Clinical Research Center Research Articles

Explore the possibilities of the artificial intelligence program in the diagnosis of diabetic macular edema, age-related macular degeneration, central serous choriopathy and vitreomacular interface anomalies on the structural optical coherence tomography scans.

Background: macular diseases present a large group of pathological conditions leading to vision loss and poor vision. Early diagnosis of such changes plays an important role in the treatment tactics and comes one of the crucial factors in predicting results.
 Aims: study the possibilities of the artificial intelligence program in the diagnosis of the macular diseases based on the scans of structural OCT analysis.
 Materials and methods: the study included patients undergoing examination and treatment at the Federal Medico-Biological Agency Federal Research Clinical Center and the Moscow Regional Research Clinical Institute named after M.F. Vladimirsky. 200 eyes with the macular diseases and also eyes without macular pathology were examined. A comparative clinical analysis of structural OCT scans performed on an RTVue XR 110-2 tomograph was carried out. Retina AI software was used to analyze OCT scans.
 Results: during the OCT scans analysis various pathological structures of the macular were identified, and then a probable diagnosis was defined. The obtained results were compared with the diagnosis of the ophthalmologists. The sensitivity of the method was 95.16%; specificity - 97.76%; accuracy - 97.38%.
 Conclusions: Retina.AI allows ophthalmologists to successfully perform automated analysis of the OCT scans and identify various pathological conditions of the eye fundus.

Prediction of tumor lysis syndrome in childhood acute lymphoblastic leukemia based on machine learning models: a retrospective study.

Tumor lysis syndrome (TLS) often occurs early after induction chemotherapy for acute lymphoblastic leukemia (ALL) and can rapidly progress. This study aimed to construct a machine learning model to predict the risk of TLS using clinical indicators at the time of ALL diagnosis. This observational cohort study was conducted at the National Clinical Research Center for Child Health and Disease. Data were collected from pediatric ALL patients diagnosed between December 2008 and December 2021. Four machine learning models were constructed using the Least Absolute Shrinkage and Selection Operator (LASSO) to select key clinical indicators for model construction. The study included 2,243 pediatric ALL patients, and the occurrence of TLS was 8.87%. A total of 33 indicators with missing values ≤30% were collected, and 12 risk factors were selected through LASSO regression analysis. The CatBoost model with the best performance after feature screening was selected to predict the TLS of ALL patients. The CatBoost model had an AUC of 0.832 and an accuracy of 0.758. The risk factors most associated with TLS were the absence of potassium, phosphorus, aspartate transaminase (AST), white blood cell count (WBC), and urea levels. We developed the first TLS prediction model for pediatric ALL to assist clinicians in risk stratification at diagnosis and in developing personalized treatment protocols. This study is registered on the China Clinical Trials Registry platform (ChiCTR2200060616). https://www.chictr.org.cn/, identifier ChiCTR2200060616.

Operationalising personalisation in a healthcare system

The balance of power is shifting away from traditional institutions into the hands of individuals. A top priority for every hospital leadership team is the need to provide a much more personalised experience for two primary constituencies: leaders and staff (internal) and patients, including members of the broader communities served (external). Personalisation is seeing and treating people as individuals, whether those people are patients or staff. It is achieved when people know they matter. Operationalising personalisation is the act of adapting the way an organisation functions to make it more likely that both internal and external constituencies at all levels build the skills and have the tools to see and treat people as individuals. Many barriers to personalisation exist within organisational cultures that are designed, instead, for standardisation; however, there is a methodical approach to identifying and overcoming those barriers and to creating an environment where people know they matter as individuals. One private, not-for-profit clinical research centre, hospital and graduate school embarked on this approach, examined organisational systems over a year, identified actions to take and behaviours to change, and improved their personalisation readiness scores across four categories by 17, 21, 32 and 32 percentage points. The experiences of this organisation give other organisations a blueprint to follow in their own pursuits of operationalising personalisation across the enterprise.

