Use of biologics in patients with psoriasis - A retrospective analysis based on real-world data.

OBJECTIVE: To summarize and analysis the application of biologic agents in patients with psoriasis in the real world. METHODS: Relying on collected data from June 2020 to September 2021 in the database of China Psoriasis Standardized Diagnosis and Treatment Center, 2529 cases of psoriasis patients treated with biologic agents in 188 different tertiary hospitals across China were retrospective analyzed. The collected information mainly includes demographic data (age, gender, psoriasis history), curative effectiveness of used biologics drug withdrawal and its reason. According to the collected information, condition of the usage for each category of biologics and influencing factor of biologics replacement were analyzed. RESULT: A total of 2529 patients were analyzed, which included 1626 male (64.29%) and 903 female (35.71%) with an average age of 42.12 ± 14.70 (17 âˆ¼ 85) years old; 2336 (92.37%) patients were aged from 19 to 60 years old. Within these patients, 2362 of them (93.40%) had a psoriasis area and severity index (PASI) score, and 1776 of these patients had moderate to severe cases (75.19%). According to the patient's self-evaluation of the past efficacy of biological agents, secukinumab was chosen by the most people to have the highest efficacy (1140 cases, 93.60%). The main reason for the withdrawal of secukinumab is that the disease is already well controlled at the time of withdrawal (67 cases, 38.95%); for TNF- α inhibitor is the poor curative effect; for ustekinumab and ixekizumab were the non-affordable price. CONCLUSIONS: In the current biotherapy of psoriasis in China, the efficacy of secukinumab is thought by most people to be the highest. Secukinumab is the first choice when the needs of changing biologics appear.

Real-world systemic sequential therapy with regorafenib for recurrent hepatocellular carcinoma: analysis of 93 cases from a single center.

BACKGROUND: Regorafenib is an oral multikinase inhibitor and became the first second-line systemic treatment for hepatocellular carcinoma (HCC) following the phase III RESORCE trial. This single-center study retrospectively analyzed the clinical data and follow-up results of patients with recurrent HCC treated with regorafenib and discussed the prognostic factors to provide guidance for clinical treatment. METHODS: Ninety-three recurrent HCC patients were enrolled in the research and follow up from December 2017 to December 2020. Clinical and pathological data were collected. SPSS software v26.0 was used (Chicago, IL, USA) for statistical analysis. A two-sided P < 0.05 was considered statistically significant. RESULTS: The patients included 81 males and 12 females with a median age of 57 years. Eighty-seven patients had hepatitis B virus (HBV) infection. The objective response rate (ORR) was 14.0%, and the disease control rate (DCR) was 62.4%. The median overall survival (mOS) and median time to progression (mTTP) were 15.9 and 5.0 months. Multivariate analysis showed that Child-Pugh classification, the Eastern Cooperative Oncology Group performance status (ECOG PS), the neutrophil-to-lymphocyte ratio (NLR), combined treatment, and the time from first diagnosis of HCC to second-line treatment were independent factors affecting the prognosis of recurrent HCC patients. CONCLUSIONS: This real-world study demonstrated similar findings to those of the RESORCE trial. Regorafenib could effectively improve the prognosis of patients after first-line treatment failure. Combination therapy under multidisciplinary treatment (MDT) team guidance could be effective in impeding tumor progression and improving the prognosis of recurrent HCC patients.

Application of artificial intelligence in a real-world research for predicting the risk of liver metastasis in T1 colorectal cancer.

