore, in this paper, a multifunctional double-network PAA-SA hydrogel consisting of poly(acrylic acid) (PAA) and sodium alginate (SA) was prepared by a simple strategy. As a rigid network structure, SA endowed the hydrogel double network structure with excellent mechanical performance. As a wearable sensor, the PAA-SA hydrogel exhibited excellent tensile properties (strain: 1799.2 %), self-healing, high sensitivity (GF = 9.9), reliable repeatability, self-adhesive, 3D printability and antibacterial activity. Additionally, the highly sensitive wearing sensing PAA-SA hydrogel could accurately and real-time monitor various intense or subtle human movements, such as joint bending, face and throat vibration. Moreover, PAA-SA hydrogels were not only used for handwritten recognition of Arabic numerals and English letters, but also for real-time sensing of temperature changes and monitoring of human sweating. The prepared multifunctional wearable sensing hydrogel has the advantages of simple and versatile methods and low cost, making it a promising candidate for applications in different fields such as electronic skin, soft robotics, and medical monitoring.

TMODINET: A trustworthy multi-omics dynamic learning integration network for cancer diagnostic

Multiple types of omics data contain a wealth of biomedical information which reflect different aspects of clinical samples. Multi-omics integrated analysis is more likely to lead to more accurate clinical decisions. Existing cancer diagnostic methods based on multi-omics data integration mainly focus on the classification accuracy of the model, while neglecting the interpretability of the internal mechanism and the reliability of the results, which are crucial in specific domains such as precision medicine and the life sciences. To overcome this limitation, we propose a trustworthy multi-omics dynamic learning framework (TMODINET) for cancer diagnostic. The framework employs multi-omics adaptive dynamic learning to process each sample to provide patient-centered personality diagnosis by using self-attentional learning of features and modalities. To characterize the correlation between samples well, we introduce a graph dynamic learning method which can adaptively adjust the graph structure according to the specific classification results for specific graph convolutional networks (GCN) learning. Moreover, we utilize an uncertainty mechanism by employing Dirichlet distribution and Dempster-Shafer theory to obtain uncertainty and integrate multi-omics data at the decision level, ensuring trustworthy for cancer diagnosis. Extensive experiments on four real-world multimodal medical datasets are conducted. Compared to state-of-the-art methods, the superior performance and trustworthiness of our proposed algorithm are clearly validated. Our model has great potential for clinical diagnosis.