Integrating lymph node ratio into personalized radiotherapy for oral cavity squamous cell carcinoma.

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.

Personalized surgical recommendations and quantitative therapeutic insights for patients with metastatic breast cancer: Insights from deep learning.

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.

Evolution of Digital Health and Exploration of Patented Technologies (2017-2021): Bibliometric Analysis.

BACKGROUND: The 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. OBJECTIVE: The primary objective of this study is to gain a more profound understanding of technology hotspots and development trends within the field of digital health. METHODS: Using 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. RESULTS: A 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. CONCLUSIONS: The 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.

Individualized survival prediction and surgery recommendation for patients with glioblastoma.

Background: There is a lack of individualized evidence on surgical choices for glioblastoma (GBM) patients. Aim: This study aimed to make individualized treatment recommendations for patients with GBM and to determine the importance of demographic and tumor characteristic variables in the selection of extent of resection. Methods: We proposed Balanced Decision Ensembles (BDE) to make survival predictions and individualized treatment recommendations. We developed several DL models to counterfactually predict the individual treatment effect (ITE) of patients with GBM. We divided the patients into the recommended (Rec.) and anti-recommended groups based on whether their actual treatment was consistent with the model recommendation. Results: The BDE achieved the best recommendation effects (difference in restricted mean survival time (dRMST): 5.90; 95% confidence interval (CI), 4.40-7.39; hazard ratio (HR): 0.71; 95% CI, 0.65-0.77), followed by BITES and DeepSurv. Inverse probability treatment weighting (IPTW)-adjusted HR, IPTW-adjusted OR, natural direct effect, and control direct effect demonstrated better survival outcomes of the Rec. group. Conclusion: The ITE calculation method is crucial, as it may result in better or worse recommendations. Furthermore, the significant protective effects of machine recommendations on survival time and mortality indicate the superiority of the model for application in patients with GBM. Overall, the model identifies patients with tumors located in the right and left frontal and middle temporal lobes, as well as those with larger tumor sizes, as optimal candidates for SpTR.

Determining individual suitability for neoadjuvant systemic therapy in breast cancer patients through deep learning.

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.

US-guided Percutaneous Radiofrequency Ablation for Secondary Hyperparathyroidism: Long-term Outcomes and Prognostic Factors.

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.

Optimizing adjuvant treatment options for patients with glioblastoma.

Background: This study focused on minimizing the costs and toxic effects associated with unnecessary chemotherapy. We sought to optimize the adjuvant therapy strategy, choosing between radiotherapy (RT) and chemoradiotherapy (CRT), for patients based on their specific characteristics. This selection process utilized an innovative deep learning method. Methods: We trained six machine learning (ML) models to advise on the most suitable treatment for glioblastoma (GBM) patients. To assess the protective efficacy of these ML models, we employed various metrics: hazards ratio (HR), inverse probability treatment weighting (IPTW)-adjusted HR (HRa), the difference in restricted mean survival time (dRMST), and the number needed to treat (NNT). Results: The Balanced Individual Treatment Effect for Survival data (BITES) model emerged as the most effective, demonstrating significant protective benefits (HR: 0.53, 95% CI, 0.48-0.60; IPTW-adjusted HR: 0.65, 95% CI, 0.55-0.78; dRMST: 7.92, 95% CI, 7.81-8.15; NNT: 1.67, 95% CI, 1.24-2.41). Patients whose treatment aligned with BITES recommendations exhibited notably better survival rates compared to those who received different treatments, both before and after IPTW adjustment. In the CRT-recommended group, a significant survival advantage was observed when choosing CRT over RT (p < 0.001). However, this was not the case in the RT-recommended group (p = 0.06). Males, older patients, and those whose tumor invasion is confined to the ventricular system were more frequently advised to undergo RT. Conclusion: Our study suggests that BITES can effectively identify GBM patients likely to benefit from CRT. These ML models show promise in transforming the complex heterogeneity of real-world clinical practice into precise, personalized treatment recommendations.

Deep learning-guided adjuvant chemotherapy selection for elderly patients with breast cancer.