BACKGROUND: Liver is the most common metastatic site of colorectal cancer (CRC) and liver metastasis (LM) determines subsequent treatment as well as prognosis of patients, especially in T1 patients. T1 CRC patients with LM are recommended to adopt surgery and systematic treatments rather than endoscopic therapy alone. Nevertheless, there is still no effective model to predict the risk of LM in T1 CRC patients. Hence, we aim to construct an accurate predictive model and an easy-to-use tool clinically. METHODS: We integrated two independent CRC cohorts from Surveillance Epidemiology and End Results database (SEER, training dataset) and Xijing hospital (testing dataset). Artificial intelligence (AI) and machine learning (ML) methods were adopted to establish the predictive model. RESULTS: A total of 16,785 and 326 T1 CRC patients from SEER database and Xijing hospital were incorporated respectively into the study. Every single ML model demonstrated great predictive capability, with an area under the curve (AUC) close to 0.95 and a stacking bagging model displaying the best performance (AUC = 0.9631). Expectedly, the stacking model exhibited a favorable discriminative ability and precisely screened out all eight LM cases from 326 T1 patients in the outer validation cohort. In the subgroup analysis, the stacking model also demonstrated a splendid predictive ability for patients with tumor size ranging from one to50mm (AUC = 0.956). CONCLUSION: We successfully established an innovative and convenient AI model for predicting LM in T1 CRC patients, which was further verified in the external dataset. Ultimately, we designed a novel and easy-to-use decision tree, which only incorporated four fundamental parameters and could be successfully applied in clinical practice.

[Narrative evidence-based medicine:a strategy for evaluation of clinical efficacy of Chinese medicine].

Rich experience of clinical diagnosis and treatment has been accumulated in the developmental history of Chinese medicine, and the efficacy has been increasingly accepted by the public. However, the evaluation of clinical efficacy is currently based more on scientific evidence instead of merely the changes of patient symptoms. In Chinese medicine, the changes of major disease indicators, patient symptoms, and pathogenesis are the major criteria for the evaluation of clinical efficacy. The lack of well-accepted and uniform criteria and the uncertainty of subjective evaluation limit the development of clinical Chinese medicine. Evidence-based medicine combines clinical skills with the current best evidence. Narrative medicine, utilizing people's narratives in clinical practice, emphasizes patient feelings, willingness, and value orientation. The introduction of both evidence-based medicine and narrative medicine into the evaluation of clinical efficacy refers to the construction of the clinical efficacy evaluation system in a paradigm of participatory diagnosis and treatment. It can fully reflect the characteristics of Chinese medicine, respect the values of patients, and achieve universal clinical evidence. Therefore, it helps to improve the diagnosis and treatment, the relationship between doctors and patients, patients' life quality and decision-making awareness, and finally the new evaluation model of clinical efficacy of Chinese medicine.

[Development and trends of real-world research based on bibliometric and knowledge map analysis].

To explore the focus and trends in real-world studies in Chinese through knowledge mapping method, databases CNKI, VIP, Wanfang and Sinomed were retrieved, with 1 757 relevant articles published before September 30rd, 2020 finally included, whose bibliographical records were imported into NoteExpress to avoid duplication and check relativity. VOSviewer, a bibliometric analysis tool, was used to analyze their development. It was found that real-world studies have mainly taken shape after 2010, in which traditional Chinese medicine research plays an important role. China Journal of Chinese Material Medica was the leading journal with 120 papers, the China Academy of Chinese Medical Sciences the most contribution institution with 338 papers, and Xie Yanming from the institution the most contribution author with 250 papers. This study helps clinicians and researchers in better understanding the evolution of real-world research over more than two decades in China.

"Mobile Health" for the Management of Spondyloarthritis and Its Application in China.

PURPOSE OF THE REVIEW: Spondyloarthritis (SpA) is a group of inflammatory diseases characterized by inflammation in the spine, peripheral joints, and entheses that usually start at the prime of one's life and lead to impaired physical function and reduced quality of life. Ankylosing spondylitis (AS) is prototype of SpA. This article reviews the opportunities and challenges of using mobile health (mHealth) in managing SpA, and report some of our experiences using a mHealth solution for management of SpA patients and performing related research in China. RECENT FINDINGS: The recent rapid development of mobile communications and the common use of intelligent electronic devices have led to the increasing application of mHealth for chronic disease management by healthcare providers and patients alike. This is a promising new technology that can help mitigate limitations in time and space for patient management, promote easier communication between patients and their healthcare providers, reduce medical expenses, and optimize medical services. We have developed a smartphone-based mHealth SpA management system (SpAMS) that also helps the patients to monitor, manage, and share information on their disease with their physician at regular intervals. There is a shift from a paternalistic model of healthcare to more personalized healthcare in which disease management is conducted by the patient together with their healthcare providers. The increasing utility of mHealth is expected to benefit disease management, promote patient-doctor communication, reduce medical expenses, and optimize medical services.

