To quantify the relative contributions of internal and external psychological variables to occupational burnout among healthcare workers, providing a quantitative basis for formulating precise organizational intervention strategies. A cross-sectional survey was conducted among 417 healthcare workers from 3 hospitals. Dominance analysis was employed to calculate the relative importance of perceived stress, work-family conflict, resilience, psychological distress, and social support in predicting occupational burnout. Dominance analysis showed that, among psychological demands, perceived stress (38.12

Background: Diagnosis-related groups (DRGs) payment reform has been widely implemented in China to improve healthcare efficiency and control rising medical costs. Hypertensive disorders of pregnancy (HDP) impose a substantial clinical and economic burden. Objective: To evaluate the impact of DRG reform on hospitalization costs, cost structure, and average length of stay (ALOS) among patients with HDP. Methods: Using data from the Shanghai Hospital Development Center covering all tertiary hospitals, we conducted an interrupted time series analysis of HDP hospitalizations from January 2015 to December 2024. Models incorporated seasonal adjustment and corrections for autocorrelation and heteroskedasticity to assess changes in ALOS, hospitalization costs, and out-of-pocket (OOP) payments following the implementation of DRGs in April 2022. Results: From 2015 to 2024, the distribution of HDP subtypes remained relatively stable, with a slight increase in chronic hypertension with superimposed pre-eclampsia. Following the DRG reform, ALOS showed a decreasing trend (−0.001 per month). Concurrently, the overall hospitalization cost trend changed from a pre-reform increase to a post-reform decline, with average costs decreasing by 68.85 CNY per month. The reduction in pharmaceutical expenses accelerated from 3.70 CNY to 15.40 per month (P = 0.019), while other expenses reversed from a monthly increase of 17.42 to a decrease of 54.65 CNY (all P < 0.05). However, severe pre-eclampsia/eclampsia-related costs remained the highest without a significant improvement after the reform. Conclusion: DRG reform was associated with improved efficiency and a reversal in cost growth among patients with HDP. However, its effectiveness was limited in severe cases.

BACKGROUND:There is a lack of studies exploring the performance of Transformers-based language models in common risks assessment among psychiatric inpatients. We aim to develop a scalable risk assessment model using multidimensional textualized data and test the stability, robustness, and benefit of this approach. METHODS:In this real-world cohort study, a deep learning language model was developed and validated using first hospitalized cases diagnosed with schizophrenia, bipolar disorder, and depressive disorder between January 2016 and March 2023 in three hospitals. The algorithm was externally validated on an independent testing cohort comprising 1180 patients. A total of 140 features, including first medical records (FMR), laboratory examinations, medical orders, and psychological scales, were assessed for analysis. The outcomes were short- and long-term impulsivity (STI and LTI), risk of suicide (STSS and LTSS), and need of physical restraint (STPR and LTPR) assessed by qualified nurses or clinicians. Analysis was carried out between August 2024 and June 2024. Models with different architectures and input settings were compared with each other. The area under the receiver operating characteristic curve (AUROC) was used to assess the primary performance of models. The clinical utility was determined by the net benefit under Youden's threshold. RESULTS:Of 7451 patients included in this study, 2982 (47.6%) were male, and the median (interquartile range) age was 42 (28-57) years. The overall incidence of outcomes was 635 (8.5%), 728 (10.5%), 659 (8.8%), 803 (10.8%), 588 (7.9%), and 728 (9.8%) for STPR, LTPR, STSS, LTSS, STI, and LTI, respectively. The multitask semi-structured Transformers-based language (SSTL) model showed more promising AUROCs (STPR: 0.915; LTPR: 0.844; STSS: 0.867; LTSS: 0.879; STI: 0.899; LTI: 0.894) in the prediction of these outcomes than single-tasked or multimodal language models and traditional structured data models. Combining FMR with other data from electronic health records led to significant improvements in the performance and clinical utility of SSTL models based on demographic, diagnosis, laboratory tests, treatment, and psychological scales. CONCLUSIONS:The SSTL model shows potential advantages in prognostic evaluation. FMR is a strong predictor for common risks prediction and may benefit other tasks in psychiatry with minimum requirements for data and data processing.

