BACKGROUND: There are limited data available regarding the connection between heavy metal exposure and mortality among hypertension patients.
OBJECTIVE: We intend to establish an interpretable machine learning (ML) model with high efficiency and robustness that monitors mortality based on heavy metal exposure among hypertension patients.
METHODS: Our datasets were obtained from the US National Health and Nutrition Examination Survey (NHANES, 2013-2018). We developed 5 ML models for mortality prediction among hypertension patients by heavy metal exposure, and tested them by 10 discrimination characteristics. Further, we chose the optimally performing model after parameter adjustment by genetic algorithm (GA) for prediction. Finally, in order to visualize the model\'s ability to make decisions, we used SHapley Additive exPlanation (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) algorithm to illustrate the features. The study included 2347 participants in total.
RESULTS: A best-performing eXtreme Gradient Boosting (XGB) with GA for mortality prediction among hypertension patients by 13 heavy metals was selected (AUC 0.959; 95% CI 0.953-0.965; accuracy 96.8%). According to sum of SHAP values, cadmium (0.094), cobalt (2.048), lead (1.12), tungsten (0.129) in urine, and lead (2.026), mercury (1.703) in blood positively influenced the model, while barium (- 0.001), molybdenum (- 2.066), antimony (- 0.398), tin (- 0.498), thallium (- 2.297) in urine, and selenium (- 0.842), manganese (- 1.193) in blood negatively influenced the model.
CONCLUSIONS: Hypertension patients\' mortality associated with heavy metal exposure was predicted by an efficient, robust, and interpretable GA-XGB model with SHAP and LIME. Cadmium, cobalt, lead, tungsten in urine, and mercury in blood are positively correlated with mortality, while barium, molybdenum, antimony, tin, thallium in urine, and lead, selenium, manganese in blood is negatively correlated with mortality.

The economic trend and the health care landscape are rapidly evolving across Asia. Effective real-world data (RWD) for regulatory and clinical decision-making is a crucial milestone associated with this evolution. This necessitates a critical evaluation of RWD generation within distinct nations for the use of various RWD warehouses in the generation of real-world evidence (RWE). In this article, we outline the RWD generation trends for 2 contrasting nation archetypes: \"Solo Scholars\"-nations with relatively self-sufficient RWD research systems-and \"Global Collaborators\"-countries largely reliant on international infrastructures for RWD generation. The key trends and patterns in RWD generation, country-specific insights into the predominant databases used in each country to produce RWE, and insights into the broader landscape of RWD database use across these countries are discussed. Conclusively, the data point out the heterogeneous nature of RWD generation practices across 10 different Asian nations and advocate for strategic enhancements in data harmonization. The evidence highlights the imperative for improved database integration and the establishment of standardized protocols and infrastructure for leveraging electronic medical records (EMR) in streamlining RWD acquisition. The clinical data analysis and reporting system of Hong Kong is an excellent example of a successful EMR system that showcases the capacity of integrated robust EMR platforms to consolidate and produce diverse RWE. This, in turn, can potentially reduce the necessity for reliance on numerous condition-specific local and global registries or limited and largely unavailable medical insurance or claims databases in most Asian nations. Linking health technology assessment processes with open data initiatives such as the Observational Medical Outcomes Partnership Common Data Model and the Observational Health Data Sciences and Informatics could enable the leveraging of global data resources to inform local decision-making. Advancing such initiatives is crucial for reinforcing health care frameworks in resource-limited settings and advancing toward cohesive, evidence-driven health care policy and improved patient outcomes in the region.

With the rapid development of modern medical technology and the dramatic increase in the amount of medical data, traditional centralized medical information management is facing many challenges. In recent years blockchain, which is a peer-to-peer distributed database, has been increasingly accepted and adopted by different industries and use cases. Key areas of healthcare blockchain applications include electronic medical record (EMR) management, medical device supply chain management, remote condition monitoring, insurance claims and personal health data (PHD) management, among others. Even so, there are a number of challenges in applying blockchain concepts to healthcare and its data, including interoperability, data security privacy, scalability, TPS and so on. While these challenges may hinder the development of blockchain in healthcare scenarios, they can be improved with existing technologies In this paper, we propose a blockchain-based healthcare operations management framework that is combined with the Interplanetary File System (IPFS) for managing EMRs, protects data privacy through a distributed approach while ensuring that this medical ledger is tamper-proof. Doctors act as full nodes, patients can participate in network maintenance either as light nodes or as full nodes, and the hospital acts as the endpoint database of data, i.e., the IPFS node, which saves the arithmetic power of nodes and allows the data stored in the hospitals and departments to be shared with the other organizations that have uploaded the data. Therefore, the integration of blockchain and zero-knowledge proof proposed in this paper helps to protect data privacy and is efficient, better scalable, and more throughput.