Deep learning model to predict lupus nephritis renal flare based on dynamic multivariable time-series data

ObjectivesTo develop an interpretable deep learning model of lupus nephritis (LN) relapse prediction based on dynamic multivariable time-series data.DesignA single-centre, retrospective cohort study in China.SettingA Chinese central tertiary hospital.ParticipantsThe cohort...

Voluntariness of consent in paediatric HIV clinical trials: a mixed-methods, cross-sectional study of participants in the CHAPAS-4 and ODYSSEY trials in Uganda

ObjectivesTo examine the voluntariness of consent in paediatric HIV clinical trials and the associated factors.DesignMixed-methods, cross-sectional study combining a quantitative survey conducted concurrently with indepth interviews.Setting and participantsFrom January 2021...

Clinical practice guidelines for prevention and treatment of postoperative gastrointestinal disorder with Integrated Traditional Chinese and Western Medicine (2023).

Postoperative gastrointestinal disorder (POGD) was a common complication after surgery under anesthesia. Strategies in combination with Traditional Chinese Medicine and Western medicine showed some distinct effects but standardized clinical practice guidelines were not available. Thus, a multidisciplinary expert team from various professional bodies including the Perioperative and Anesthesia Professional Committees of the Chinese Association of Integrative Medicine (CAIM), jointly with Gansu Province Clinical Research Center of Integrative Anesthesiology/Anesthesia and Pain Medical Center of Gansu Provincial Hospital of Traditional Chinese Medicine and WHO Collaborating Center for Guideline Implementation and Knowledge Translation/Chinese Grading of Recommendations, Assessment, Development, and Evaluation (GRADE) Center/Gansu Provincial Center for Medical Guideline Industry Technology/Evidence-based Medicine Center of Lanzhou University, was established to develop evidence-based guidelines. Clinical questions (7 background and 12 clinical questions) were identified through literature reviews and expert consensus meetings. Based on systematic reviews/meta-analyses, evidence quality was analyzed and the advantages and disadvantages of interventional measures were weighed with input from patients' preferences. Finally, 20 recommendations were developed through the Delphi-based consensus meetings. These recommendations included disease definitions, etiologies, pathogenesis, syndrome differentiation, diagnosis, and perioperative prevention and treatment.

Suitability of emu (Dromaius novaehollandiae) eggs for in ovo imaging research as an alternative to conventional animal model: First experience and non‐invasive investigation of physiological embryonal development on computed tomography

AbstractFertilized bird eggs are an alternative model to conventional animal testing. In recent studies, a preclinical imaging model based on large ostrich eggs was introduced in a clinical research centre using imaging systems designed for humans, thus bypassing the need for dedicated small animal imaging systems. Ostrich eggs are only laid during the season with increased daylength, which limits its year‐round availability. The current study focuses on large emu eggs instead of ostrich eggs and aims at investigating its suitability for preclinical imaging research. Physiological development of emu embryos was observed by serial weightings and serial CT scans until developmental day (DD) 46. Differences between fertilized a non‐fertilized eggs were analysed. In fertilized eggs, the embryo was identified on CT scans as early as DD 13. As expected, CT scans showed continuous embryonal development and growth over time, comparable to ostriches. Neither the eggs' volume and weight nor the weight loss nor the radiodensity provided significant differences between fertilized and non‐fertilized eggs. Despite inferior incubation success in emus compared to ostriches, suitability of emu eggs for artificial incubation and subsequent research was confirmed. Hence, emu eggs represent an alternative model for preclinical imaging and allow a year‐round use for research purposes if combined with ostrich eggs.

Trends of Diabetic Retinopathy Research from 2018-2022: A bibliometric analysis

Introduction & Objectives : Diabetic Retinopathy (DR) is one of the leading cause of visual impairment and blindness. Abundant studies have been done around the topic. This study aims to identify research hotspot of DR during the last five years.
 Methods : Document search in the Scopus database was done using the term “diabetic retinopathy” in Title, Abstracts, and Author Keywords. We included only articles written in English published between 2018 and 2022. The dataset were analyzed using VOSviewer to conduct bibliometric analysis, such as citation analysis of sources and institutions, co-authorship analysis of countries, and co- occurrence analysis of author keywords.
 Results : A total of 8.377 articles on DR were retrieved. Number of articles in DR had been increasing steadily overtime. China had the most publications with over 2.000 articles, while United States had the most international collaboration. The most active institution was Guangdong Provincial Clinical Research Center for Ocular Diseases. Scientific Reports was the most prolific journal in DR research. Co- occurrence analysis of author keywords formed 5 clusters; DR management, risk factors for DR, examination for DR, pathogenesis of DR, and diagnostic method for DR.
 Conclusion : This study revealed research trends on diabetic retinopathy research for the last five years. It may provide information for researchers to identify potential collaborator and give better insight on DR research topics