Wastewater treatment plants (WWTPs) play an essential role in urban water system, assisting in realizing urbanization and sustainable development. They consume large amounts of energy and chemicals to remove the wastewater pollutants each year around the world, highlighting an urgent need to explore and discover the energy and chemical saving potential of WWTPs. Recently, deep learning model has attracted increasing attention in various research fields. This study evaluated an Attention optimized bidirectional Gated recurrent unit Long short-term memory (ABGL) model against several benchmark deep learning models. Comparative analysis revealed that while ABGL demonstrates superior performance, the optimal model selection should be carefully evaluated based on data accuracy and computational complexity. Among these models, ABGL showed best accuracy and feasibility for the ability of predicting energy and chemical consumption. The results of the model predictions showed that energy saving and chemical saving of studied WWTP could be as high as 9.21 % and 18.78 %, respectively. Accordingly, the energy intensity of the WWTP should be controlled below 0.28 kWh/ m3 and the chemical intensity be controlled below 0.09 kg/m3. Implementation of the deep learning model such as ABGL will assist the decision-makers of WWTPs in optimizing the input efficiency, setting a novel paradigm that guides the smart operations of the whole sector by the state-of-the-art DNN model.

ABSTRACT Background and Aims To investigate the status of self‐management of health behaviors in children with Type 1 diabetes mellitus and to analyze their influencing factors. Self‐management skills are essential for disease management in children with Type 1 diabetes. Methods This cross‐sectional study was conducted on 132 children with Type 1 diabetes mellitus hospitalized in the Department of Endocrinology and Genetic Metabolism of a tertiary children's hospital. Children were selected from September 2023 to March 2024 by convenience sampling method. A general information questionnaire and the Type 1 Diabetes Behavioral Rating Scale were used to conduct the questionnaire survey. Results The mean of health behavior self‐management score was (0.60 ± 0.15), and the mean scores of the four dimensions were: daily care behaviors (0.74 ± 0.16), adjustment of diabetes care behaviors (0.29 ± 0.24), diabetes care behavior intervention (0.52 ± 0.25), and other diabetes care behaviors (0.61 ± 0.27) points; one‐way analysis of variance showed that the differences in self‐management scores of health behaviors of children with Type 1 diabetes mellitus were statistically significant when comparing children with different ages, years since diagnosis, whether they were only children, family structure, whether there was a family member with a diagnosis of diabetes mellitus, literacy level of the parents, and average monthly family income (p < 0.05); the differences between age, whether they were only children, family structure, whether there was a family member with a diagnosed with diabetes mellitus, and average monthly family income were influential factors in the self‐management of health behaviors of children with Type 1 diabetes mellitus (p < 0.05). Conclusion The level of health behavior self‐management of children with Type 1 diabetes mellitus is in the middle‐low level, and individualized interventions can be carried out for children with different characteristics to promote the improvement of children's ability to manage their disease and improve their quality of life.

AimWe aimed to develop and internally validate a machine learning (ML)-based model for the prediction of the risk of type 2 diabetes mellitus (T2DM) in children with obesity.MethodsIn total, 292 children with obesity and T2DM were enrolled between July 2023 and February 2024 and followed for at least 1 year. Eight ML algorithms (Decision Tree, Logistic Regression, Support Vector Machine (SVM), Multilayer Perceptron, Adaptive Boosting, Random Forest, Gradient Boosting Decision Tree, and Extreme Gradient Boosting) were compared for their capacity to identify key clinical and laboratory characteristics of T2DM in children and to create a risk prediction model.ResultsForty-nine children were diagnosed with T2DM during the follow-up period. The SVM algorithm was the best predictor of T2DM, with the largest area under the receiver operating characteristic curve (0.98) and accuracy (93.2%). The SVM algorithm identified eight predictors: BMI, creatinine, prealbumin, glucose (180 min), glycosylated hemoglobin A1c, thyrotropin, total thyroxine (T4), and free T4 concentrations. Thus, an ML-based prediction model accurately identifies children with obesity at high risk of T2DM. If externally validated, this tool could facilitate early, personalized interventions aimed at preventing T2DM.DiscussionThe rising prevalence of obesity in childhood is associated with an increase in the risk of early-onset T2DM. Therefore, the early identification of individuals at high risk is crucial to prevent the development of this disease. In a comparative analysis of the performance of multiple ML algorithms, we found that the SVM algorithm was the best predictor of the development of T2DM.

