The diagnosis of hematological disorders is currently established from the combined results of different tests, including those assessing morphology (M), immunophenotype (I), cytogenetics (C), and molecular biology (M) (collectively known as the MICM classification). In this workflow, most of the results are interpreted manually (i.e., by a human, without automation), which is expertise-dependent, labor-intensive, time-consuming, and with inherent interobserver variability. Also, with advances in instruments and technologies, the data is gaining higher dimensionality and throughput, making additional challenges for manual analysis. Recently, artificial intelligence (AI) has emerged as a promising tool in clinical hematology to ensure timely diagnosis, precise risk stratification, and treatment success. In this review, we summarize the current advances, limitations, and challenges of AI models and raise potential strategies for improving their performance in each sector of the MICM pipeline. Finally, we share perspectives, highlight future directions, and call for extensive interdisciplinary cooperation to perfect AI with wise human-level strategies and promote its integration into the clinical workflow.

Clinical research on rare diseases has always faced multiple challenges in clinical research design and implementation due to small sample sizes of patients,high heterogeneity,and limited research resources.The rapid development of digital intelligence technology has provided innovative solutions for rare disease research.This article systematically explores the current status and response strategies of clinical research on rare diseases in the digital intelligence age.On the one hand,the efficiency of rare disease research has been optimized through adaptive design,mixed trial mode,and precision medicine stratification methods.On the other hand,solutions based on digital technology have been proposed to address the practical challenges of recruitment difficulties and underrepresentation of rare disease clinical research patients,data management and technical barriers,and insufficient coverage of natural medical history and baseline databases through digital intelligence technology.By combining international collaboration,intelligent screening,and remote experiments,a multidisciplinary collaboration and international cooperation,adaptive design,digital data platform,and patient-centered remote research model have been constructed as the core implementation strategies.Typical cases demonstrate that digital intelligence technology not only effectively shortens the drug development cycle,but also significantly enhances patient benefits,providing a replicable practical paradigm for global rare disease research.The practice of digital platforms represented by the International Rare Disease Research Alliance and the China Rare Disease Diagnosis and Treatment Collaboration Network has further verified the feasibility and promotional value of the digitalization path.In summary,digital intelligence technology has shown considerable promise in overcoming the clinical research challenges of rare diseases and accelerating the development of treatment plans,providing systematic references for researchers,regulatory agencies,and patient organizations.It is expected to drive the clinical research of rare diseases towards a more efficient and accurate future.

Objective To develop and validate a machine learning-based predictive model to assess the in-hospital mortality risk of patients with myocardial infarction(MI)complicated by heart failure(HF)undergoing percutaneous coronary intervention(PCI).Methods This retrospective study analyzed MI patients with HF who underwent PCI at The First Affiliated Hospital of Xinjiang Medical University from January 2019 to January 2023.Patient data,including demographic characteristics,vital signs,laboratory test results,imaging parameters and medication use,were collected and randomly divided into a training set(70％)and a validation set(30％).The extreme gradient boosting(XGBoost)model was used to identify variables significantly associated with in-hospital mortality,and the Shapley additive explanations(SHAP)model was applied to assess feature importance.A predictive model was then constructed using univariate and multivariate Logistic regression analyses.Model performance was evaluated using receiver operating characteristic(ROC)curves,area under the curve(AUC)values,calibration curves,and decision curve analysis.Finally,a nomogram was developed for intuitive risk assessment.Results A total of 1 214 MI patients with HF were included in the study,with a median age of 64 years.The in-hospital mortality rate was 7.41％(90 deaths).XGBoost feature selection identified ten key predictive variables:age,myoglobin,albumin,fasting blood glucose,N-terminal pro-B-type natriuretic peptide(NT-proBNP),diabetes mellitus,creatinine,cystatin C,procalcitonin,and left ventricular ejection fraction.Based on these variables,a Logistic regression model was developed,with seven final predictors:age,diabetes mellitus,creatinine,fasting blood glucose,cystatin C,NT-proBNP,and albumin.The model demonstrated high predictive accuracy,with AUC value of 0.869(95％CI:0.84-0.89)in the training set and 0.827(95％CI:0.79-0.85)in the validation set.The calibration curve indicated that the predicted probabilities were consistent with the actual observed outcomes,and decision curve analysis showed that the model had a high net benefit across various decision thresholds.Conclusion This study developed a machine learning-based predictive model incorporating Logistic regression to assess the in-hospital mortality risk of MI patients with HF undergoing PCI.The model demonstrated high predictive performance and clinical utility.The nomogram derived from this model provides an intuitive tool for individualized risk assessment,aiding clinicians in the early identification of high-risk patients,optimizing intervention strategies,and improving patient outcomes.

