Medical Resources Research Articles

Impact of the COVID-19 Pandemic on Home Medical Care Utilization in Japan: An Interrupted Time Series Analysis.

The COVID-19 pandemic affected healthcare utilization worldwide, but changes in home medical care utilization have not been fully revealed. This study aims to clarify the changes in the use of home medical care services in Japan due to the pandemic. Interrupted time series analysis of national medical claims data. Individuals with home medical care use occurring in Japan between April 2019 and March 2022. The declaration of a state of emergency (April 2020) by the Japanese government. The outcomes were the monthly uses of regular home visits, emergency house calls, terminal care, and in-home deaths. Terminal care was stratified by care setting (home or nursing home) and the type of home medical care facilities (enhanced home care support clinics and hospitals (HCSCs), conventional HCSCs, and general clinics and hospitals). Regular home visits showed no significant change, but emergency house calls exhibited an upward trend (1258 uses/month, 95% CI 43to2473). Both terminal care and in-home deaths experienced an immediate increase in level (1116 uses/month, 95% CI 549to1683; 1459 uses/month, 95% CI 612to2307), followed by a gradual increase in trend (141 uses/month, 95% CI 73to209; 215 uses/month, 95% CI 114to317). The immediate increase of terminal care occurred only for home patients. Enhanced HCSCs showed the most prominent increase in both level and trend, followed by conventional HCSCs, and general clinics and hospitals. The COVID-19 pandemic increased the use of emergency house calls and terminal care among home medical care in Japan, particularly for home patients and enhanced HCSCs. These findings suggest that the pandemic revitalized the importance of home medical care as a patient-centered care delivery model and highlight the need for strategic healthcare planning and home medical care resource allocation to anticipate future pandemics.

Machine-learning-based prediction by stacking ensemble strategy for surgical outcomes in patients with degenerative cervical myelopathy

BackgroundMachine learning (ML) is extensively employed for forecasting the outcome of various illnesses. The objective of the study was to develop ML based classifiers using a stacking ensemble strategy to predict the Japanese Orthopedic Association (JOA) recovery rate for patients with degenerative cervical myelopathy (DCM).MethodsA total of 672 patients with DCM were included in the study and labeled with JOA recovery rate by 1-year follow-up. All data were collected during 2012–2023 and were randomly divided into training and testing (8:2) sub-datasets. A total of 91 initial ML classifiers were developed, and the top 3 initial classifiers with the best performance were further stacked into an ensemble classifier with a supported vector machine (SVM) classifier. The area under the curve (AUC) was the main indicator to assess the prediction performance of all classifiers. The primary predicted outcome was the JOA recovery rate.ResultsBy applying an ensemble learning strategy (e.g., stacking), the accuracy of the ML classifier improved following combining three widely used ML models (e.g., RFE-SVM, EmbeddingLR-LR, and RFE-AdaBoost). Decision curve analysis showed the merits of the ensemble classifiers, as the curves of the top 3 initial classifiers varied a lot in predicting JOA recovery rate in DCM patients.ConclusionsThe ensemble classifiers successfully predict the JOA recovery rate in DCM patients, which showed a high potential for assisting physicians in managing DCM patients and making full use of medical resources.

Spatial-temporal distribution of neglected tropical diseases burdens in China from 2005 to 2020