Correlation of MYB/NFIB gene fusion with the grade and prognosis of head and neck adenoid cystic carcinoma and the concordance of two detection methods

Objective: To explore the correlation between MYB/NFIB gene fusion and clinicopathological features such as tumor grade and prognosis of head and neck adenoid cystic carcinoma (ACC), and to assess the concordant rate of fluorescent in situ hybridization (FISH) with MYB and NFIB immunohistochemistry. Methods: FISH detection of MYB/NFIB gene fusion was performed on 48 head and neck ACC cases and 15 non-ACC salivary gland tumors at National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China during April 2014 and January 2020. ACC cases were divided into grade Ⅰ-Ⅱ, grade Ⅲ and high-grade transformation, according to pathological grading criteria. Prognosis, FISH results and other clinicopathological characteristics were analyzed. MYB and NFIB immunohistochemistry was performed on the 48 ACC and 15 non-ACC cases. The diagnostic accuracy of FISH and immunohistochemistry was compared. Results: FISH detected MYB/NFIB gene fusion in 41.7% (20/48) of the ACC. Its positive rate was inversely correlated with higher pathological grades (P=0.036). The higher histological grade was linked to worse progression-free survival (P=0.024), whereas there was no correlation between the status of gene fusion detected by FISH and progression-free survival (P=0.536). FISH didnot detect MYB/NFIB gene fusion in 15 non-ACC salivary gland tumors The specificity of diagnosing ACC is 100% for both FISH detection of gene fusion and immunohistochemical detection of MYB expression. However, the sensitivity for both methods was only about 41.7%, respectively. By combining FISH and MYB immunohistochemistry, the sensitivity for diagnosing ACC was increased to 66.7%. Conclusions: MYB/NFIB gene fusion has a lower detection rate in grade Ⅲ ACC and high-grade transformation ACC. Meanwhile gene fusion status is not correlated with prognosis. The sensitivity for diagnosing ACC can be improved by combining FISH and MYB immunohistochemistry.

Chinese guildeline on diagnosis and treatment of basal cell carcinoma (2023 edition)

Basal cell carcinoma (BCC) is the most common skin malignancy, with a higher prevalence in Caucasians than in East Asians. Although there is a lack of epidemiological data in China, it is generally believed that the incidence of BCC in China is increasing due to the aging population. A variety of risk factors are related to the occurrence of BCC, among which ultraviolet rays and gene mutations play a major role, especially the abnormal activation of Hedgehog (Hh) signaling pathway, which is considered to be the most important pathogenesis of BCC. The clinical manifestations of BCC are highly specific, and most experienced doctors can make a preliminary diagnosis by clinical manifestations. Dermoscopy and other imaging methods can greatly improve the accuracy of diagnosis, but there are still some atypical or rare types of BCC that need further confirmation through histopathological examination. This guideline is initiated by the National Clinical Research Center for Skin and Immune Diseases (based on Peking University First Hospital). It has invited a panel of experts consisting of 24 senior dermatologists specializing in dermatologic surgery from the Dermatologic Surgery Group of the Chinese Medical Doctor Association of Dermatology, the Dermatologic Surgery Group of the Dermatology & Venereology Committee, Chinese Association of Integration Medicine, and the Dermatologic Surgery and Cosmetic Branch of Clina Leprosy Association. In addition, experts from the Burn and Plastic Surgery (Maxillofacial), Ophthalmology, Otolaryngology, Head and Neck Surgery, Radiation Therapy, and Pathology were also invited to participate. This panel forms the "Chinese Guideline for the Diagnosis and Treatment of Basal Cell Carcinoma" expert group. Based on the latest domestic and international research findings, the guideline was developed through four rounds of discussions by the expert group and revised to provide valuable references for clinical healthcare providers in the diagnosis and treatment of BCC.