Objectives: This study aims to evaluate the association between antibiotic prophylaxis (particularly cephalosporins) and clinical outcomes in elderly hip fracture patients. Methods: We analyzed 4044 elderly hip fracture patients (2008–2022) from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database using inverse probability treatment weighting (IPTW). Cox proportional hazards models assessed mortality risk, while logistic regression evaluated infection and Intensive Care Unit (ICU) admission risks. Dose–response and subgroup analyses were performed for significant findings. Results: In total, 166 patients received no antibiotics, 2589 received Cephalosporin monotherapy, 403 received non-cephalosporin therapy, and 886 received Cephalosporin combination therapy. After IPTW adjustment, monotherapy showed significantly lower mortality risk versus combination therapy at all timepoints (hazard ratio (HR) for 28-day mortality: 0.46, 95% confidence interval (95% CI): 0.28–0.75; HR for 90-day mortality: 0.60, 95% CI: 0.44–0.82; HR for 180-day mortality: 0.67, 95% CI: 0.51–0.87; HR for 1-year mortality: 0.71, 95% CI: 0.57–0.89). The SII cut-off values were 1310.1 for 28-day mortality, 2077.5 for both 90-day and 180-day mortality, 1742.2 for 1-year mortality, 2199.7 for ICU admission, and 1930.7 for infection. Subgroup analyses showed that males and internal fixation patients derived more benefits after cephalosporin monotherapy treatment at all time nodes. Patients with multiple injuries had a lower risk of 28-day mortality, while high-comorbidity patients (CCI ≥ 5) and those with osteoporosis exhibited particular advantages with cephalosporin monotherapy. Conclusions: Cephalosporin monotherapy appears non-inferior to combination therapy for elderly hip fracture patients, potentially reducing long-term mortality risk, especially in males, internal fixation cases, and patients with CCI ≥ 5 and osteoporosis.

Background The conventional treatment for locally advanced head and neck squamous cell carcinoma (LA-HNSCC) is surgery; however, the efficacy of definitive chemoradiotherapy (CRT) remains controversial.Objective This study aimed to evaluate the ability of deep learning (DL) models to identify patients with LA-HNSCC who can achieve organ preservation through definitive CRT and provide individualized adjuvant treatment recommendations for patients who are better suited for surgery.Methods Five models were developed for treatment recommendations. Their performance was assessed by comparing the difference in overall survival rates between patients whose actual treatments aligned with the model recommendations and those whose treatments did not. Inverse probability treatment weighting (IPTW) was employed to reduce bias. The effect of the characteristics on treatment plan selection was quantified through causal inference.Results A total of 7,376 patients with LA-HNSCC were enrolled. Balanced Individual Treatment Effect for Survival data (BITES) demonstrated superior performance in both the CRT recommendation (IPTW-adjusted hazard ratio (HR): 0.84, 95% confidence interval (CI), 0.72-0.98) and the adjuvant therapy recommendation (IPTW-adjusted HR: 0.77, 95% CI, 0.61-0.85), outperforming other models and the National Comprehensive Cancer Network guidelines (IPTW-adjusted HR: 0.87, 95% CI, 0.73-0.96).Conclusion BITES can identify the most suitable treatment option for an individual patient from the three most common treatment options. DL models facilitate the establishment of a valid and reliable treatment recommendation system supported by quantitative evidence.