BACKGROUND: In recent years, the incidence of gastrointestinal neuroendocrine tumors (GI-NETs) has remarkably increased due to the widespread use of screening gastrointestinal endoscopy. Currently, the most common treatments are surgery and endoscopic resection. Compared to surgery, endoscopic resection possesses a higher risk of resection margin residues for the treatment of GI-NETs.
METHODS: A total of 315 patients who underwent surgery or endoscopic resection for GI-NETs were included. We analyzed their resection modality (surgery, ESD, EMR), margin status, Preoperative marking and Prognosis.
RESULTS: Among 315 patients included, 175 cases underwent endoscopic resection and 140 cases underwent surgical treatment. A total of 43 (43/175, 24.57%) and 10 (10/140, 7.14%) patients exhibited positive resection margins after endoscopic resection and surgery, respectively. Multivariate regression analysis suggested that no preoperative marking and endoscopic treatment methods were risk factors for resection margin residues. Among the patients with positive margin residues after endoscopic resection, 5 patients underwent the radical surgical resection and 1 patient underwent additional ESD resection. The remaining 37 patients had no recurrence during a median follow-up of 36 months.
CONCLUSIONS: Compared with surgery, endoscopic therapy has a higher margin residual rate. During endoscopic resection, preoperative marking may reduce the rate of lateral margin residues, and endoscopic submucosal dissection may be preferred than endoscopic mucosal resection. Periodical follow-up may be an alternative method for patients with positive margin residues after endoscopic resection.

UNASSIGNED: Data about eosinophil-to-lymphocyte ratio (ELR) and eosinophil-to-monocyte ratio (EMR) in patients with community-acquired pneumonia (CAP) are rare. We aimed to evaluate the role of EMR and ELR in predicting disease severity and mortality in patients with CAP.
UNASSIGNED: A total of 454 patients (76 with severe CAP (SCAP), 378 with non-SCAP) were enrolled from November 18, 2020, and November 21, 2021. Laboratory examination on day 1 after admission was measured. The ELR and EMR values were calculated for patients. Propensity score matching (PSM) was performed to balance potential confounding factors. Binary logistic regression model was fitted to identify the potential risk factors for disease severity and Cox proportional hazards regression model analysis for mortality in CAP. Receiver operating characteristic (ROC) analysis was performed to distinguish disease severity and mortality.
UNASSIGNED: EMR and ELR at admission were significantly lower in SCAP patients than in non-SCAP patients (P<0.001). EMR < 0.018 ([OR] = 12.104, 95% CI: 4.970-29.479), neutrophil (NEU) ([OR]=1.098, 95% CI:1.005-1.199), and age ([OR]=1.091, 95% CI:1.054-1.130) were independent risk factors for disease severity of CAP. EMR < 0.032 ([HR] = 5.816, 95% CI: 1.704-9.848) was an independent predictor of in-hospital mortality. Combining EMR or ELR with CRB-65 improved the overall accuracy of disease severity prediction (AUC from 0.894 to 0.937), the same as CURB-65. The area under the curve of EMR (AUC=0.704; 95% CI: 0.582-0.827) to predict in-hospital mortality was higher than that of CURB-65 (AUC=0.619; 95% CI: 0.484-0.754). Otherwise, EMR combined with CRB-65 (AUC=0.721; 95% CI: 0.592-0.851) had significantly higher diagnostic accuracy for in-hospital mortality than that of CURB-65 alone.
UNASSIGNED: EMR combined with CRB-65 was superior to CURB-65 in predicting mortality in patients with CAP. This new combination was simpler and easier to obtain for physicians in clinics or admission, and it was more convenient for early recognition of patients with poor prognoses.

There are limited data available regarding the connection between hypertension and heavy metal exposure. The authors intend to establish an interpretable machine learning (ML) model with high efficiency and robustness that identifies hypertension based on heavy metal exposure. Our datasets were obtained from the US National Health and Nutrition Examination Survey (NHANES, 2013-2020.3). The authors developed 5 ML models for hypertension identification by heavy metal exposure, and tested them by 10 discrimination characteristics. Further, the authors chose the optimally performing model after parameter adjustment by Genetic Algorithm (GA) for identification. Finally, in order to visualize the model\'s ability to make decisions, the authors used SHapley Additive exPlanation (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) algorithm to illustrate the features. The study included 19 368 participants in total. A best-performing eXtreme Gradient Boosting (XGB) with GA for hypertension identification by 16 heavy metals was selected (AUC: 0.774; 95% CI: 0.772-0.776; accuracy: 87.7%). According to SHAP values, Barium (0.02), Cadmium (0.017), Lead (0.017), Antimony (0.008), Tin (0.007), Manganese (0.006), Thallium (0.004), Tungsten (0.004) in urine, and Lead (0.048), Mercury (0.035), Selenium (0.05), Manganese (0.007) in blood positively influenced the model, while Cadmium (-0.001) in urine negatively influenced the model. Study participants\' hypertension associated with heavy metal exposure was identified by an efficient, robust, and interpretable GA-XGB model with SHAP and LIME. Barium, Cadmium, Lead, Antimony, Tin, Manganese, Thallium, Tungsten in urine, and Lead, Mercury, Selenium, Manganese in blood are positively correlated with hypertension, while Cadmium in blood is negatively correlated with hypertension.