Olfactory Dysfunction in Adults from Rio Grande do Norte: A Cross-Sectional Study.

Introduction Smell is one of the senses of the human body, and it can be affected by several factors, such as viral infections, traumatic brain injury, iatrogenesis, smoking, and neurodegenerative and systemic diseases. Objectives The main goal of the present study is to describe the epidemiology of olfactory disorders in Rio Grande do Norte (RN). More specifically, to determine the prevalence of olfactory dysfunction and to identify the main risk factors related to these dysfunctions in the state's population. Methods A total of 180 volunteers living in the RN underwent the Connecticut Clinical Research Center (CCCRC) smell test and a clinical and demographic questionnaire. Results A total of 58.89% of the patients presented normosmia and 87.78% were classified as having between normal and mild hyposmia. A statistically significant relationship was found between worse performance in the test and nasal surgery ( p = 0.041) and the subjective feeling of not having an accurate sense of smell ( p = 0.006 on the right nostril). There was no statistical relationship between the olfactory status and the report of coronavirus disease 2019 (COVID-19) infection ( p = 0.254). Conclusion The occurrence of altered sense of smell in our study was different from that reported in other studies that used the same test. The relationship with COVID-19 was not clear.

Abstract WP100: Trends in the Utilization of Intravenous Thrombolysis for Ischemic Stroke in Korea From 2013 to 2022

Introduction: IV thrombolysis is a proven treatment for acute ischemic stroke (AIS), but it is still underutilized in real-world clinical practice. Using a nationwide multicenter stroke registry, we aimed to determine whether there are significant trends in the rate of IV thrombolysis in different patient populations. Methods: This study assessed patients with AIS or transient ischemic attack (TIA) registered prospectively in the Clinical Research Center for Stroke-Korea (CRCS-K) registry between 2013 and 2022. Trends in IV thrombolysis rate were respectively analyzed for all patients (cohort 1), patients who arrived at the hospital within 4.5 hours of onset (cohort 2), and patients potentially eligible for IV thrombolysis (cohort 3), using joinpoint regression analysis. Trends in IV thrombolysis rates in cohorts 1-3 were further investigated using generalized linear mixed-effects models adjusted for patient characteristics and accounting for hospital heterogeneity. Results: A total of 76535 patients were included in the analysis. The mean age of the patients increased from 67.3 to 69.8 years, and the median time from onset to hospital arrival increased over the 10-year period. During the study period, proportion of patients arriving at the hospital within 4.5 hours of onset and the proportion of patients potentially eligible for IV thrombolysis decreased, especially after 2016. IV thrombolysis rates significantly declined over the 10-year period in cohorts 1-3, with a pronounced decrease in the treatment rate in potentially IV thrombolysis eligible patients from 2013 to 2016 (average annual percent change [95% CI] -4.55% [-5.66% to -3.46%] in cohort 1; -2.63% [-3.95% to -1.34%] in cohort 2; -1.33% [-2.06% to -0.49%] in cohort 3). In the multivariable model, patients who arrived in 2022 were less likely to receive IV thrombolysis compared to patients who arrived in 2013 (adjusted odds ratio [95% CI], 0.83 [0.75 - 0.93]). Conclusions: Utilization of IV thrombolysis has declined over the decade in Korea, even accounting for the decline in the number of patients who are candidates for the treatment. Urgent interventions to increase IV thrombolysis rates are needed to improve acute stroke care.

Low-Dose Sulfonylurea Plus DPP4 Inhibitor Lower Blood Glucose and Enhance Beta-Cell Function Without Hypoglycemia.