[Real-world study of paritaprevir/ritonavir-ombitasvir combined with dasabuvir for the treatment of chronic hepatitis C 1b genotype infection in China].

Objective: To evaluate the real-world safety and curative effect of ombitasvir combined with dasabuvir for the treatment of chronic hepatitis C 1b genotype infection in non-cirrhotic or compensated cirrhotic patients. Methods: A real-world research method was adopted, and the research was conducted at three medical centers of mainland China. Non- cirrhotic or compensated cirrhotic patients with HCV genotype 1b infection who were initially treated with IFN/PEG-IFN-alpha combined with ribavirin, and ombitasvir combined with dasabuvir for 8 or 12 weeks were taken. Sustained virological response (SVR) and the incidence of adverse events during treatment and follow-up were evaluated after 12 weeks of drug withdrawal at OBV/PTV/r 25/150/100mg once daily and DSV 250mg, twice daily. Median and range were used for description of non-normally distributed data. Results: 80 cases of GT1b were included in this study. Of these 88.8% (71/80) were newly diagnosed, 12.5% (10/80) were compensated cirrhotic, 97.5% (78/80) received 12 weeks treatment, and 2.5% (2/80) received 8 weeks treatment. The rate of HCV RNA negative at EOT (end of treatment) was 100% (64/64). A total of 67 patients completed the treatment within 12 weeks, and 43 patients returned to the hospital for further consultations, and SVR12 was 100%(43/43). No patient discontinued the drugs because of an adverse event during treatment. Conclusion: In the real world, Ombitasvir combined with dasabuvir for the treatment of chronic hepatitis C 1b genotype infection in China has 100% rates of EOT and SVR12 with well- tolerability and safety.

Disparities of Trastuzumab Use in Resource-Limited or Resource-Abundant Regions and Its Survival Benefit on HER2 Positive Breast Cancer: A Real-World Study from China.

BACKGROUND: Trastuzumab is a key component of therapy for human epidermal growth receptor 2 (HER2) positive breast cancer. Because real-world data are lacking, the present research was conducted to evaluate the actual use of and the effectiveness of trastuzumab in the real world in China. METHODS: Inpatients with HER2 positive invasive breast cancer from 13 hospitals in Eastern China (2010-2015, n = 1,139) were included in this study. We aimed to assess the actual use of trastuzumab and to evaluate potential efficacy from trastuzumab in real-world research. RESULTS: Of 1,017 patients with early stage breast cancer (EBC), 40.5% (412/1,017) received trastuzumab therapy. Patients with EBC in resource-abundant regions (gross domestic product per capita >$15,000 and trastuzumab included in Medicare) are more likely to receive trastuzumab than those in resource-limited regions (37.3% vs. 13.0%, p < .05). After metastasis, 50.8% (366/720) patients received trastuzumab as their first-line therapy. More than 10% of patients with metastatic breast cancer (MBC) continued trastuzumab therapy after twice progression in resource-abundant regions, whereas more than 40% of patients never received any trastuzumab therapy during the whole course of therapy in resource-limited regions. Overall, the improvement in survival for trastuzumab versus non-trastuzumab was substantial in EBC (hazard ratio [HR] = 0.609, 95% confidence interval [CI]: 0.505-0.744) and in MBC (HR = 0.541, 95% CI: 0.418-0.606). This association was greater for patients with MBC who had never received trastuzumab (HR = 0.493, 95% CI: 0.372-0.576) than for those who had received adequate trastuzumab therapy in EBC stage (HR = 0.878, 95% CI: 0.506-1.431). CONCLUSION: This study showed great disparities in trastuzumab use in different regions and different treatment stages. Both EBC and MBC patients can benefit from trastuzumab, as the survival data show; however, when trastuzumab is adequate in the early stage, a further trastuzumab-based therapy in first-line treatment of MBC will be ineffective, especially for those with short disease-free survival, and a second line of anti-HER2 therapy will be recommended. (Research number: CSCO-BC RWS 15001). IMPLICATIONS FOR PRACTICE: This article explores the disparities in the rates of trastuzumab use due to the inequitable allocation of medical resources in China. The irrational use can be found both in resource-abundant regions and in resource-limited regions. Although trastuzumab-based therapy improved survival, the actual use of trastuzumab in the early stage of breast cancer may influence the subsequent therapeutic effect after metastasis. These findings from real-world research could help to optimize HER2 therapy after metastasis, especially in regions with limited access to these expensive targeted drugs.