PURPOSE:Tonsillectomy is one of the most common surgical procedures, with 289,000 ambulatory procedures performed annually in children <15 years of age, and pain is a major cause of post-tonsillectomy complications. We sought to evaluate the effect of parent participation in postoperative pain management programs on children's post-tonsillectomy pain score and other outcome measures. METHODS:Parent participation in postoperative pain management programs was based on the quality improvement model developed by the Evidence-Based Nursing Center of Fudan University and validated among child urological patients. This between-group experimental controlled study was conducted in the inpatient ENT ward of a tertiary children's hospital. The control group comprised 118 children randomly selected from April 1 to May 15, 2022, and the experimental group included 117 children randomly selected from June 1 to July 15, 2022. To evaluate the effectiveness of the model, the control group received routine postoperative pain management, and the intervention group received the program of parental involvement in postoperative pain management. Postoperative pain-related data were collected for the two groups of children. RESULTS:There was no significant difference in the demographic characteristics of the two groups of children (P > 0.05). The pain score of the children in the intervention group was significantly lower than that of the control group when returning to the ward on the day of surgery (Z = 3.185, P = 0.002), after 2 h (Z = 7.280, P<0.001), after 4 h (Z = 6.4000, P<0.001), after 24 h (Z = 2.698, P = 0.009), at discharge (Z = 3.397, P = 0.002), and at the postoperative hospital visit (Z = 3.349, P = 0.001). There were no significant differences in the pain score at 02:00 in the morning after the operation or effective sleep time after the operation between the two groups (P > 0.05). CONCLUSIONS:and Clinical Implications: Programs of parental participation in postoperative pain management applied to children undergoing tonsillectomy can improve the participation of parents in postoperative pain management of children, relieve postoperative pain in children undergoing tonsillectomy, and improve children's postoperative quality of life.

AIM:To construct an evidence ecosystem-based postoperative pain management programme for children with postoperative pain management. DESIGN:A mixed research design that combines qualitative and quantitative studies. METHODS:According to the literature search and analysis, the postoperative pain management programme for children was constructed from three aspects: assessment of pain intensity of children, management principles and management methods, and the preliminary draft of the programme was finally constructed to include three first-level entries and 11 second-level entries. In January-February 2023, the first draft of the postoperative pain management programme for children was developed based on a literature review using the ecosystem of evidence theory as the research framework; in March-April 2023, the postoperative pain management programme for children was revised and finalised through two rounds of Delphi expert consultation. RESULTS:In the second round of expert consultation, the return rate of valid questionnaires was 100%, the expert authority coefficient was 0.83, the importance scores and feasibility scores of each entry were > 3.5, the coefficients of variation were < 0.25, the Kendall's harmony coefficients of the importance scores of the entries were 0.650 (χ2 = 273.134, p < 0.001) and those of the feasibility scores were 0.649 (χ2 = 272.720, p < 0.001). The resulting postoperative pain management programme for the affected patients included three level 1, 11 level 2 and eight level 3 entries. PATIENT OR PUBLIC CONTRIBUTION:The postoperative pain management programme for children constructed based on the evidence ecosystem is practical and scientific, but its effectiveness in clinical practice needs to be further verified by a controlled study design. OBJECTIVES:Evidence ecosystem; paediatrics, surgery; pain; Delphi method.