BackgroundOut of the 21 neglected tropical diseases (NTDs) listed by the World Health Organization, 15 affect the People’s Republic of China. Despite significant achievements in controlling NTDs, comprehensive assessments of the disease burden based on actual case data and detailed information on spatial and temporal dynamics are still lacking. This study aims to assess the disease burden and spatial–temporal distribution of NTDs in China from 2005 to 2020, to provide a reference for the formulation of national health agendas in line with the global health agenda, and guide resource allocation.MethodsThe number of cases and deaths of major NTDs in China from 2005 to 2020 were downloaded from the China Public Health Science Data Center (https://www.phsciencedata.cn/Share/index.jsp) of the Chinese Center for Disease Control and Prevention and relevant literatures. Simplified formulas for disability-adjusted life years (DALYs) helped estimate the years of life lost (YLLs), years lived with disability (YLDs), and total DALYs. Spatial autocorrelation analysis of the average NTDs burden data for the years 2005 to 2020 was evaluated using Moran's I statistic.ResultsChina's overall NTDs burden decreased significantly, from 245,444.53 DALYs in 2005 to 18,984.34 DALYs in 2020, marking a reduction of 92.27%. In 2005, the DALYs caused by schistosomiasis and rabies represent a substantial proportion of the total disease burden, accounting for 65.37% and 34.43% respectively. In 2015, Hunan and Sichuan provinces had the highest diversity of NTDs, with 9 and 8 number of different NTDs reported respectively. And the highest disease burden was observed in Sichuan (242,683.46 DALYs), Xizang Zizhiqu (178,318.99 DALYs) and Guangdong (154,228.31 DALYs). The “high-high” clustering areas of NTDs were mainly in China's central and southern regions, as identified by spatial autocorrelation analysis.ConclusionsChina has made unremitting efforts in the prevention and control of NTDs, and the disease burden of major NTDs in China has decreased significantly. Using the One Health concept to guide disease prevention and control in the field to effectively save medical resources and achieve precise intervention.Graphical abstract

Socioeconomic Indices Are Associated With Increased Resource Utilizations, but Not 90-Day Complications Following Total Hip and Knee Arthroplasty

BackgroundSocioeconomic disadvantage has been associated with negative outcomes following total hip arthroplasty (THA) and total knee arthroplasty (TKA). The area deprivation index (ADI) and distressed communities index (DCI) are composite rankings that score socioeconomic status (SES) using patients’ home addresses. The purpose of this study was to examine the association of ADI and DCI with outcomes following THA and TKA while controlling for potential confounding covariates. MethodsA series of 4,146 consecutive patients undergoing primary THA and TKA between January 2018 and May 2023 were queried from our institutional total joint registry. The 90-day medical and surgical complications and resource utilization were collected. The ADI and DCI scores were obtained for each patient, and the association between these scores and postoperative outcomes was analyzed. ResultsThe ADI and DCI were both associated with patient age, sex, race, comorbidity burden, and smoking status. After controlling for these variables, higher ADI and DCI scores were associated with increased length of stay (P = 0.003 and P = 0.008, respectively), but were not associated with the occurrence of any 90-day complication, reoperation, or revision. ConclusionsThe SES, as quantified by ADI and DCI, was associated with multiple known risk factors for complications following THA and TKA, but was not independently associated with complications, reoperations, or revision surgeries at 90 days postoperatively. While convenient metrics for the quantification of SES, in some populations, ADI and DCI may not be independently associated with detrimental outcomes following THA and TKA.

Improving Fairness of Automated Chest Radiograph Diagnosis by Contrastive Learning.

Purpose To develop an artificial intelligence model that uses supervised contrastive learning (SCL) to minimize bias in chest radiograph diagnosis. Materials and Methods In this retrospective study, the proposed method was evaluated on two datasets: the Medical Imaging and Data Resource Center (MIDRC) dataset with 77 887 chest radiographs in 27 796 patients collected as of April 20, 2023, for COVID-19 diagnosis and the National Institutes of Health ChestX-ray14 dataset with 112 120 chest radiographs in 30 805 patients collected between 1992 and 2015. In the ChestX-ray14 dataset, thoracic abnormalities included atelectasis, cardiomegaly, effusion, infiltration, mass, nodule, pneumonia, pneumothorax, consolidation, edema, emphysema, fibrosis, pleural thickening, and hernia. The proposed method used SCL with carefully selected positive and negative samples to generate fair image embeddings, which were fine-tuned for subsequent tasks to reduce bias in chest radiograph diagnosis. The method was evaluated using the marginal area under the receiver operating characteristic curve difference (∆mAUC). Results The proposed model showed a significant decrease in bias across all subgroups compared with the baseline models, as evidenced by a paired t test (P < .001). The ∆mAUCs obtained by the proposed method were 0.01 (95% CI: 0.01, 0.01), 0.21 (95% CI: 0.21, 0.21), and 0.10 (95% CI: 0.10, 0.10) for sex, race, and age subgroups, respectively, on the MIDRC dataset and 0.01 (95% CI: 0.01, 0.01) and 0.05 (95% CI: 0.05, 0.05) for sex and age subgroups, respectively, on the ChestX-ray14 dataset. Conclusion Employing SCL can mitigate bias in chest radiograph diagnosis, addressing concerns of fairness and reliability in deep learning-based diagnostic methods. Keywords: Thorax, Diagnosis, Supervised Learning, Convolutional Neural Network (CNN), Computer-aided Diagnosis (CAD) Supplemental material is available for this article. © RSNA, 2024 See also the commentary by Johnson in this issue.