PURPOSE: The efficacy of adjuvant chemotherapy in elderly breast cancer patients is currently controversial. This study aims to provide personalized adjuvant chemotherapy recommendations using deep learning (DL). METHODS: Six models with various causal inference approaches were trained to make individualized chemotherapy recommendations. Patients who received actual treatment recommended by DL models were compared with those who did not. Inverse probability treatment weighting (IPTW) was used to reduce bias. Linear regression, IPTW-adjusted risk difference (RD), and SurvSHAP(t) were used to interpret the best model. RESULTS: A total of 5352 elderly breast cancer patients were included. The median (interquartile range) follow-up time was 52 (30-80) months. Among all models, the balanced individual treatment effect for survival data (BITES) performed best. Treatment according to following BITES recommendations was associated with survival benefit, with a multivariate hazard ratio (HR) of 0.78 (95% confidence interval (CI): 0.64-0.94), IPTW-adjusted HR of 0.74 (95% CI: 0.59-0.93), RD of 12.40% (95% CI: 8.01-16.90%), IPTW-adjusted RD of 11.50% (95% CI: 7.16-15.80%), difference in restricted mean survival time (dRMST) of 12.44 (95% CI: 8.28-16.60) months, IPTW-adjusted dRMST of 7.81 (95% CI: 2.93-11.93) months, and p value of the IPTW-adjusted Log-rank test of 0.033. By interpreting BITES, the debiased impact of patient characteristics on adjuvant chemotherapy was quantified, which mainly included breast cancer subtype, tumor size, number of positive lymph nodes, TNM stages, histological grades, and surgical type. CONCLUSION: Our results emphasize the potential of DL models in guiding adjuvant chemotherapy decisions for elderly breast cancer patients.

Single-cell transcriptomics reveals variations in monocytes and Tregs between gout flare and remission.

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.

Effective early strategy to prevent olfactory and gustatory dysfunction in COVID-19: A randomized controlled trial.

BACKGROUND: Olfactory and gustatory dysfunctions (OGDs) are key symptoms of COVID-19, which may lead to neurological complications, and lack of effective treatment. This may be because post-disease treatments may be too late to protect the olfactory and gustatory functions. AIM: To evaluate the effectiveness of early use of saline nasal irrigation (SNI), corticosteroid nasal spray, and saline or chlorhexidine gluconate mouthwash for preventing OGDs in COVID-19. DESIGN: This study was a double-blind randomized controlled trial. METHODS: The study was conducted from May 5 to June 16, 2022. We recruited patients from three hospitals who were admitted with COVID-19 but without OGDs on the day of admission. Olfactory and gustatory functions were evaluated using the Taste and Smell Survey and the numerical visual analog scale. Participants were randomized to the saline, drug, or control groups. The control group received no intervention, saline group received SNI plus saline nasal spray and mouthwash, and the trial group received SNI plus budesonide nasal spray and chlorhexidine gluconate mouthwash. Participants were assessed again on the day of discharge. RESULTS: A total of 379 patients completed the trial. The prevalence of OGDs was significantly lower in the saline (11.8%, 95% CI, 6.6-19.0%; P < 0.001) and trial (8.3%, 95% CI, 4.1-14.8%; P < 0.001) groups than in the control group (40.0%, 95% CI, 31.8-48.6%). Additionally, both interventions reduced the severity of OGDs. CONCLUSIONS: We demonstrated effective strategies for preventing COVID-19-related OGDs, and the findings may guide early management of SARS-CoV-2 infection to reduce the incidence of COVID-19-related complications.

MSU crystal deposition contributes to inflammation and immune responses in gout remission.

As a prominent feature of gout, monosodium urate (MSU) crystal deposition induces gout flares, but its impact on immune inflammation in gout remission remains unclear. Using single-cell RNA sequencing (scRNA-seq), we characterize the transcription profiling of peripheral blood mononuclear cells (PBMCs) among intercritical remission gout, advanced remission gout, and normal controls. We find systemic inflammation in gout remission with MSU crystal deposition at the intercritical and advanced stages, evidenced by activated inflammatory pathways, strengthened inflammatory cell-cell interactions, and elevated arachidonic acid metabolic activity. We also find increased HLA-DQA1high classic monocytes and PTGS2high monocytes in advanced gout and overactivated CD8+ T cell subtypes in intercritical and advanced gout. Additionally, the osteoclast differentiation pathway is significantly enriched in monocytes, T cells, and B cells from advanced gout. Overall, we demonstrate systemic inflammation and distinctive immune responses in gout remission with MSU crystal deposition, allowing further exploration of the underlying mechanism and clinical significance in conversion from intercritical to advanced stage.

Evaluation of Chinese healthcare organizations' innovative performance in the digital health era.