Objective To analyze the long-term trend in the disease burden of congenital birth defects(CBDs)among neonates in China from 1990 to 2021,compare the trend with global patterns,and identify key subtypes along with their association with socioeconomic status to provide evidence for public health interventions.Methods Utilizing data from the Global Burden of Disease Study 2021(GBD 2021),we extracted indicators including disability-adjusted life years(DALYs),mortality,and prevalence for the neonatal period(＜28 days)in China,encompassing ten major CBD subtypes.Joinpoint regression analysis was employed to calculate annual percent changes and estimate annual percent changes(EAPC),with comparisons of subtype composition between 1990 and 2021.Nonlinear regression was used to assess the relationship between DALYs rates and the Socio-demographic Index(SDI).Results From 1990 to 2021,DALYs rates for neonatal CBDs declined significantly both globally and in China,with China's EAPC at-4.67％[95％CI:(—5.06,—4.28)],substantially exceeding the global average of-1.70％[95％CI:(—1.75,—1.64)].Congenital heart anomalies remained the primary burden,while neural tube defects and orofacial clefts in China showed notable reductions(EAPCs of-7.25％and-11.22％,respectively).However,DALYs rates for congenital musculoskeletal and limb anomalies exceeded global expected levels.A resurgence in the prevalence was observed post-2015,with higher burdens in males.DALYs rates exhibited a negative correlation with SDI.Conclusion China has achieved significant reductions in the neonatal CBDs burden,surpassing global trends;yet challenges persist in managing congenital heart anomalies and musculoskeletal defects.Future efforts should focus on enhancing early screening,surgical interventions,and regional equity to align with global health objectives.

In recent decades, the global community has encountered several significant viral outbreaks, including the Ebola epidemic in West Africa, the Zika virus epidemic in South America, and the recent worldwide COVID-19 pandemic. In these instances, the deployment of effective vaccines has been instrumental in protecting public health. Nevertheless, as new challenges emerge in the prevention and management of infectious diseases, the traditional model of global vaccine development confronts both unprecedented opportunities and challenges. These circumstances underscore the limitations inherent in conventional vaccine development, particularly the protracted timelines and substantial costs involved. This article examines innovative approaches in contemporary vaccine clinical trials, investigates randomization techniques specific to vaccine studies, and delineates essential statistical considerations pertinent to vaccine trial design. The objective is to provide scientific support for vaccine development and to foster ongoing innovation and optimization within the realm of vaccine research and development.

Objective To develop and validate a machine learning-based predictive model to assess the in-hospital mortality risk of patients with myocardial infarction(MI)complicated by heart failure(HF)undergoing percutaneous coronary intervention(PCI).Methods This retrospective study analyzed MI patients with HF who underwent PCI at The First Affiliated Hospital of Xinjiang Medical University from January 2019 to January 2023.Patient data,including demographic characteristics,vital signs,laboratory test results,imaging parameters and medication use,were collected and randomly divided into a training set(70％)and a validation set(30％).The extreme gradient boosting(XGBoost)model was used to identify variables significantly associated with in-hospital mortality,and the Shapley additive explanations(SHAP)model was applied to assess feature importance.A predictive model was then constructed using univariate and multivariate Logistic regression analyses.Model performance was evaluated using receiver operating characteristic(ROC)curves,area under the curve(AUC)values,calibration curves,and decision curve analysis.Finally,a nomogram was developed for intuitive risk assessment.Results A total of 1 214 MI patients with HF were included in the study,with a median age of 64 years.The in-hospital mortality rate was 7.41％(90 deaths).XGBoost feature selection identified ten key predictive variables:age,myoglobin,albumin,fasting blood glucose,N-terminal pro-B-type natriuretic peptide(NT-proBNP),diabetes mellitus,creatinine,cystatin C,procalcitonin,and left ventricular ejection fraction.Based on these variables,a Logistic regression model was developed,with seven final predictors:age,diabetes mellitus,creatinine,fasting blood glucose,cystatin C,NT-proBNP,and albumin.The model demonstrated high predictive accuracy,with AUC value of 0.869(95％CI:0.84-0.89)in the training set and 0.827(95％CI:0.79-0.85)in the validation set.The calibration curve indicated that the predicted probabilities were consistent with the actual observed outcomes,and decision curve analysis showed that the model had a high net benefit across various decision thresholds.Conclusion This study developed a machine learning-based predictive model incorporating Logistic regression to assess the in-hospital mortality risk of MI patients with HF undergoing PCI.The model demonstrated high predictive performance and clinical utility.The nomogram derived from this model provides an intuitive tool for individualized risk assessment,aiding clinicians in the early identification of high-risk patients,optimizing intervention strategies,and improving patient outcomes.

In recent decades, the global community has encountered several significant viral outbreaks, including the Ebola epidemic in West Africa, the Zika virus epidemic in South America, and the recent worldwide COVID-19 pandemic. In these instances, the deployment of effective vaccines has been instrumental in protecting public health. Nevertheless, as new challenges emerge in the prevention and management of infectious diseases, the traditional model of global vaccine development confronts both unprecedented opportunities and challenges. These circumstances underscore the limitations inherent in conventional vaccine development, particularly the protracted timelines and substantial costs involved. This article examines innovative approaches in contemporary vaccine clinical trials, investigates randomization techniques specific to vaccine studies, and delineates essential statistical considerations pertinent to vaccine trial design. The objective is to provide scientific support for vaccine development and to foster ongoing innovation and optimization within the realm of vaccine research and development.