Maternal mortality due to obstetric hemorrhage by surgical injury during cesarean section: A nationwide study.

Obstetric hemorrhage remains a largely preventable cause of maternal mortality globally. The contribution of uterine atony to hemorrhage-related maternal mortality has decreased in France, while the contribution of other causes of obstetric hemorrhage such as surgical injury during cesarean has been reported to increase. However, little evidence exists regarding the risk factors and care processes of women who died from this cause of hemorrhage. Therefore, we aimed to describe the clinical profile, underlying mechanisms, and preventability factors among women who died from obstetric hemorrhage by surgical injury during cesarean section. Nationwide analysis of all hemorrhage-related maternal deaths by surgical injury during cesarean in France identified by the nationwide permanent enhanced maternal mortality surveillance system (ENCMM) between 2007 and 2018. We described the characteristics of the women, delivery hospitals, circumstances of hemorrhage, features of obstetric and resuscitation/transfusion care, and main preventability factors. Between 2007 and 2018, hemorrhage-related maternal mortality in France decreased from 1.6/100 000 live births (95% CI 1.1-2.2) (39/2 472 650) in 2007-2009 to 0.8/100 000 live births (95% CI 0.5-1.3) (19/2 311 783) in 2016-2018. Hemorrhage-related maternal mortality ratio due to surgical injury during cesarean increased from 0.08 (95% CI 0.01-0.3) (2/2 472 650) to 0.2 (95% CI 0.07-0.5) (5/2 311 783) per 100 000 live births. Among the 18 women who died from surgical injury during cesarean over the 12-year study period, we report a high prevalence of obesity (67%, 12/18), previous cesarean (72%, 13/18), and second-stage cesareans (56%, 10/18). In 22% (4/18), cesarean section was performed in a hospital providing <1000 births annually, with no blood bank (39%, 7/18) or no adult intensive care (44%, 8/18) on-site. Overall preventability of deaths was 94% (17/18). Main preventability factors were related to delay in hemorrhage diagnosis (77%, 14/18) due to late recognition of abnormal parameters (33%, 6/18) and late bedside ultrasound (56%, 10/18), and delay in management due to insufficient surgical skills (56%, 10/18). In France, surgical injury during cesarean section is an increasing, largely preventable contributor to hemorrhage-related maternal mortality, as other causes of fatal hemorrhage have become less frequent. The profile of these women showed a high prevalence of obesity, previous cesarean, second-stage cesarean, and delivery in hospitals with limited medical and surgical resources, which suggests explanatory mechanisms for the fatal outcome and opportunities for prevention.

Exploring the factors affecting the readiness for hospital discharge after total knee arthroplasty: A structural equation model approach.

To investigate the factors that influence readiness for hospital discharge in Chinese patients after total knee arthroplasty and to identify priorities for nursing interventions. A cross-sectional study. From January to August 2022, data were collected from 339 patients at two tertiary A-level hospitals in Jinan, Shandong Province. SPSS 26.0 and Mplus 8.3 software were used for statistical analysis. Results from multiple linear regression showed that patients' age, residence status, education level, knee pain during sleep, quality of discharge teaching, self-efficacy for rehabilitation, pain control knowledge, and social support were factors influencing their readiness for hospital discharge. The results of the structural equation model had shown that there were also indirect effects of the education level, knee pain during sleep, quality of discharge teaching, and pain control knowledge. Patients' readiness for hospital discharge needs further improvement, hence physicians and nurses should judiciously allocate medical resources and concentrate their efforts on high-risk groups characterized by low readiness for hospital discharge. This study underscores the importance of physicians and nurses prioritizing key factors such as age, residency status, education level, and social support in total knee arthroplasty patients to enhance their readiness for hospital discharge. By implementing targeted discharge planning, effective pain management, and comprehensive rehabilitation education, healthcare providers can improve patient outcomes. This study identified key factors influencing readiness for hospital discharge in total knee arthroplasty patients, guiding targeted nursing interventions to improve post-operative care. STROBE. The participants recruited for this study were actively engaged in the data collection process.