Real-World Research on Retinal Diseases Using Health Claims Database: A Narrative Review.

Real-world data (RWD) has emerged as a crucial component in understanding and improving patient outcomes across various medical conditions, including retinal diseases. Health claims databases, generated from healthcare reimbursement claims, offer a comprehensive source of RWD, providing insights into patient outcomes, healthcare utilization, and treatment effectiveness. However, the use of these databases for research also presents unique challenges. This narrative review explores the role of real-world research on retinal diseases using health claims databases, highlighting their advantages, limitations, and potential contributions to advancing our understanding and management of the diseases. The review examines the applications of health claims databases in retinal disease research, including epidemiological studies, comparative effectiveness and safety analyses, economic burden assessments, and evaluations of patient outcomes and quality of care. Previous findings demonstrate the value of these databases in generating prevalence and incidence estimates, identifying risk factors and predictors, evaluating treatment effectiveness and safety, and understanding healthcare utilization patterns and costs associated with retinal diseases. Despite their strengths, health claims databases face challenges related to data limitations, biases, privacy concerns, and methodological issues. Accordingly, the review also explores future directions and opportunities, including advancements in data collection and analysis, integration with electronic health records, collaborative research networks and consortia, and the evolving regulatory landscape. These developments are expected to enhance the utility of health claims databases for retinal disease research, resulting in more comprehensive and impactful findings across diverse retinal disorders and robust real-world insights from a large population.

Feasibility and tolerability of eribulin-based chemotherapy versus other chemotherapy regimens for patients with metastatic triple-negative breast cancer: a single-centre retrospective study.

Background: Patients with Triple-negative breast cancer (TNBC) face a poor prognosis and limited therapeutic options. Current data on eribulin usage to treat TNBC is scarce. Therefore, we sought to compare the feasibility and tolerability of eribulin-based regimens with other chemotherapy regimens in patients with TNBC. Method: This retrospective study was conducted at Fujian Medical University Cancer Hospital and included 159 patients with TNBC enrolled between October 2011 and January 2023. Patients underwent treatment with eribulin-based and other chemotherapy regimens. The study's primary endpoints were progression-free survival (PFS) and overall survival (OS), while its secondary endpoint was objective response rate (ORR), disease control rate (DCR), and safety. Tumour response was assessed using RECIST V.1.1 criteria. Results: Of the 159 participants in the study, 42 individuals (26.4%) received treatment with eribulin, whereas 117 participants (73.6%) were administered alternative chemotherapy regimens, which included nab-paclitaxel-based therapy (n = 45) and platinum-based therapy (n = 51). The follow-up period for all patients ended on 31 December 2022, and the median follow-up time was 18.3 months (range:0.7-27.5). Following propensity score matching (PSM), eribulin-based treatment resulted in longer median progression-free survival compared to platinum-based (hazard ratio (HR) = 0.41, p = 0.006), nab-paclitaxel-based (hazard ratio = 0.36, p = 0.001) and other chemotherapy (HR = 0.39, p < 0.001). Also, eribulin induced a remarkable prolongation of the median overall survival duration in all three comparative groups. The group receiving eribulin treatment showed significantly reduced incidences of any grade of anaemia, peripheral neuropathy, nausea and vomiting, and hair loss compared to other chemotherapy groups. Conclusion: For the salvage treatment of advanced TNBC, treatment with eribulin produced longer median PFS and OS than other chemotherapy regimens, with a well-tolerated safety profile. Therefore, further investigation of eribulin-based treatment in larger randomized trials for patients with advanced TNBC is warranted.