Background:This study aimed to evaluate the impact of nipple-sparing mastectomy (NSM) and modified radical mastectomy (MRM) on individual survival outcomes and to assess the potential of neoadjuvant systemic therapy (NST) in reducing surgical intervention requirements. Methods:To develop treatment recommendations for breast cancer patients, five machine learning models were trained. To mitigate bias in treatment allocation, advanced statistical methods, including propensity score matching (PSM) and inverse probability treatment weighting (IPTW), were applied. Results:NSM demonstrated either superior or noninferior survival outcomes compared with MRM across all breast cancer stages, irrespective of adjustments for IPTW and PSM. Among all models and National Comprehensive Cancer Network guidelines, the Balanced Individual and Mixture Effect (BIME) for survival regression model proposed in this study showed the strongest protective effects in treatment recommendations, as evidenced by an IPTW hazard ratio of 0.39 (95% CI: 0.26-0.59), an IPTW risk difference of 19.66% (95% CI: 18.20-21.13), and an IPTW difference in restricted mean survival time of 17.77 months (95% CI: 16.37-19.21). NST independently reduced the probability of surgical intervention by 1.4% (95% CI: 0.9%-2.0%), with the greatest impact observed in patients with locally advanced breast cancer, in whom a 4.5% reduction (95% CI: 3.8%-5.2%) in surgical selection was noted. Conclusions:The BIME model provides superior accuracy in recommending surgical approaches for breast cancer patients, leading to improved survival outcomes. These findings underscore the potential of BIME to enhance clinical decision-making. However, further investigation incorporating comprehensive prognostic evaluation is needed to optimize the surgical selection process and refine its clinical utility.

Background:Biomarkers for predicting suicide risk in hospitalised patients with mental disorders have been understudied. Currently, suicide risk assessment tools based on objective indicators are limited in China. Aims:To examine the value of various biomarkers in suicide risk prediction and develop a risk assessment model with clinical utility using machine learning. Methods:This cohort study analysed patients with major depressive disorder (MDD) who were hospitalised for the first time between January 2016 and March 2023 from four specialised mental health institutions. A total of 139 features, including biomarker measurements, medical orders and psychological scales, were assessed for analysis. Their suicide risk was evaluated by qualified nurses using Nurse's Global Assessment of Suicide Risk within 1 week after admission. Five machine learning models were trained with 10-fold cross-validation across three hospitals and were externally validated in an independent cohort. The primary performance was assessed using the area under the receiver operating characteristic curve (AUROC). The model was interpreted using the SHapley Additive exPlanations (SHAP) analysis. Biomarker importance was evaluated by comparing model performance with and without these biomarkers. Results:Of 3143 patients with MDD included in this study, the incidence of high suicide risk within 1 week after first admission was 660 (21.0%). Among all models, the Extreme Gradient Boosting can more effectively predict future risks, with an AUROC higher than 0.8 (p<0.001). The SHAP values identified the 10 most important features, including five biomarkers. After clustering analysis, electroconvulsive therapy, physical restraint, β2-microglobulin and triiodothyronine were found to have heterogeneous effects on suicide risk. Combining biomarkers with other data from electronic health records significantly improved the performance and clinical utility of machine learning models based on demographics, diagnosis, laboratory tests, medical orders and psychological scales. Conclusions:This study demonstrates the potential for a biomarker-based suicide risk assessment for patients with MDD, emphasising the interaction between biomarkers and therapeutic interventions.

ObjectiveThis study aimed to systematically characterize the morphological patterns of proximal fibular fractures occurring concurrently with tibial plateau fractures.MethodsData were retrospectively collected from a Level-1 trauma center between January 2011 and January 2024 by querying hospital information and picture archiving and communication systems with keywords "tibial plateau fracture" and "fibular fracture" or "fibular head fracture." Radiographic morphology was evaluated using standard anteroposterior radiographs and three-dimensional computed tomography (3D-CT), categorizing proximal fibular fractures into 13 predefined morphological patterns. Descriptive data, including fracture location, number of fragments, and degree of displacement, were recorded and classified. The distribution patterns of proximal fibular fractures were further correlated with the tibial plateau fractures, categorized according to the CT-based three-column classification system.ResultsA total of 223 eligible patients (123 males) were included in the analysis. Group I, II, and III proximal fibular fractures were observed in 63 (28.3%), 121 (54.3%), and 39 (17.4%) patients, respectively. Within group II, subtype II3p was the predominant fracture pattern, occurring in 61 patients (50.4%). Group I fibular fractures did not occur in tibial plateau posterior column or combined lateral and posterior column fractures. Group II fibular fractures were absent in tibial plateau lateral column or combined medial and lateral column fractures. Group III fibular fractures exclusively presented with combined lateral and posterior column or three-column tibial plateau fractures. Logistic regression indicated that group I proximal fibular fractures were significantly more associated with isolated medial column tibial plateau fractures, whereas group II fibula fractures were significantly associated with lateral-posterior and medial-posterior column tibial plateau fractures.ConclusionsThe morphological diversity observed in proximal fibular fractures underscores the complexity and heterogeneity of concomitant tibial plateau fractures. Further clinical and biomechanical investigations are warranted to elucidate the pathomechanics underlying comminuted fibular fractures associated with tibial plateau injuries.