Weekly Image Guidance in Patients With Cervical Cancer Treated With Intensity-Modulated Radiation Therapy: Results of a Large Cohort Study.

Image guidance is recommended for patients undergoing intensity-modulated radiation therapy (IMRT) for cervical cancer. In this study, we evaluated the feasibility of a weekly image guidance pattern and analyzed the long-term outcomes in a large cohort of patients. The study enrolled patients with Stage IB-IVA cervical cancer who received definitive radiotherapy or concurrent chemoradiotherapy. IMRT was delivered at a dose of 50.4 Gy in 28 fractions, with weekly cone-beam computed tomography (CBCT). Physicians advised patients on rectum and bladder preparation to help them prepare on nonimaging guidance days. When significant tumor regression was observed, a second computed tomography simulation and replanning were performed. The median follow-up periods were 63.4 months. The incidence rates of loco-regional and distant failure were 9.9% and 13.6%. The 5-year overall survival (OS), disease-free survival (DFS), loco-regional relapse-free survival (LRFS), and distant metastasis-free survival (DMFS) rates were 80.1%, 72.9%, 78.3%, and 74.8%, respectively. For patients with different stages, the 5-year OS, DFS, LRFS, and DMFS rates were statistically significant. For patients with and without positive regional lymph nodes, the 5-year OS, DFS, LRFS, and DMFS rates were 64.5% and 86.0%, 56.8% and 78.8%, 62.7% and 84.3%, and 58.8% and 81.0%, respectively. Multivariate analysis showed that age, histology, tumor size, cancer stage, pretreatment squamous cell carcinoma antigen level, and para-aortic metastatic lymph nodes were independent prognostic factors of OS. Fifty-six (4.0%) patients experienced late Grade 3/4 chronic toxicities. IMRT with weekly CBCT is an acceptable image guidance strategy in countries with limited medical resources.

Hyperthermia and Exertional Heatstroke During Running, Cycling, Open Water Swimming, and Triathlon Events.

Few previous epidemiological studies, sports medicine position statements, and expert panel consensus reports have evaluated the similarities and differences of hyperthermia and exertional heatstroke (EHS) during endurance running, cycling, open water swimming, and triathlon competitions. Accordingly, we conducted manual online searches of the PubMed and Google Scholar databases using pre-defined inclusion criteria. The initial manual screenings of 1192 article titles and abstracts, and subsequent reviews of full-length pdf versions identified 80 articles that were acceptable for inclusion. These articles indicated that event medical teams recognized hyperthermia and EHS in the majority of running and triathlon field studies (range, 58.8 to 85.7%), whereas few reports of hyperthermia and EHS appeared in cycling and open water swimming field studies (range, 0 to 20%). Sports medicine position statements and consensus reports also exhibited these event-specific differences. Thus, we proposed mechanisms that involved physiological effector responses (sweating, increased skin blood flow) and biophysical heat transfer to the environment (evaporation, convection, radiation, and conduction). We anticipate that the above information will help race directors to distribute pre-race safety advice to athletes and will assist medical directors to better allocate medical resources (eg, staff number and skill sets, medical equipment) and optimize the management of hyperthermia and EHS.