NRS2002 score as a prognostic factor in solid tumors treated with immune checkpoint inhibitor therapy: a real-world evidence analysis.

To observe the antitumour efficacy of programmed death 1 (PD-1) inhibitors in the real world and explore the relationship between NRS2002 score or other clinical characteristics and immunotherapy efficacy, we retrospectively analyzed 341 tumor patients who received immune checkpoint inhibitor (ICI) treatment at one center. A total of 341 solid tumor patients treated with ICIs from June 2018 to December 2021 were retrospectively included in this study. Patient characteristics, ICI responses, and survival status were documented, and the relationships between clinical factors and survival were analyzed. Among all patients, the median progression-free survival (PFS) was 5.8 months, and the median overall survival (OS) was 12.5 months. The Performance Status (PS), NRS2002 score, The Naples Prognostic Score (NPS), Lymphocyte and C-reactive protein ratio (LCR), line of therapy, and nutritional support were significantly related to PFS or OS according to univariate analysis. The median PFS and OS were significantly better in the group without nutritional risk (NRS2002 0-2) than those with nutritional risk (NRS2002 ≥ 3) (PFS: HR = 1.82, 95% CI 1.30-2.54, p value < .001; OS: HR = 2.49, 95% CI 1.73-3.59, p value < .001). Cox regression analysis revealed that the NRS2002 score was an independent prognostic factor for both PFS and OS. The objective response rate (ORR) in the group at nutritional risk was lower than that in the group without nutritional risk (8.33% and 19.71%, respectively, p value = .037). Patients at nutritional risk according to the NRS2002 score at initial treatment had a poorer prognosis than those without nutritional risk. The NRS2002 could be used as a preliminary index to predict the efficacy of immune checkpoint inhibitor therapy.

The Efficacy and Safety of Apatinib and Anlotinib in Advanced Non-Small Cell Lung Cancer.

Background: Anlotinib and apatinib, both vascular endothelial growth factor receptor-tyrosine kinase inhibitors (VEGFR-TKIs), are clinically established in the treatment of advanced non-small cell lung cancer (NSCLC) in China, with anlotinib emerging as a standard treatment strategy. This study was conducted to evaluate the efficacy and safety of apatinib and anlotinib, and to compare their differences in treating patients with advanced NSCLC. Patients and Methods: We retrospectively analyzed the data of patients with advanced NSCLC treated with apatinib or anlotinib at a hospital in Eastern China from January 2017 to December 2021. The primary endpoint was progression-free survival (PFS), while secondary endpoints included objective response rate (ORR), disease control rate (DCR), overall survival (OS), and safety profile. Results: A total of 145 patients were included in this study. Median PFS (mPFS) was 3.53 months for the apatinib group and 5.3 months for the anlotinib group (HR = 0.59, 95% CI: 0.41-0.84; P = 0.004), and median OS (mOS) was 7.6 months versus 15.6 months (HR = 0.68, 95% CI: 0.46-1.00; P = 0.048), which all showed significant differences after adjusting for confounders (P < 0.05). Subgroup analysis revealed that the presence or absence of bone metastases significantly influenced PFS in both treatment groups. The ORR was 3.03% in the anlotinib group versus 10.13% in the apatinib group (P = 0.12), the DCR was 72.73% versus 51.90% (P = 0.21). No unanticipated adverse events (AEs) were observed. The incidence of grade 3-4 AEs was significantly higher in the apatinib group (31.65% vs 13.64%, P < 0.05). Conclusion: Anlotinib demonstrated greater efficacy and safety compared to apatinib in the treatment of advanced NSCLC, particularly in patients with bone metastases and EGFR(-).

[Evaluation of the clinical effect of acupuncture in treatment of neck pain in cervical spondylosis based on propensity score matching].