Background: Healthcare workers' relationship with industry is not merely an agent mediating between consumer and vendor, but they are also inventors of the interventions they exist to deliver. Driven by the background of the digital health era, scientific research and technological (Sci-tech) innovation in the medical field are becoming more and more closely integrated. However, scholars shed little light on Sci-tech relevance to evaluate the innovation performance of healthcare organizations, a distinctive feature of healthcare organizations' innovation in the digital health era. Methods: Academic publications and patents are the manifestations of scientific research outputs and technological innovation outcomes, respectively. The study extracted data from publications and patents of 159 hospitals in China to evaluate their innovation performance. A total of 18 indicators were constructed, four of which were based on text similarity match and represented the Sci-tech relevance. We then applied factor analyses, analytical hierarchy process, and logistic regression to construct an evaluation model. We also examined the relationship between hospitals' innovation performance and their geographical locations. Finally, we implemented a mediation analysis to show the influence of digital health on hospital innovation performance. Results: A total of 16 indicators were involved, four of which represented the Sci-tech including the number of articles matched per patent (NAMP), the number of patents matched per article (NPMA), the proportion of highly matched patents (HMP), and the proportion of highly matched articles (HMA). Indicators of HMP (r = 0.52, P = 2.40 × 10-12), NAMP (r = 0.52, P = 2.54 × 10-12), and NPMA (r = 0.51, P = 5.53 × 10-12) showed a strong positive correlation with hospital innovation performance score. The evaluation model in this study was different from other Chinese existing hospital ranking systems. The regional innovation performance index (RIP) of healthcare organizations is highly correlated with per capita disposable income (r = 0.58) and regional GDP (r = 0.60). There was a positive correlation between digital health innovation performance scores and overall hospital innovation performance scores (r = 0.20). In addition, the hospitals' digital health innovation performance affected the hospital's overall innovation score with the mediation of Sci-tech relevance indicators (NPMA and HMA). The hospitals' digital health innovation performance score showed a significant correlation with the number of healthcare workers (r = 0.44). Conclusion: This study constructed an assessment model with four invented indicators focusing on Sci-tech relevance to provide a novel tool for researchers to evaluate the innovation performance of healthcare organizations in the digital health era. The regions with high RIP were concentrated on the eastern coastal areas with a higher level of economic development. Therefore, the promotion of scientific and technological innovation policies could be carried out in advance in areas with better economic development. The innovations in the digital health field by healthcare workers enhance the Sci-tech relevance in hospitals and boost their innovation performance. The development of digital health in hospitals depends on the input of medical personnel.

Analyzing and predicting the risk of death in stroke patients using machine learning.

Background: Stroke is an acute disorder and dysfunction of the focal neurological system that has long been recognized as one of the leading causes of death and severe disability in most regions globally. This study aimed to supplement and exploit multiple comorbidities, laboratory tests and demographic factors to more accurately predict death related to stroke, and furthermore, to make inferences about the heterogeneity of treatment in stroke patients to guide better treatment planning. Methods: We extracted data from the Medical Information Mart from the Intensive Care (MIMIC)-IV database. We compared the distribution of the demographic factors between the control and death groups. Subsequently, we also developed machine learning (ML) models to predict mortality among stroke patients. Furthermore, we used meta-learner to recognize the heterogeneity effects of warfarin and human albumin. We comprehensively evaluated and interpreted these models using Shapley Additive Explanation (SHAP) analysis. Results: We included 7,483 patients with MIMIC-IV in this study. Of these, 1,414 (18.9%) patients died during hospitalization or 30 days after discharge. We found that the distributions of age, marital status, insurance type, and BMI differed between the two groups. Our machine learning model achieved the highest level of accuracy to date in predicting mortality in stroke patients. We also observed that patients who were consistent with the model determination had significantly better survival outcomes than the inconsistent population and were better than the overall treatment group. Conclusion: We used several highly interpretive machine learning models to predict stroke prognosis with the highest accuracy to date and to identify heterogeneous treatment effects of warfarin and human albumin in stroke patients. Our interpretation of the model yielded a number of findings that are consistent with clinical knowledge and warrant further study and verification.

Alterations in smell or taste in individuals infected with SARS-CoV-2 during periods of Omicron variant dominance.

OBJECTIVES: To characterize the prevalence, severity, correlation with initial symptoms, and role of vaccination in patients with COVID-19 with smell or taste alterations (STAs). METHODS: We conducted an observational study of patients infected with SARS-CoV-2 Omicron admitted to three hospitals between May 17 and June 16, 2022. The olfactory and gustatory functions were evaluated using the taste and smell survey and the numerical visual analog scale at two time points. RESULTS: The T1 and T2 time point assessments were completed by 688 and 385 participants, respectively. The prevalence of STAs at two time points was 41.3% vs 42.6%. Furthermore, no difference existed in the severity distribution of taste and smell survey, smell, or taste visual analog scale scores between the groups. Patients with initial symptoms of headache (P = 0.03) and muscle pain (P = 0.04) were more likely to develop STAs, whereas higher education; three-dose vaccination; no symptoms yet; or initial symptoms of cough, throat discomfort, and fever demonstrated protective effects, and the results were statistically significant. CONCLUSION: The prevalence of STAs did not decrease significantly during the Omicron dominance, but the severity was reduced, and vaccination demonstrated a protective effect. In addition, the findings suggest that the presence of STAs is likely to be an important indicator of viral invasion of the nervous system.