Low-dose sulfonylureas (SUs) have been found to augment the classical incretin effect, increase glucose sensitivity and late phase incretin potentiation. To evaluate potential synergy between low-dose SU plus a dipeptidyl peptidase 4 (DPP4) inhibitor. Unblinded randomized crossover study at the Clinical Research Centre, University of Dundee. Thirty participants with T2DM (HbA1c < 64 mmol/mol) were treated with diet or metformin. Participants completed 4, 14-day blocks in a random order: control, gliclazide 20 mg (SU), sitagliptin 100 mg (DPP4 inhibitor [DPP4i]), or combination (SUDPP4i). A mixed meal test was conducted after each intervention. The primary outcome was the effect of treatment on beta-cell glucose sensitivity. Secondary outcomes included frequency of glucose <3 mmol/L on continuous glucose monitoring, subanalyses by genotype (KNCJ11 E23K), gender, and body mass index. SU combination with DPP4i showed additive effect on glucose lowering: mean glucose area under the curve (mean 95% CI) (mmol/L) was control 11.5 (10.7-12.3), DPP4i 10.2 (9.4-11.1), SU 9.7 (8.9-10.5), SUDPP4i 8.7 (7.9-9.5) (P < .001). Glucose sensitivity mirrored the additive effect (pmol min-1 m-2 mM-1): control 71.5 (51.1-91.9), DPP4i 75.9 (55.7-96.0), SU 86.3 (66.1-106.4), SUDPP4i 94.1 (73.9-114.3) (P = .04). The additive effect was seen in men but not women. Glucose time in range <3 mmol/L on continuous glucose monitoring (%) was unaffected: control 1 (2-4), DPP4i 2 (3-6), SU 1 (0-4), SUDPP4i 3 (2-7) (P = .65). Low-dose sulfonylurea plus DPP4i has a potent glucose-lowering effect through augmentation of beta-cell function. A double-blind randomized controlled trial would formalize efficacy and safety of this combination, which may avoid negative aspects of SU.

Expression Profiles of Protease in Onychomycosis-Related Pathogenic Trichophyton rubrum and Tinea Capitis-Related Pathogenic Trichophyton violaceum.

The two fungal species Trichophyton rubrum and Trichophyton violaceum are common pathogens on human, infecting keratinized tissue of the outer body parts. Both species are belonging to the "Trichophyton rubrum complex" and share very high similarity in the genome. Secreted proteinases, key factors for keratin degradation, are nearly identical. Contrary, the ecological niches are differing. Trichophyton rubrum preferably infects skin and nails, whereas T. violaceum preferably infects the scalp. We postulate, that differences in the protease expression contribute to differences in ecological preferences. We analyzed the expression profiles of all 22 endoprotease genes, 12 subtilisins (S8A), 5 deuterolysins (M35) and 5 fungalysins (M36), for both species. To compare the influence of the keratin source, we designed experiments with human nail keratin, sheep wool keratin and keratin free cultivation media. Samples were taken at 12h, 24h, 48h and 96h post incubation in keratin medium. The expression of the proteases is higher in wool-keratin medium compared to human nail medium, with the exception of MEP4 and SUB6. Expression in the keratin-free medium is lowest. The expression profiles of the two species are remarkable different. The expression of MEP1, MEP3, SUB5, SUB11 and SUB12 are higher in T. rubrum compared to T. violaceum. MEP2, NpIIc, NpIIe, SUB1, SUB3, SUB4, SUB7 and SUB8 are higher expressed in T. violaceum compared to T. rubrum. The differences of the protease expression in the two species may expalin the differences in the ecological niches. Further analysis are necessary to verify the hypothesis.Please check and conform the edit made in title.Here I thinke the species of strains shouldnt be capital， and the right expression should be, "Expression Profiles of Protease in Onychomycosis-Related Pathogenic Trichophyton rubrum and Tinea Capitis-Related Pathogenic Trichophyton violaceum"Author names: Please confirm if the author names are presented accurately and in the correct se-quence (given name, middle name/initial, family name). Author 1 Given name: [Jingjing] Last name [Chen], Author 2 Given name: [Yangmin] Last name [Gao], Author 3 Given name: [Shuzhen] Last name [Xiong], Author 4 Given name: [Ping] Last name [Zhan]. Also, kindly confirm the details in the metadata are correct.YesPlease check and confirm the inserted city and country are correctly identified for affiliation 3.Please change the affiliations, Affiliation 2:²Jiangxi Provincial Clinical Research Center for Skin Diseases, Dermatology Hospital of Jiangxi Province,The Affiliated Dermatology Hospital of Nanchang University, Nanchang, 330200, Jiangxi; Affiliation 3: 3Institute of Clinical Medicine, Jiangxi Provincial People's Hospital, The First Affiliated Hospital of Nanchang Medical College,Nanchang 330001, Jiangxi. Thanks a lot!