Feasibility and safety evaluation of ultra-remote robot-assisted laparoscopic hysterectomy

ObjectiveTo assess the safety and feasibility of ultra-remote robot-assisted laparoscopic hysterectomy using the Edge Multi-Port Endoscopic Surgical Robot MP1000 (Shenzhen Edge Medical Co., Ltd., Shenzhen, China) combined with 5G communication technology. MethodsA case of remote robot-assisted laparoscopic hysterectomy was successfully completed on May 2024 by using the Edge Multi-Port Endoscopic Surgical Robot MP1000 at Zhongnan Hospital of Wuhan University and the People's Liberation Army General Hospital, approximately 1, 200 ​km apart. The procedure was simultaneously broadcast during the 36th Annual Meeting of the International Society for Gynecologic Endoscopy in Conjuction with the Peking University Gynecologic Oncology Summit Forum. ResultsA 49-year-old female was hospitalized in the Department of Gynecology of Zhongnan Hospital of Wuhan University for frequent urination for half a year and increased menstrual flow for over a month. The patient was diagnosed with abnormal uterine bleeding caused by multiple uterine leiomyoma and endometrial polyps, combined with moderate anemia. There were no contraindications for surgery, and the patient had surgical indications. On May 2024, the patient underwent a 5G remote robot-assisted laparoscopic hysterectomy and bilateral salpingectomy under general anesthesia. The procedure was successful, with no surgical complications and no interruptions during the live broadcast. The intraoperative blood loss was approximately 20 ​mL, and the surgery lasted about 70 ​min. The bidirectional latency during the operation was around 19 ​ms, with no adverse events related to the robot or the network. The patient recovered well postoperatively and was discharged on the fourth day with no postoperative complications. ConclusionPreliminary findings indicate that ultra-remote robot-assisted laparoscopic hysterectomy is safe and feasible with the support of 5G communication technology. This surgery represents the first globally broadcast remote procedure in the field of gynecology, marking a new milestone in the stability and safety of China's remote medical technology. Remote robotic surgery is expected to be widely promoted in the future, providing services to patients in areas with limited medical resources.

An innovative patient clustering method using data envelopment Analysis–Discriminant analysis and artificial neural networks: A case study in healthcare systems

A major lesson healthcare managers learned from the COVID-19 outbreak is the need for more effective patient classification and medical resource allocation for future pandemics. In their view, hospitalization mortality could be greatly reduced if more effective systems for patient classification were in place before the outbreak to evaluate and assign treatment facilities. This study presents a scalable patient clustering approach using a Self-Organizing Map (SOM) of the Artificial Neural Network (ANN) to cluster patients for appropriate treatment allocation. The patients’ membership is forecasted using Data Envelopment Analysis–Discriminant Analysis (DEA-DA). The objectives of this research are to develop a flexible framework that healthcare systems can adopt to cluster patients based on specific testing criteria from medical records and to assign them to suitable medical centers with appropriate treatment resources. This method aims to enhance healthcare system efficiency by ensuring patients with severe illnesses receive care at well-equipped centers, while those with milder symptoms are directed to other suitable facilities. The approach is scalable and adaptable to any type of widespread illness and aims to increase recovery rates and decrease mortality rates, as confirmed by the case study results.

Towards a Region-Wide Glycaemic Management System: Strategies and Applications for Glycaemic Management of Patients with Diabetes During Hospitalisation.

This study proposes a region-wide blood glucose management system to solve the problem of blood glucose management in patients with diabetes. A professional team of doctors, nurses and dietitians jointly developed a region-wide blood glucose management system. The system operates through a collaborative approach where each team member utilises their specialised role, such as data monitoring, algorithm development or patient support, to contribute to a comprehensive blood glucose management network. This integration ensures accurate glucose tracking, personalised feedback and timely adjustments to treatment plans. The system allows the patient to have a good treatment plan, giving comprehensive medical guidance, and the physician team is responsible for the patient's health status. The region-wide blood glucose management system increased the overall blood glucose monitoring rate of patients and reduced the hospitalisation time (from 11.27 days to 9.52 days) and hospitalisation costs (from 12,173.8 yuan to 9502.4 yuan). At the same time, the system effectively counted the incidence and occurrence time of hyperglycaemia and hypoglycaemia adverse events, which can provide a reference for clinical prevention of adverse events. A region-wide blood glucose management system can improve medical efficiency, save medical resources and provide a strong guarantee for the health of patients with diabetes. Compared with the traditional diabetes management mode, the region-wide blood glucose management system is more systematic and standardised, meaning it can better meet the needs of patients with diabetes.