Introduction: The relationships between calcium, bone mineral density, and hip fracture have been studied for a long time, but there are still different opinions on the matter. The aim of this study was to decipher the relationship between these factors from National Health and Nutrition Examination Survey (NHANES) data. Methods: After we performed data cleaning for the obtained NHANES data, we used multiple imputation to obtain the complete data and conducted an analysis for different variables. First, by using multivariate linear regression models, we confirmed the association between calcium and bone mineral density, and then we confirmed the association between bone mineral density and hip fracture by using multivariate logistic regression models. A mediation analysis of these variables was performed. Results: The analysis in this study included data on 18,003 participants from the NHANES, and we were able to find a strong association between calcium and bone mineral density (p < 0.001). The association between bone mineral density and hip fracture was also significant (p < 0.001). One augmented gram of daily calcium intake was associated with a 0.04 unit increase in BMD level, and a one unit increase in BMD level could downgrade the occurrence of hip fracture for 5.4 times. The mediation analysis showed that the femur BMD level and total BMD level have a mediating relationship with hip fracture, and no clear relationship among calcium, BMD, and hip fracture could be established. Conclusions: Although it is difficult to draw strict conclusions from the mediation analysis in this study, we can observe a clear association between calcium and BMD as well as an association between BMD and hip fracture.

Background The role of surgery in metastatic breast cancer (MBC) is currently controversial. Several novel statistical and deep learning (DL) methods promise to infer the suitability of surgery at the individual level. Objective The objective of this study was to identify the most applicable DL model for determining patients with MBC who could benefit from surgery and the type of surgery required. Methods We introduced the deep survival regression with mixture effects (DSME), a semi‐parametric DL model integrating three causal inference methods. Six models were trained to make individualized treatment recommendations. Patients who received treatments in line with the DL models' recommendations were compared with those who underwent treatments divergent from the recommendations. Inverse probability weighting (IPW) was used to minimize bias. The effects of various features on surgery selection were visualized and quantified using multivariate linear regression and causal inference. Results In total, 5269 female patients with MBC were included. DSME was an independent protective factor, outperforming other models in recommending surgery (IPW‐adjusted hazard ratio [HR] = 0.39, 95% confidence interval [CI]: 0.19–0.78) and type of surgery (IPW‐adjusted HR = 0.66, 95% CI: 0.48–0.93). DSME was superior to other models and traditional guidelines, suggesting a higher proportion of patients benefiting from surgery, especially breast‐conserving surgery. The debiased effect of patient characteristics, including age, tumor size, metastatic sites, lymph node status, and breast cancer subtypes, on surgery decision was also quantified. Conclusions Our findings suggested that DSME could effectively identify patients with MBC likely to benefit from surgery and the specific type of surgery needed. This method can facilitate the development of efficient, reliable treatment recommendation systems and provide quantifiable evidence for decision‐making.