Efficacy and safety of the orthopaedic manipulation techniques of the Lin School of Lingnan Region in the treatment of adolescent idiopathic scoliosis: protocol of a participant-and-assessor-blinded randomized controlled study

BackgroundAdolescent idiopathic scoliosis (AIS) is the most common developmental spine disorder among children. It is characterized by a lateral deviation of the spine that gives rise to the distinctive “S” or “C” shaped bending of the spine. The Lin School of Lingnan Region (LSLR), one of the prominent schools for bare-handed orthopaedic manipulation in southern China, provides preliminary evidences that the orthopaedic manipulation techniques help to correct deviations of the spine. Previous research found that Orthopaedic Manipulation Techniques of LSLR (OMT-LSLR) could reduce the Cobb’s angles in patients with AIS. Therefore, the current study aims to investigate the effectiveness and safety of the OMT-LSLR in treating teenagers with AIS.MethodsIn this participant-and-assessor-blinded randomized controlled clinical trial, 50 participants identified AIS without surgical indications will be recruited and randomized into two groups to receive physiotherapy scoliosis-specific exercises training with either orthopaedic manipulation or sham manipulation treatment for 16 weeks, followed by post-treatment visits at week 24. Primary outcome measure is the change of Scoliosis Research Society-22 (SRS-22) questionnaire score. Secondary outcome measures include Traditional Chinese version of Spinal Appearance Questionnaire (TC-SAQ) score, Italian Spine Youth Quality of Life (ISYQOL) score, the change of Cobb’s angle measured by Xray, and the change of Cobb’s angle, spinal rotation and muscle volume measured by three-dimensional (3D) ultrasound. The trial will be conducted at the Chinese University of Hong Kong Chinese Medicine Specialty Clinic cum Clinical Teaching and Research Centre in Hong Kong (CUHK-CMSCTRC).DiscussionThe results of this study will establish comprehensive clinical evidence about the efficacy and safety of the Orthopaedic Manipulation Techniques of the Lin School of Lingnan Region in the Treatment of Adolescent Idiopathic Scoliosis. One of the characteristics of this trial is that it is a participant-and-assessor-blinded randomized controlled clinical trial with sham manipulation. The study would also apply three-dimensional (3D) ultrasound technology to investigate the relationship between the change of the muscle volume and the spinal curve.Trial registrationThe trial is registered on ClinicalTrials.gov (Identifier: NCT05639023) on December 6, 2022.

Assessment of Knowledge, Attitude, and Practices on Genetic Research Data Reuse for Future Research: Clinical Trial Investigators Perspectives

ABSTRACT Introduction: According to the principle of good clinical practice, it is imperative that the personnel involved in the pharmaceutical or genetic research possess an educational background and comprehensive training. The clinical trial investigator must ensure the safeguard the privacy and confidentiality and prevent inadvertent reuse of research results of study participants. Aim: The objective of the current research is to assess the knowledge, attitude, and practices of clinical trial investigators concerning the reuse of genetic research data. Settings and Design: As a cross-sectional study, there was only one-time collection of knowledge, attitude, and practice on genetics and its data for future research from clinical trial investigators from the Tertiary Care Hospital and Clinical Research Centers in Belagavi Karnataka, India. Subjects and Methods: A study was conducted using validated knowledge, attitude, and practices questionnaire on the clinical trial investigators. Statistical Analysis Used: Data were analyzed using the SPSS software version 21one-way analysis of variance. Results: The present study was comprised n = 50 clinical trial investigators calculated by using the general formula for the calculation of sample size with a confidence of interval limit, of whom 64% exhibited awareness of genetic data reuse in clinical trials. Seventy-four percent of clinical trial investigators expressed concerns about confidentiality issues related to the reuse of genomic data. Conclusions: The lack of synchronized international conference on harmonization of technical requirements for pharmaceuticals for human use (ICH) guidelines directives concerning genomic sampling and data management in health-care research presents a formidable obstacle for pharmaceutical sponsors in achieving consistent and standardized genomic research samples and its data execution in pharmaceutical research on a global scale.