Digital orthodontics' current state and prospects

The world is transitioning to a digital age, and orthodontics is no exception. The use of technology in orthodontics has risen dramatically, and computer literacy is no longer rudimentary. Since the invention and development of mobile phones, digital technology has h a huge impact on our daily lives. Digital technology has substantially improved medical diagnosis, educational resources, therapeutic modalities, and surgical techniques over the past two decades. When computerised scheduling was introduced in dental and orthodontic offices in 1974, digital technology began to take hold. Every facet of orthodontic treatment has been impacted by digital technology

Development of a System for Predicting Hospitalization Time for Patients With Traumatic Brain Injury Based on Machine Learning Algorithms: User-Centered Design Case Study.

Currently, the treatment and care of patients with traumatic brain injury (TBI) are intractable health problems worldwide and greatly increase the medical burden in society. However, machine learning-based algorithms and the use of a large amount of data accumulated in the clinic in the past can predict the hospitalization time of patients with brain injury in advance, so as to design a reasonable arrangement of resources and effectively reduce the medical burden of society. Especially in China, where medical resources are so tight, this method has important application value. We aimed to develop a system based on a machine learning model for predicting the length of hospitalization of patients with TBI, which is available to patients, nurses, and physicians. We collected information on 1128 patients who received treatment at the Neurosurgery Center of the Second Affiliated Hospital of Anhui Medical University from May 2017 to May 2022, and we trained and tested the machine learning model using 5 cross-validations to avoid overfitting; 28 types of independent variables were used as input variables in the machine learning model, and the length of hospitalization was used as the output variables. Once the models were trained, we obtained the error and goodness of fit (R2) of each machine learning model from the 5 rounds of cross-validation and compared them to select the best predictive model to be encapsulated in the developed system. In addition, we externally tested the models using clinical data related to patients treated at the First Affiliated Hospital of Anhui Medical University from June 2021 to February 2022. Six machine learning models were built, including support vector regression machine, convolutional neural network, back propagation neural network, random forest, logistic regression, and multilayer perceptron. Among them, the support vector regression has the smallest error of 10.22% on the test set, the highest goodness of fit of 90.4%, and all performances are the best among the 6 models. In addition, we used external datasets to verify the experimental results of these 6 models in order to avoid experimental chance, and the support vector regression machine eventually performed the best in the external datasets. Therefore, we chose to encapsulate the support vector regression machine into our system for predicting the length of stay of patients with traumatic brain trauma. Finally, we made the developed system available to patients, nurses, and physicians, and the satisfaction questionnaire showed that patients, nurses, and physicians agreed that the system was effective in providing clinical decisions to help patients, nurses, and physicians. This study shows that the support vector regression machine model developed using machine learning methods can accurately predict the length of hospitalization of patients with TBI, and the developed prediction system has strong clinical use.

Cosmetic medical tourists’ use of online and offline experiential and procedural information resources in decision-making: Implications for digital health literacy and neoliberalism

Background: When deciding to undergo aesthetic health procedures overseas, cosmetic medical tourists access various information resources to make informed decisions about locations, facilities, health providers and procedure(s). Aim: Existing research has investigated the different resources cosmetic tourists access in their decision-making process, however, there has yet to be an in-depth analysis of the significance of each information resource in this process. Methods: Interviews with Australian cosmetic tourists regarding how and why they decided to use specific information resources. Results: We found that cosmetic medical tourists simultaneously and repeatedly used four main information resources in their decision making – websites, existing social networks, online support communities and surgeon consultations. Discussion: We characterise these resources as offering both experiential and procedural information, both generalised (non-specific and available to everyone) and personalised (originating in individual experience or tailored to the individual) information and being located both online (internet-based) and offline (in-person). Successful accomplishment of the cosmetic medical tourist journey relies on engagement with most of these resources, highlighting the role of digital health literacy and the complexity of this decision-making process. Conclusions: This process has implications for understanding the practice of digital health literacy and identifiably positions cosmetic medical tourists as neoliberal individuals.