The Influence of Childhood Trauma and Family Functioning on Internet Addiction in Adolescents: A Chain-Mediated Model Analysis.

OBJECTIVE: This study aimed to examine the prevalence of Internet addiction in adolescents, analyze the associations of childhood trauma, systematic family dynamics, and family functioning with Internet addiction, and investigate the mediating chain role of anxiety and depression in the relationship of childhood trauma and family functioning with adolescent Internet addiction. METHODS: This was a cross-sectional study in which general sociodemographic data were obtained from 3357 adolescents in grades 6-12 who were assessed using psychometric instruments such as the Childhood Trauma Questionnaire, Young Internet Addiction Test, Systematic Family Dynamics Self-Rating Scale (SSFD), Family Functioning Assessment (FAD), Self-Rating Depression Scale (SDS), and Self-Rating Anxiety Scale (SAS). RESULTS: (1) The prevalence of Internet addiction among adolescents was 26.09% (876/3357). The prevalence of childhood trauma was 54.96% (1845/3357), and the prevalence of Internet addiction was significantly different between adolescents who suffered childhood trauma and those who did not (χ2 = 96.801, ν = 1, p = 0.000). (2) Childhood trauma and various dimensions of systematic family dynamics had a significant negative and positive relationship with poor family functioning and anxiety or depression, respectively. (3) Childhood trauma was a positive predictor of Internet addiction through the chain-mediated effect of anxiety and depression, but there were no direct effects. Poor family functioning was a positive predictor of adolescent Internet addiction, and this positive prediction was augmented by the chain-mediated effect of anxiety and depression. CONCLUSIONS: Childhood trauma and poor family functioning or support predicted Internet addiction in adolescents, with anxiety and depression as mediators.

Prediction of acute kidney injury in patients with femoral neck fracture utilizing machine learning.

Background: Acute kidney injury (AKI) is a common complication associated with significant morbidity and mortality in high-energy trauma patients. Given the poor efficacy of interventions after AKI development, it is important to predict AKI before its diagnosis. Therefore, this study aimed to develop models using machine learning algorithms to predict the risk of AKI in patients with femoral neck fractures. Methods: We developed machine-learning models using the Medical Information Mart from Intensive Care (MIMIC)-IV database. AKI was predicted using 10 predictive models in three-time windows, 24, 48, and 72 h. Three optimal models were selected according to the accuracy and area under the receiver operating characteristic curve (AUROC), and the hyperparameters were adjusted using a random search algorithm. The Shapley additive explanation (SHAP) analysis was used to determine the impact and importance of each feature on the prediction. Compact models were developed using important features chosen based on their SHAP values and clinical availability. Finally, we evaluated the models using metrics such as accuracy, precision, AUROC, recall, F1 scores, and kappa values on the test set after hyperparameter tuning. Results: A total of 1,596 patients in MIMIC-IV were included in the final cohort, and 402 (25%) patients developed AKI after surgery. The light gradient boosting machine (LightGBM) model showed the best overall performance for predicting AKI before 24, 48, and 72 h. AUROCs were 0.929, 0.862, and 0.904. The SHAP value was used to interpret the prediction models. Renal function markers and perioperative blood transfusions are the most critical features for predicting AKI. In compact models, LightGBM still performs the best. AUROCs were 0.930, 0.859, and 0.901. Conclusions: In our analysis, we discovered that LightGBM had the best metrics among all algorithms used. Our study identified the LightGBM as a solid first-choice algorithm for early AKI prediction in patients after femoral neck fracture surgery.

The Beneficial Effects of Hydrogen-Rich Saline Irrigation on Chronic Rhinitis: A Randomized, Double-Blind Clinical Trial.