Gout commonly manifests as a painful, self-limiting inflammatory arthritis. Nevertheless, the understanding of the inflammatory and immune responses underlying gout flares and remission remains ambiguous. Here, based on single-cell RNA-Seq and an independent validation cohort, we identified the potential mechanism of gout flare, which likely involves the upregulation of HLA-DQA1+ nonclassical monocytes and is related to antigen processing and presentation. Furthermore, Tregs also play an essential role in the suppressive capacity during gout remission. Cell communication analysis suggested the existence of altered crosstalk between monocytes and other T cell types, such as Tregs. Moreover, we observed the systemic upregulation of inflammatory and cytokine genes, primarily in classical monocytes, during gout flares. All monocyte subtypes showed increased arachidonic acid metabolic activity along with upregulation of prostaglandin-endoperoxide synthase 2 (PTGS2). We also detected a decrease in blood arachidonic acid and an increase in leukotriene B4 levels during gout flares. In summary, our study illustrates the distinctive immune cell responses and systemic inflammation patterns that characterize the transition from gout flares to remission, and it suggests that blood monocyte subtypes and Tregs are potential intervention targets for preventing recurrent gout attacks and progression.

Background Although favorable outcomes have been reported with radiofrequency ablation (RFA) for secondary hyperparathyroidism (SHPT), the long-term efficacy remains insufficiently investigated. Purpose To evaluate the long-term efficacy and safety of US-guided percutaneous RFA in patients with SHPT undergoing dialysis and to identify possible predictors associated with treatment failure. Materials and Methods This retrospective study included consecutive patients with SHPT with at least one enlarged parathyroid gland accessible for RFA who were undergoing dialysis at seven tertiary centers from May 2013 to July 2022. The primary end point was the proportion of patients with parathyroid hormone (PTH) levels less than or equal to 585 pg/mL at the end of follow-up. Secondary end points were the proportion of patients with normal calcium and phosphorus levels, the technical success rate, procedure-related complications, and improvement in self-rated hyperparathyroidism-related symptoms (0-3 ranking scale). The Wilcoxon signed rank test and generalized estimating equation model were used to evaluate treatment outcomes. Univariable and multivariable regression analyses identified variables associated with treatment failure (recurrent or persistent hyperparathyroidism). Results This study included 165 patients (median age, 51 years [IQR, 44-60 years]; 92 female) and 582 glands. RFA effectively reduced PTH, calcium, and phosphorus levels, with targeted ranges achieved in 78.2% (129 of 165), 72.7% (120 of 165), and 60.0% (99 of 165) of patients, respectively, at the end of follow-up (mean, 51 months). For the RFA sessions, the technical success rate was 100% (214 of 214). Median symptom scores (ostealgia, arthralgia, pruritus) decreased (all P < .001). Regarding complications, only hypocalcemia (45.8%, 98 of 214) was common. Treatment failure occurred in 36 patients (recurrent [n = 5] or persistent [n = 31] hyperparathyroidism). The only potential independent predictor of treatment failure was having less than four treated glands (odds ratio, 17.18; 95% CI: 4.34, 67.95; P < .001). Conclusion US-guided percutaneous RFA was effective and safe in the long term as a nonsurgical alternative for patients with SHPT undergoing dialysis; the only potential independent predictor of treatment failure was a lower number (<4) of treated glands. © RSNA, 2024 Supplemental material is available for this article.