OBJECTIVE: To observe the clinical effect and safety of acupuncture in treatment of neck pain due to cervical spondylosis. METHODS: According to the patients' preference and acceptance for the interventions of neck pain induced by cervical spondylosis, an acupuncture group (221 cases) and a non-acupuncture group (251 cases) were divided. After the control of confounding factors with propensity score matching, 218 cases were included in either acupuncture group or non-acupuncture group. In the acupuncture group, acupuncture was applied to Dazhui (GV 14), Baihui (GV 20), ashi points, bilateral neck-Jiaji (EX-B 2), Fengchi (GB 20), Houxi (SI 3), Shenmai (BL 62), etc. The treatment was given once daily, one course of intervention was composed of 5 treatments and 3 courses were included. In the non-acupuncture group, the oral administration of imrecoxib tablets and cobalt tablets was prescribed for 2 weeks. Before and after treatment, the scores of Northwick Park questionnaire (NPQ) and the simplified McGill pain questionnaire (SF-MPQ) were observed, and the safety was assessed in patients of the two groups. RESULTS: After treatment completion, the scores of NPQ and SF-MPQ were all reduced when compared with those before treatment in each group (P<0.001), and the scores of NPQ and SF-MPQ in the acupuncture group were lower than those of the non-acupuncture group (P<0.001). The incidence of adverse reactions was 6.0% (13/218) in the acupuncture group and was 10.1% (22/218) in the non-acupuncture group, without statistical significance in comparison (P>0.05). CONCLUSION: Acupuncture is effective and safe in the relief of neck pain and the improvement of comprehensive quality of life in the patients with cervical spondylosis.

A Case Series of Continuous Theta Burst Stimulation Treatment for the Supplementary Motor Area Twice a Day in Patients with Obsessive-Compulsive Disorder: A Real World TMS Registry Study in Japan.

Obsessive-compulsive disorder (OCD) is a psychiatric disorder characterized by patterns in which unwanted thoughts and fears are evoked as obsessions and furthermore, compulsive behaviors are provoked repeatedly, with a prevalence rate of 2% of the population. These obsessive-compulsive symptoms disrupt daily life and cause great distress to the individual. At present, OCD is treated with antidepressants, mainly selective serotonin reuptake inhibitors, and psychotherapy, including the exposure and response prevention method. However, these approaches may only show a certain level of efficacy, and approximately 50% of patients with OCD show treatment resistance. This situation has led to the research and development of neuromodulation therapies, including transcranial magnetic stimulation treatment, for OCD worldwide in recent years. In this case series, we retrospectively analyzed the TMS registry data of continuous theta burst stimulation (cTBS) therapy targeting the bilateral supplementary motor cortex for six patients with OCD whose obsessive-compulsive symptoms had not improved with pharmacotherapy. The results suggest that treatment with cTBS for the bilateral supplementary motor area may reduce obsessive-compulsive symptoms in patients with OCD, despite the limitations of an open-label preliminary case series. The present findings warrant further validation with a randomized, sham-controlled trial with a larger sample size in the future.

A machine learning-based model for predicting the risk of early-stage inguinal lymph node metastases in patients with squamous cell carcinoma of the penis.

Objective: Inguinal lymph node metastasis (ILNM) is significantly associated with poor prognosis in patients with squamous cell carcinoma of the penis (SCCP). Patient prognosis could be improved if the probability of ILNM incidence could be accurately predicted at an early stage. We developed a predictive model based on machine learning combined with big data to achieve this. Methods: Data of patients diagnosed with SCCP were obtained from the Surveillance, Epidemiology, and End Results Program Research Data. By combing variables that represented the patients' clinical characteristics, we applied five machine learning algorithms to create predictive models based on logistic regression, eXtreme Gradient Boosting, Random Forest, Support Vector Machine, and k-Nearest Neighbor. Model performance was evaluated by ten-fold cross-validation receiver operating characteristic curves, which were used to calculate the area under the curve of the five models for predictive accuracy. Decision curve analysis was conducted to estimate the clinical utility of the models. An external validation cohort of 74 SCCP patients was selected from the Affiliated Hospital of Xuzhou Medical University (February 2008 to March 2021). Results: A total of 1,056 patients with SCCP from the SEER database were enrolled as the training cohort, of which 164 (15.5%) developed early-stage ILNM. In the external validation cohort, 16.2% of patients developed early-stage ILNM. Multivariate logistic regression showed that tumor grade, inguinal lymph node dissection, radiotherapy, and chemotherapy were independent predictors of early-stage ILNM risk. The model based on the eXtreme Gradient Boosting algorithm showed stable and efficient prediction performance in both the training and external validation groups. Conclusion: The ML model based on the XGB algorithm has high predictive effectiveness and may be used to predict early-stage ILNM risk in SCCP patients. Therefore, it may show promise in clinical decision-making.