The study aims to develop AICare, an interpretable mortality prediction model, using electronic medical records (EMR) from follow-up visits for end-stage renal disease (ESRD) patients. AICare includes a multichannel feature extraction module and an adaptive feature importance recalibration module. It integrates dynamic records and static features to perform personalized health context representation learning. The dataset encompasses 13,091 visits and demographic data of 656 peritoneal dialysis (PD) patients spanning 12 years. An additional public dataset of 4,789 visits from 1,363 hemodialysis (HD) patients is also considered. AICare outperforms traditional deep learning models in mortality prediction while retaining interpretability. It uncovers mortality-feature relationships and variations in feature importance and provides reference values. An AI-doctor interaction system is developed for visualizing patients\' health trajectories and risk indicators.

Endoscopic submucosa dissection (ESD) allows complete excision of the whole lesion, which results in a higher percentage of complete excision and an improved quality of life by minimizing the amount of excision as opposed to an endoscopic mucosal resection (EMR). Although ESD is now being carried out in the majority of hospitals, ESD\'s possible complications (such as trauma and perforation) have given rise to doubts about ESD practices in patients with early-stage stomach cancer when deciding on therapy and reimbursement. This study was designed to evaluate the effectiveness and safety of ESD over EMR in treating early-stage stomach cancer. Four main databases have been searched, including EMBASE and published. The ROBINS-I tool suggested in the Cochrane Handbook has been applied to evaluate the quality of the chosen trials. It may better reflect the risk of bias in the included studies. The meta-analyses were carried out with ReMan 5.3, and the results were treated with endote. Seven cohort studies have been completed. Meta analysis indicated that EMR and ESD surgery did not differ significantly from each other in terms of postoperative haemorrhage (OR, 0.76; 95%CI, 0.56,1.04 p = 0.09); EMR, however, was associated with a lower rate of postoperative perforation than ESD surgery (OR, 0.36; 95%CI, 0.24,0.54 p < 0.0001). Taking into account that ESD and EMR did not differ significantly in the risk of wound bleeding, even though the risk of perforation is not likely to result in life-threatening illness. In the analysis of these data, however, the potential advantages of EMR might be greater than ESD.

Electrolytic manganese residue (EMR) is a harmful by-product in the electrolytic manganese industry. Calcination is an efficient method for disposing EMR. In this study, thermogravimetric-mass spectrometry (TG-MS) combined with X-ray diffraction (XRD) was used for analysing the thermal reactions and phase transitions during calcination. The pozzolanic activity of calcined EMR was determined by the potential hydraulicity test and strength activity index (SAI) test. The leaching characteristics of Mn were determined by TCLP test and BCR SE method. The results showed that MnSO4 was converted into stable MnO2 during calcination. Meanwhile, Mn-rich bustamite (Ca0.228Mn0.772SiO3) was converted into Ca(Mn, Ca)Si2O6. The gypsum was transformed into anhydrite and then decomposed into CaO and SO2. Additionally, the organic pollutants and ammonia were completely removed following calcination at 700 °C. The leaching concentration of Mn decreased from 819.9 mg L-1 to 339.6 mg L-1 following calcination at 1100 °C. The chemical forms of Mn were transformed from acid-soluble fraction to residual fraction. The pozzolanic activity tests indicated that EMR1100-Gy maintained a complete shape. The compressive strength of EMR1100-PO reached 33.83 MPa. Finally, the leaching concentrations of heavy metals met the standard limits. This study provides a better understanding for the treatment and utilization of EMR.

BACKGROUND: To effectively monitor medical insurance funds in the era of big data, the study tries to construct an inpatient cost rationality judgement model by designing a virtuous cycle of inpatient cost supervision information system and exploring a complete set of inpatient cost supervision methods.
OBJECTIVE: To lay the foundation for applying artificial intelligence (AI) technology in medical insurance cost control supervision and provide feasible paths and available tools for medical insurance cost control managers.
METHODS: By way of collecting and cleaning electronic medical record (EMR) data from 2016 to 2018 of a city in East China, focusing on basic patient information and cost information, and using a combination of machine learning modeling and information system construction, the study tries to form a feasible inpatient cost supervision method and operation path.
RESULTS: The set of the regulatory method, applied in nursing homes of a city in East China, is compelling. The accuracy rates of rationality judgement in different main diseases are stable up to 80%, the false positive rate is steady within 10%, and rehabilitation fee days of hospitalization, and the number of complications are important factors affecting the rationality of the inpatient cost.
CONCLUSIONS: The model construction and optimization method combining machine learning and information system can make practical cost rationality judgement on medical institution\'s inpatient cost data, which can directly reflect the key influencing factors of relevant inpatient costs, and achieve the effect of guiding medical behavior and improving the efficiency of medical insurance fund use.