Objective To analyze the long-term trend in the disease burden of congenital birth defects(CBDs)among neonates in China from 1990 to 2021,compare the trend with global patterns,and identify key subtypes along with their association with socioeconomic status to provide evidence for public health interventions.Methods Utilizing data from the Global Burden of Disease Study 2021(GBD 2021),we extracted indicators including disability-adjusted life years(DALYs),mortality,and prevalence for the neonatal period(＜28 days)in China,encompassing ten major CBD subtypes.Joinpoint regression analysis was employed to calculate annual percent changes and estimate annual percent changes(EAPC),with comparisons of subtype composition between 1990 and 2021.Nonlinear regression was used to assess the relationship between DALYs rates and the Socio-demographic Index(SDI).Results From 1990 to 2021,DALYs rates for neonatal CBDs declined significantly both globally and in China,with China's EAPC at-4.67％[95％CI:(—5.06,—4.28)],substantially exceeding the global average of-1.70％[95％CI:(—1.75,—1.64)].Congenital heart anomalies remained the primary burden,while neural tube defects and orofacial clefts in China showed notable reductions(EAPCs of-7.25％and-11.22％,respectively).However,DALYs rates for congenital musculoskeletal and limb anomalies exceeded global expected levels.A resurgence in the prevalence was observed post-2015,with higher burdens in males.DALYs rates exhibited a negative correlation with SDI.Conclusion China has achieved significant reductions in the neonatal CBDs burden,surpassing global trends;yet challenges persist in managing congenital heart anomalies and musculoskeletal defects.Future efforts should focus on enhancing early screening,surgical interventions,and regional equity to align with global health objectives.

Clinical research on rare diseases has always faced multiple challenges in clinical research design and implementation due to small sample sizes of patients,high heterogeneity,and limited research resources.The rapid development of digital intelligence technology has provided innovative solutions for rare disease research.This article systematically explores the current status and response strategies of clinical research on rare diseases in the digital intelligence age.On the one hand,the efficiency of rare disease research has been optimized through adaptive design,mixed trial mode,and precision medicine stratification methods.On the other hand,solutions based on digital technology have been proposed to address the practical challenges of recruitment difficulties and underrepresentation of rare disease clinical research patients,data management and technical barriers,and insufficient coverage of natural medical history and baseline databases through digital intelligence technology.By combining international collaboration,intelligent screening,and remote experiments,a multidisciplinary collaboration and international cooperation,adaptive design,digital data platform,and patient-centered remote research model have been constructed as the core implementation strategies.Typical cases demonstrate that digital intelligence technology not only effectively shortens the drug development cycle,but also significantly enhances patient benefits,providing a replicable practical paradigm for global rare disease research.The practice of digital platforms represented by the International Rare Disease Research Alliance and the China Rare Disease Diagnosis and Treatment Collaboration Network has further verified the feasibility and promotional value of the digitalization path.In summary,digital intelligence technology has shown considerable promise in overcoming the clinical research challenges of rare diseases and accelerating the development of treatment plans,providing systematic references for researchers,regulatory agencies,and patient organizations.It is expected to drive the clinical research of rare diseases towards a more efficient and accurate future.

Background: and Purpose This study aimed to determine the changes in cerebral blood flow (CBF) in patients who received different durations of hemodialysis (HD) using arterial spin labeling magnetic resonance imaging. Methods: The study included 46 patients who received HD and 24 demographically similar healthy controls (HCs). Patients who received HD were divided into three subgroups based on its duration: HD-1 (n=15, dialysis duration ≤24 months), HD-2 (n=16, dialysis duration >24 and ≤72 months), and HD-3 (n=15, dialysis duration ≥73 months). All subjects completed the Mini Mental State Examination and Montreal Cognitive Assessment tests, and the patients who received HD underwent laboratory tests. Group-level differences in the global and regional CBFs between patients who received HD and HCs were assessed. Correlation analysis was performed to evaluate the associations among CBF, clinical variables, and cognitive function. Results: Compared with HCs, global and regional CBFs were significantly increased in the HD-1 and HD-2 groups (p<0.05), but there was no significant difference in the HD-3 group (p>0.05). However, compared with the HD-1 group, the HD-3 group had significantly decreased global and regional CBFs (p<0.05). The cognitive function was worse in patients who received long-term HD than in HCs. Increased dialysis duration and hemoglobin level were predictive risk factors for decreased CBF in patients who received long-term HD. Conclusions Patients who received long-term HD with normal CBF had worse cognitive function, which may be related to increased dialysis duration.