Application of machine learning techniques in real-world research to predict the risk of liver metastasis in rectal cancer.

Background: The liver is the most common site of distant metastasis in rectal cancer, and liver metastasis dramatically affects the treatment strategy of patients. This study aimed to develop and validate a clinical prediction model based on machine learning algorithms to predict the risk of liver metastasis in patients with rectal cancer. Methods: We integrated two rectal cancer cohorts from Surveillance, Epidemiology, and End Results (SEER) and Chinese multicenter hospitals from 2010-2017. We also built and validated liver metastasis prediction models for rectal cancer using six machine learning algorithms, including random forest (RF), light gradient boosting (LGBM), extreme gradient boosting (XGB), multilayer perceptron (MLP), logistic regression (LR), and K-nearest neighbor (KNN). The models were evaluated by combining several metrics, such as the area under the curve (AUC), accuracy score, sensitivity, specificity and F1 score. Finally, we created a network calculator using the best model. Results: The study cohort consisted of 19,958 patients from the SEER database and 924 patients from two hospitals in China. The AUC values of the six prediction models ranged from 0.70 to 0.95. The XGB model showed the best predictive power, with the following metrics assessed in the internal test set: AUC (0.918), accuracy (0.884), sensitivity (0.721), and specificity (0.787). The XGB model was assessed in the outer test set with the following metrics: AUC (0.926), accuracy (0.919), sensitivity (0.740), and specificity (0.765). The XGB algorithm also shows a good fit on the calibration decision curves for both the internal test set and the external validation set. Finally, we constructed an online web calculator using the XGB model to help generalize the model and to assist physicians in their decision-making better. Conclusion: We successfully developed an XGB-based machine learning model to predict liver metastasis from rectal cancer, which was also validated with a real-world dataset. Finally, we developed a web-based predictor to guide clinical diagnosis and treatment strategies better.

A Machine Learning Algorithm for Predicting the Risk of Developing to M1b Stage of Patients With Germ Cell Testicular Cancer.

Objective: Distant metastasis other than non-regional lymph nodes and lung (i.e., M1b stage) significantly contributes to the poor survival prognosis of patients with germ cell testicular cancer (GCTC). The aim of this study was to develop a machine learning (ML) algorithm model to predict the risk of patients with GCTC developing the M1b stage, which can be used to assist in early intervention of patients. Methods: The clinical and pathological data of patients with GCTC were obtained from the Surveillance, Epidemiology, and End Results (SEER) database. Combing the patient's characteristic variables, we applied six machine learning (ML) algorithms to develop the predictive models, including logistic regression(LR), eXtreme Gradient Boosting (XGBoost), light Gradient Boosting Machine (lightGBM), random forest (RF), multilayer perceptron (MLP), and k-nearest neighbor (kNN). Model performances were evaluated by 10-fold cross-receiver operating characteristic (ROC) curves, which calculated the area under the curve (AUC) of models for predictive accuracy. A total of 54 patients from our own center (October 2006 to June 2021) were collected as the external validation cohort. Results: A total of 4,323 patients eligible for inclusion were screened for enrollment from the SEER database, of which 178 (4.12%) developing M1b stage. Multivariate logistic regression showed that lymph node dissection (LND), T stage, N stage, lung metastases, and distant lymph node metastases were the independent predictors of developing M1b stage risk. The models based on both the XGBoost and RF algorithms showed stable and efficient prediction performance in the training and external validation groups. Conclusion: S-stage is not an independent factor for predicting the risk of developing the M1b stage of patients with GCTC. The ML models based on both XGBoost and RF algorithms have high predictive effectiveness and may be used to predict the risk of developing the M1b stage of patients with GCTC, which is of promising value in clinical decision-making. Models still need to be tested with a larger sample of real-world data.