Health economic evaluation of an artificial intelligence (AI)-based rapid nutritional diagnostic system for hospitalised patients: A multicentre, randomised controlled trial

Background & aimsMalnutrition is prevalent among hospitalised patients, and increases the morbidity, mortality, and medical costs; yet nutritional assessments on admission are not routine. This study assessed the clinical and economic benefits of using an artificial intelligence (AI)-based rapid nutritional diagnostic system for routine nutritional screening of hospitalised patients. MethodsA nationwide multicentre randomised controlled trial was conducted at 11 centres in 10 provinces. Hospitalised patients were randomised to either receive an assessment using an AI-based rapid nutritional diagnostic system as part of routine care (experimental group), or not (control group). The overall medical resource costs were calculated for each participant and a decision-tree was generated based on an intention-to-treat analysis to analyse the cost-effectiveness of various treatment modalities. Subgroup analyses were performed according to clinical characteristics and a probabilistic sensitivity analysis was performed to evaluate the influence of parameter variations on the incremental cost-effectiveness ratio (ICER). ResultsIn total, 5763 patients participated in the study, 2830 in the experimental arm and 2933 in the control arm. The experimental arm had a significantly higher cure rate than the control arm (23.24% versus 20.18%; p = 0.005). The experimental arm incurred an incremental cost of 276.52 CNY, leading to an additional 3.06 cures, yielding an ICER of 90.37 CNY. Sensitivity analysis revealed that the decision-tree model was relatively stable. ConclusionThe integration of the AI-based rapid nutritional diagnostic system into routine inpatient care substantially enhanced the cure rate among hospitalised patients and was cost-effective. RegistrationNCT04776070 (https://clinicaltrials.gov/study/NCT04776070)

Investigation and Analysis of the Current Status of Health-Related Quality of Life in Adolescents with Hemophilia in Hubei Province.

Aims/Background Reliable health-related quality of life data are critical in developing countries, in order to advocate for government agencies to develop national hemophilia care programmes. This study aims to explore the current status and influencing factors of health-related quality of life among adolescents with hemophilia in Hubei Province, so as to provide empirical data for professionals. Methods A total of 84 children with hemophilia aged 8 to 18, who were registered in Tongji Hemophilia Treatment Center and Hubei Hemophilia Home, were selected using a cluster sampling method. The "General Situation Questionnaire of Hemophiliac Adolescents", designed by Tongji Hemophilia Treatment Center, and "the Chinese version of Canadian hemophilia outcomes-kid's life assessment tool (CHO-KLAT)", were used for this study conducted from June 1, 2022 to December 30, 2022. Results 82 completed questionnaires were included. The average age of the 82 adolescents was 13.04 ± 3.29 years and all were males. Among them, 67 were hemophilia A and 15 were hemophilia B. 61 cases were severe type, 19 were moderate type and 2 cases were mild type. The average total score of the CHO-KLAT for adolescents with hemophilia in Hubei Province was 49.49, which was lower than their counterparts in developed countries. The statistically significant influencing factors included residence, annual family income, and disease type. Conclusion This study provides empirical data support for the health management of adolescents with hemophilia, highlighting the importance of improving medical resource access, transfusion convenience, and psychological support in enhancing the quality of life for this group. The results emphasize the need for healthcare systems and policymakers to take specific measures to address these factors to improve the treatment and care conditions for adolescents with hemophilia.