BackgroundThe significant impact of digital health emerged prominently during the COVID-19 pandemic. Despite this, there is a paucity of bibliometric analyses focusing on technologies within the field of digital health patents. Patents offer a wealth of insights into technologies, commercial prospects, and competitive landscapes, often undisclosed in other publications. Given the rapid evolution of the digital health industry, safeguarding algorithms, software, and advanced surgical devices through patent systems is imperative. The patent system simultaneously acts as a valuable repository of technological knowledge, accessible to researchers. This accessibility facilitates the enhancement of existing technologies and the advancement of medical equipment, ultimately contributing to public health improvement and meeting public demands. ObjectiveThe primary objective of this study is to gain a more profound understanding of technology hotspots and development trends within the field of digital health. MethodsUsing a bibliometric analysis methodology, we assessed the global technological output reflected in patents on digital health published between 2017 and 2021. Using Citespace5.1R8 and Excel 2016, we conducted bibliometric visualization and comparative analyses of key metrics, including national contributions, institutional affiliations, inventor profiles, and technology topics. ResultsA total of 15,763 digital health patents were identified as published between 2017 and 2021. The China National Intellectual Property Administration secured the top position with 7253 published patents, whereas Koninklijke Philips emerged as the leading institution with 329 patents. Notably, Assaf Govari emerged as the most prolific inventor. Technology hot spots encompassed categories such as “Medical Equipment and Information Systems,” “Image Analysis,” and “Electrical Diagnosis,” classified by Derwent Manual Code. A patent related to the technique of receiving and transmitting data through microchips garnered the highest citation, attributed to the patentee Covidien LP. ConclusionsThe trajectory of digital health patents has been growing since 2017, primarily propelled by China, the United States, and Japan. Applications in health interventions and enhancements in surgical devices represent the predominant scenarios for digital health technology. Algorithms emerged as the pivotal technologies protected by patents, whereas techniques related to data transfer, storage, and exchange in the digital health domain are anticipated to be focal points in forthcoming basic research.

PURPOSE:The use of postoperative radiotherapy (PORT) in patients with oral squamous cell carcinoma (OCSCC) lacks clear boundaries due to the non-negligible toxicity accompanying its remarkable cancer-killing effect. This study aims at validating the ability of deep learning models to develop individualized PORT recommendations for patients with OCSCC and quantifying the impact of patient characteristics on treatment selection. METHODS:Participants were categorized into two groups based on alignment between model-recommended and actual treatment regimens, with their overall survival compared. Inverse probability treatment weighting was used to reduce bias, and a mixed-effects multivariate linear regression illustrated how baseline characteristics influenced PORT selection. RESULTS:4990 patients with OCSCC met the inclusion criteria. Deep Survival regression with Mixture Effects (DSME) demonstrated the best performance among all the models and National Comprehensive Cancer Network guidelines. The efficacy of PORT is enhanced as the lymph node ratio (LNR) increases. Similar enhancements in efficacy are observed in patients with advanced age, large tumors, multiple positive lymph nodes, tongue involvement, and stage IVA. Early-stage (stage 0-II) OCSCC may safely omit PORT. CONCLUSIONS:This is the first study to incorporate LNR as a tumor character to make personalized recommendations for patients. DSME can effectively identify potential beneficiaries of PORT and provide quantifiable survival benefits.

BACKGROUND:The survival advantage of neoadjuvant systemic therapy (NST) for breast cancer patients remains controversial, especially when considering the heterogeneous characteristics of individual patients. OBJECTIVE:To discern the variability in responses to breast cancer treatment at the individual level and propose personalized treatment recommendations utilizing deep learning (DL). METHODS:Six models were developed to offer individualized treatment suggestions. Outcomes for patients whose actual treatments aligned with model recommendations were compared to those whose did not. The influence of certain baseline features of patients on NST selection was visualized and quantified by multivariate logistic regression and Poisson regression analyses. RESULTS:Our study included 94,487 female breast cancer patients. The Balanced Individual Treatment Effect for Survival data (BITES) model outperformed other models in performance, showing a statistically significant protective effect with inverse probability treatment weighting (IPTW)-adjusted baseline features [IPTW-adjusted hazard ratio: 0.51, 95% confidence interval (CI), 0.41-0.64; IPTW-adjusted risk difference: 21.46, 95% CI 18.90-24.01; IPTW-adjusted difference in restricted mean survival time: 21.51, 95% CI 19.37-23.80]. Adherence to BITES recommendations is associated with reduced breast cancer mortality and fewer adverse effects. BITES suggests that patients with TNM stage IIB, IIIB, triple-negative subtype, a higher number of positive axillary lymph nodes, and larger tumors are most likely to benefit from NST. CONCLUSIONS:Our results demonstrated the potential of BITES to aid in clinical treatment decisions and offer quantitative treatment insights. In our further research, these models should be validated in clinical settings and additional patient features as well as outcome measures should be studied in depth.