Effectiveness and Economic Evaluation of Polyene Phosphatidyl Choline in Patients With Liver Diseases Based on Real-World Research.

Aims: Liver disease has high prevalence, number, and disease burden in China, and polyene phosphatidyl choline (PPC) is a widely used liver protective drug. We aim to explore the effectiveness and economy of PPC in patients with liver diseases based on real-world research and compare with other hepatoprotective drugs. Methods: This is a "three-phase" study from three medical centers, including descriptive study of patients using PPC injection, self-control case study of patients using PPC injection, and specific-disease cohort study of patients using PPC injection or control drugs. The major measurements of liver function for effectiveness analysis were the alanine transaminase (ALT) level changes and recovery rate. The main statistical methods were Wilcoxon signed rank test, χ 2 test, and Mann-Whitney U test. Propensity score matching was applied to reduce bias. Cost-effectiveness analysis, cost minimization analysis, and sensitivity analysis were used for economic evaluation. Results: PPC alone or in combination with glutathione and magnesium isoglycyrrhizinate shows less total hospitalization cost (p < 0.05) and smaller cost-effectiveness ratio and was effective in protecting liver function, especially in patients with liver transplantation or postoperation of nontumor liver disease (ALT decreased significantly after PPC treatment; p < 0.05). Glutathione and magnesium isoglycyrrhizinate combined with PPC could enhance the protective function of liver. Conclusion: PPC was an effective and economic liver protective drug in patients with specific liver diseases, and PPC could enhance the liver protective function of glutathione and magnesium isoglycyrrhizinate.

Application of machine learning in the prediction of deficient mismatch repair in patients with colorectal cancer based on routine preoperative characterization.

Simple summary: Detecting deficient mismatch repair (dMMR) in patients with colorectal cancer is essential for clinical decision-making, including evaluation of prognosis, guidance of adjuvant chemotherapy and immunotherapy, and primary screening for Lynch syndrome. However, outside of tertiary care centers, existing detection methods are not widely disseminated and highly depend on the experienced pathologist. Therefore, it is of great clinical significance to develop a broadly accessible and low-cost tool for dMMR prediction, particularly prior to surgery. In this study, we developed a convenient and reliable model for predicting dMMR status in CRC patients on routine preoperative characterization utilizing multiple machine learning algorithms. This model will work as an automated screening tool for identifying patients suitable for mismatch repair testing and consequently for improving the detection rate of dMMR, while reducing unnecessary labor and cost in patients with proficient mismatch repair. Background: Deficient mismatch repair (dMMR) indicates a sustained anti-tumor immune response and has a favorable prognosis in patients with colorectal cancer (CRC). Although all CRC patients are recommended to undergo dMMR testing after surgery, current diagnostic approaches are not available for all country hospitals and patients. Therefore, efficient and low-cost predictive models for dMMR, especially for preoperative evaluations, are warranted. Methods: A large scale of 5596 CRC patients who underwent surgical resection and mismatch repair testing were enrolled and randomly divided into training and validation cohorts. The clinical features exploited for predicting dMMR comprised the demographic characteristics, preoperative laboratory data, and tumor burden information. Machine learning (ML) methods involving eight basic algorithms, ensemble learning methods, and fusion algorithms were adopted with 10-fold cross-validation, and their performance was evaluated based on the area under the receiver operating characteristic curve (AUC) and calibration curves. The clinical net benefits were assessed using a decision curve analysis (DCA), and a nomogram was developed to facilitate model clinical practicality. Results: All models achieved an AUC of nearly 0.80 in the validation cohort, with the stacking model exhibiting the best performance (AUC = 0.832). Logistical DCA revealed that the stacking model yielded more clinical net benefits than the conventional regression models. In the subgroup analysis, the stacking model also predicted dMMR regardless of the clinical stage. The nomogram showed a favorable consistence with the actual outcome in the calibration curve. Conclusion: With the aid of ML algorithms, we developed a novel and robust model for predicting dMMR in CRC patients with satisfactory discriminative performance and designed a user-friendly and convenient nomogram.