Cross-provincial inpatient mobility patterns and their determinants in China

BackgroundThe incongruity between the regional supply and demand of healthcare services is a persistent challenge both globally and in China. Patient mobility plays a pivotal role in addressing this issue. This study aims to delineate the cross-provincial inpatient mobility network (CIMN) in China and identify the underlying factors influencing this CIMN.MethodsWe established China’s CIMN by applying a spatial transfer matrix, utilizing the flow information from 5,994,624 cross-provincial inpatients in 2019, and identified the primary demand and supply provinces for healthcare services. Subsequently, we employed GeoDetector to analyze the impact of 10 influencing factors—including medical resources, medical quality, and medical expenses—on the spatial patterns of CIMN.FindingsBeijing, Shanghai, Zhejiang, and Jiangsu provinces are the preferred medical destinations for cross-provincial inpatients, while Anhui, Henan, Hebei, and Jiangsu provinces are the main sources for cross-provincial inpatients. Patient flow between provinces decreases with distance. The spatial distribution of medical resources, medical quality, and medical expenses account for 87%, 73%, and 56% of the formation of CIMN, respectively. Additionally, interactions between these factors enhance explanatory power, suggesting that considering their interactions can more effectively optimize medical resources and services.ConclusionsThe analysis of CIMN reveals the supply and demand patterns of healthcare services, providing insights into the inequality characteristics of healthcare access. Furthermore, understanding the driving factors and their interactions offers essential evidence for optimizing healthcare services.

Review of Influencing Factors of Patients' Medical Choice Behavior in Online Health Community

The development of information technology has made online medical communities a new avenue for addressing medical resource shortages. However, the complexity of information and the asymmetry between physicians and patients makes patients confused when they consult in online health community (OHC). This study systematically analyzed and summarized relevant theories and factors influencing patients' medical choice behavior through literature review. The objective is to offer guidance for patients' decisions in selecting physicians and to support the sustainable development of online medical community platforms, as well as to provide practical insights for further exploration in this field. Objective: This review examines recent theories and factors influencing patients' medical choice behavior in online health community (OHC), aiming to offer insights for patient choice regarding physician selection and the sustainable development of online medical platforms. Methods: A literature analysis was conducted to summarize studies on patients' medical choice behavior in OHC, identifying relevant theories and influencing factors. Results: The analysis identified seven key theories in the study of patients' medical choice behavior: signal theory, trust theory, social capital theory, social exchange theory, the stimulus-organism-response (SOR) model, the elaboration likelihood model (ELM), and the opportunity-motivation-ability (OMA) framework. Factors such as physicians' professional capital, online effort, service quality, online reputation, patient preferences and disease heterogeneity significantly influence patients' medical choice behavior. Conclusion: There is a trend toward integrating multiple theories in understanding patients' medical choice behavior in OHC; however, interdisciplinary research remains limited. Most studies focus on patients’ medical choice behavior from the physicians' perspective, while research from the patients' viewpoint is lacking. This study suggests two future research directions: enhancing the integration of multidisciplinary theories and expanding the scope of research subjects.

Predicting hospitalization costs for pulmonary tuberculosis patients based on machine learning

BackgroundPulmonary tuberculosis (PTB) is a prevalent chronic disease associated with a significant economic burden on patients. Using machine learning to predict hospitalization costs can allocate medical resources effectively and optimize the cost structure rationally, so as to control the hospitalization costs of patients better.MethodsThis research analyzed data (2020–2022) from a Kashgar pulmonary hospital’s information system, involving 9570 eligible PTB patients. SPSS 26.0 was used for multiple regression analysis, while Python 3.7 was used for random forest regression (RFR) and MLP. The training set included data from 2020 and 2021, while the test set included data from 2022. The models predicted seven various costs related to PTB patients, including diagnostic cost, medical service cost, material cost, treatment cost, drug cost, other cost, and total hospitalization cost. The model’s predictive performance was evaluated using R-square (R2), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE) metrics.ResultsAmong the 9570 PTB patients included in the study, the median and quartile of total hospitalization cost were 13,150.45 (9891.34, 19,648.48) yuan. Nine factors, including age, marital status, admission condition, length of hospital stay, initial treatment, presence of other diseases, transfer, drug resistance, and admission department, significantly influenced hospitalization costs for PTB patients. Overall, MLP demonstrated superior performance in most cost predictions, outperforming RFR and multiple regression; The performance of RFR is between MLP and multiple regression; The predictive performance of multiple regression is the lowest, but it shows the best results for Other costs.ConclusionThe MLP can effectively leverage patient information and accurately predict various hospitalization costs, achieving a rationalized structure of hospitalization costs by adjusting higher-cost inpatient items and balancing different cost categories. The insights of this predictive model also hold relevance for research in other medical conditions.