Purpose: Chronic rhinitis (CR) is a common chronic inflammation of the nasal mucosa. Nasal saline irrigation has been demonstrated to be an effective treatment for CR. In this study, we investigated the beneficial effects of hydrogen-rich saline irrigation as an anti-inflammatory irrigation therapy for CR and compared its effectiveness over saline irrigation. Hydrogen-rich saline (HRS) was investigated due to its antioxidant and anti-inflammatory properties. Methods: A total of 120 patients with CR were randomly divided into two groups, patients irrigated with HR (HRS group) and the control group irrigated with saline (NS group). A randomized, double-blind control study was performed. The main observation index in this study was the total score of nasal symptoms (TNSS). In addition, eosinophilic protein (ECP) of the nasal secretions, nasal nitric oxide (nNO) levels, and levels of regulatory T cells (Treg) and regulatory B cells (Breg) were also compared between the two groups. Furthermore, patients with allergic rhinitis (AR) and non-allergic rhinitis (NAR) were also evaluated based on serum-specific IgE positivity. Results: After treatment, TNSS and nasal ECP in the two groups decreased significantly (P<0.05), with patients in the HRS group showing significantly lower levels compared to the NS group (P<0.05). There were no significant differences in Treg and Breg levels between the two groups. Subgroup analysis showed that TNSS in the AR-HRS group showed a more significant reduction compared to the AR-NS group (P<0.05); however, there were no significant differences for the other inflammatory biomarkers (P>0.05). ECP levels were reduced significantly in the NAR subgroup compared to NS irrigation (P<0.05). There were no obvious adverse events observed in patients during the entire treatment period. Conclusion: Compared to saline irrigation, HRS nasal irrigation was found to improve CR clinical symptoms, especially in patients with AR. HRS could effectively be used for the clinical treatment of patients with CR.

A quantitative study of bone defects in displaced femoral neck fractures based on virtual reduction techniques.

BACKGROUND: Bone defects in femoral neck fractures are strongly associated with the prognosis after internal fixation. However, qualitative analysis of bone defects in femoral neck fractures has already been performed, quantitative studies have not been reported. In this study, we aimed to systematically analyse the morphological characteristics of bone defects in patients with femoral neck fractures using computed tomography (CT) images combined with computer image analysis techniques. METHODS: Four hundred and sixty-nine patients with femoral neck fractures from January 2014 to December 2018 at two grade A tertiary hospitals were included. Models were created in Mimics software based on CT images collected within 1 week after injury and then imported into 3-matic software for virtual reduction. The volume of the bone defect (VBD), maximum defect thickness (MDT), extent of the bone defect region (EBDR) , main defect quadrant (MDQ), collapse type and fracture classification were calculated and recorded. RESULTS: The EBDR, collapse type and MDT all had a significant positive effect on the VBD (P <0.05), with a more significant effect at higher quantiles. Age also had a significant positive effect on the VBD (P < 0.05), but its effect was more pronounced at lower quantiles. Compared to non-subcapital fractures, subcapital fractures had a positive effect on the VBD only at the 50 and 75% quantiles (P < 0.01). The female sex had a significant negative effect on the VBD compared to the male sex (P < 0.05). CONCLUSION: This study established a reliable computer image processing method for quantitative analysis of the VBD in femoral neck fractures and revealed that all patients with femoral neck fractures had bone defects, which can occur at any part of the femoral neck. The EBDR, MDT, collapse type, and patient age and sex were all important risk factors for the extent of the defect and should be taken into account in surgical planning.

Bone mesenchymal stem cells (BMSCs)-derived exosomal microRNA-21-5p regulates Kruppel-like factor 3 (KLF3) to promote osteoblast proliferation in vitro.

Bone mesenchymal stem cells (BMSCs)-derived exosomes (Exos) play important roles in osteoporosis, while the regulation of microRNA (miR)-21-5p remains unclear. The BMSCs-derived exosomes were isolated from femoral bone marrow of trauma patients, which were then used to stimulate human osteoblasts (hFOB1.19 cells). The miR-21-5p mimic or inhibitor was transfected into BMSCs to overexpress or knockdown miR-21-5p. The functions of miR-21-5p in osteoporosis were assessed by cell counting kit-8 (CCK-8) assay, alkaline phosphatase (ALP) staining and alizarin red staining assays. We found that BMSCs-derived exosomes could enhance proliferation, osteoblastic differentiation and ALP activity of hFOB1.19 cells. BMSCs-derived exosomes with upregulated miR-21-5p could further enhance these protective impacts compared with that in BMSCs-derived exosomes, while BMSCs-derived exosomes with downregulated miR-21-5p reduced these cell phenotypes. MiR-21-5p could directly bind to the 3'-untranslated region (UTR) of Kruppel-like factor 3 (KLF3), and knockdown of KLF3 obviously attenuated these inhibitory effects of BMSCs-derived exosomes with downregulated miR-21-5p on osteoblastic differentiation and ALP activity of hFOB1.19 cells. In summary, BMSCs-derived exosomal miR-21-5p improved osteoporosis through regulating KLF3, providing a potential therapeutic strategy for osteoporosis.