Effectiveness, quality of life, and safety of secukinumab versus conventional systemic therapy in patients with erythrodermic psoriasis: a comparative study.

Erythrodermic psoriasis (EP) is a rare but life-threatening variant of psoriasis less responsive to conventional systemic therapies (CST). Limited research exists on the management of EP with secukinumab. To compare the effectiveness, quality-of-life effects and safety of secukinumab versus CST in patients with EP. EP patients treated with either secukinumab or CST between August 2020 and October 2022 were identified using the National Clinical Research Center for Dermatologic and Immunologic Diseases (NCRC-DID) database encompassing 962 healthcare organizations. Propensity score matching (PSM) was performed to balance the cohorts based on demographic and clinical characteristics. The primary outcomes assessed were Psoriasis Area and Severity Index (PASI), Body Surface Area (BSA), and Dermatology Life Quality Index (DLQI) scales at 4 weeks, 10-14 weeks, and 22-24 weeks. The study included 311 patients (160 receiving secukinumab and 151 receiving CST), among them, 101 matched pairs were generated by propensity score matching (PSM). Secukinumab recipients displayed a notably accelerated response compared to those receiving CST, evidenced by significantly higher rates of achieving PASI50 (before PSM: 73.8% vs. 61.6%, after PSM: 76.2% vs. 63.4%), PASI90 (before PSM: 36.9% vs. 25.8%, after PSM: 40.6% vs. 25.7%), and BSA50 (before PSM: 64.4% vs. 50.3%, after PSM: 68.3% vs. 51.5%) at week 4 (p < 0.05). However, before PSM, secukinumab showed significantly higher DLQI0/1 rates at weeks 4 (41.3% vs. 29.8%) and 12 (63.8% vs. 44.8%). After PSM, statistically significant differences were observed at week 12 for PASI and BSA scores, and at week 4 for DLQI scores (p < 0.05). Similar efficacy trends were observed in other outcomes at week 0 up to week 24, but no statistical differences were noted. Compared to the CST, secukinumab tend to offer a more rapid response and achieve greater improvements in clinical symptoms and quality of life for EP patients.

Advanced neuromonitoring powered by ICM+ and its place in the Brand New AI World, reflections at the 20th anniversary boundary

IntroductionAdoption of the ICM+® brain monitoring software by clinical research centres worldwide has been continuously growing over the past 20 years. This has necessitated ongoing updates to accommodate evolving neuromonitoring research needs, including recent explosion of artificial intelligence (AI). Research questionWe sought to provide an update on the current features of the software. In particular, we aimed to highlight the new options of integrating AI models. Material and methodsWe reviewed all currently available ICM+ analytical areas and discussed potential AI based extensions in each. We tested a proof-of-concept integration of an AI model and evaluated its performance for real-time data processing. ResultsICM+ current analytical tools serve both real-time (bed-side) and offline (file based) analysis, including the calculation engine, Signal Calculator, Custom Statistics, Batch tools, ScriptLab and charting. The ICM+ Python plugin engine allows to execute custom Python scripts and take advantage of complex AI frameworks. For the proof-of-concept, we used a neural network convolutional model with 207,000 trainable parameters that classifies morphology of intracranial pressure (ICP) pulse waveform into 5 pulse categories (normal to pathological plus artefactual). When evaluated within ICM+ plugin script on a Windows 10 laptop the classification of a 5 min ICP waveform segment took only 0.19s with a 2.3s of initial, one-off, model loading time required. ConclusionsModernised ICM+ analytical tools, reviewed in this manuscript, include integration of custom AI models allowing them to be shared and run in real-time, facilitating rapid prototyping and validating of new AI ideas at the bed-side.

LSTM-Based Prediction Model for Tuberculosis Among HIV-Infected Patients Using Structured Electronic Medical Records: A Retrospective Machine Learning Study.

Both HIV and TB are chronic infectious diseases requiring long-term treatment and follow-up, resulting in extensive electronic medical records. With the exponential growth of health and medical big data, effectively extracting and analyzing these data has become the research hotspot. As a fundamental aspect of artificial intelligence, machine learning has been extensively applied in medical research, encompassing diagnosis, treatment, patient monitoring, drug development, and epidemiological investigations. This significantly enhances medical information systems and facilitates the interoperability of medical data. In our study, we analyzed longitudinal data from the electronic health records of 4540 patients, gathered from the National Clinical Research Center for Infectious Diseases in Shenzhen, China, spanning from 2017 to 2021. Initially, we employed the fine-tuned ChatGLM to structure the electronic medical records. Subsequently, we utilized a multi-layer perceptron to classify each patient and determined the presence of tuberculosis in HIV patients. Using machine learning-based natural language processing, we structured these records to build a specialized database for HIV and TB co-infection. We studied the epidemiological characteristics, focusing on incidence patterns, patient characteristics, and influencing factors, to uncover the transmission characteristics of these diseases in Shenzhen. Additionally, we used Long Short-Term Memory to create a predictive model for TB co-infection among HIV patients, based on their medical records. This model predicted the risk of TB co-infection, providing scientific evidence for clinical decision-making and enabling early detection and precise intervention. Based on the refined ChatGLM model tailored for structured electronic health records, the accuracy of symptom extraction consistently surpassed 0.95 precision. Key symptoms such as diarrhea and normal showed precision rates exceeding 0.90. High scores were also achieved in recall and F1 scores. Among 4540 HIV patients, 758 were diagnosed with concurrent tuberculosis, indicating a 16.7% co-infection rate, while syphilis co-infection affected 25.1%, underscoring the prevalence of concurrent infections among HIV patients. Utilizing electronic health records, a Multilayer Perceptron classifier was developed as a benchmark against Long Short-Term Memory to predict high-risk groups for HIV and tuberculosis co-infections. The Multilayer Perceptron classifier demonstrated predictive ability with AUROC values ranging from 0.616 to 0.682 on the test set, suggesting opportunities for further optimization and generalization despite its accuracy in identifying HIV-TB co-infections. In tuberculosis intelligent diagnosis based on laboratory results, the Long Short-Term Memory showed consistent performance across 5-fold cross-validation, with AUROC values ranging from 0.827 to 0.850, indicating reliability and consistency in tuberculosis prediction. Furthermore, by optimizing classification thresholds, the model achieved an overall accuracy of 81.18% in distinguishing HIV co-infected tuberculosis from simple HIV infection. Combining the Multilayer Perceptron classifier with Long Short-Term Memory represented an advanced approach for effectively extracting electronic health records and utilizing it for disease prediction. This underscored the superior performance of deep learning techniques in managing both structured and unstructured medical data. Models leveraging laboratory time-series data demonstrated notably better performance compared to those relying solely on electronic health records for predicting tuberculosis incidence. This emphasized the benefits of deep learning in handling intricate medical data and provided valuable insights for healthcare providers exploring the use of deep learning in disease prediction and management.

Consensus on clinical application of immunoglobulin G4

IgG4 is a subclass of IgG. Elevated serum IgG4 levels are an important serological feature of IgG4 related diseases and serve as a serological marker for assessing disease activity and severity. The harmonization of IgG4 detection is crucial for its clinical application. National Clinical Research Center for Dermatologic and Immunologic Diseases (Peking Union Medical College Hospital), Experimental Diagnosis Research Committee, Rheumatology and Immunology Physicians Committee of Chinese Medical Doctor Association, Autoantibodies Detection Committee, and Chinese Rheumatism Data Center have organized clinical and laboratory experts to draft this consensus, aiming to standardize IgG4 detection and provide guideline for clinician and laboratory experts to appropriate utility and interpret IgG4 results in China.