ChatGPT4's Proficiency in Addressing Patients' Questions on Systemic Lupus Erythematosus: A Blinded Comparative Study with Specialists.

OBJECTIVES: The efficacy of artificial intelligence (AI)-driven chatbots like ChatGPT4 in specialized medical consultations, particularly in rheumatology, remains underexplored. This study compares the proficiency of ChatGPT4' responses with practicing rheumatologists to inquiries from patients with systemic lupus erythematosus (SLE). METHODS: In this cross-sectional study, we curated 95 frequently asked questions (FAQs), including 55 in Chinese and 40 in English. Responses for FAQs from ChatGPT4 and 5 rheumatologists were scored separately by a panel of rheumatologists and a group of patients with SLE across 6 domains (scientific validity, logical consistency, comprehensibility, completeness, satisfaction level, and empathy) on a 0-10 scale (a score of 0 indicates entirely incorrect responses, while 10 indicates accurate and comprehensive answers). RESULTS: Rheumatologists' scoring revealed that ChatGPT4-generated responses outperformed those from rheumatologists in satisfaction level and empathy, with mean differences of 0.537 (95% CI, 0.252-0.823; p < 0.01) and 0.460 (95% CI, 0.227-0.693 p < 0.01), respectively. From the SLE patients' perspective, ChatGPT4-generated responses were comparable to the rheumatologist-provided answers in all 6 domains. Subgroup analysis revealed ChatGPT4 responses were more logically consistent and complete regardless of language, and exhibited greater comprehensibility, satisfaction, and empathy in Chinese. However, ChatGPT4 responses were inferior in comprehensibility for English FAQs. CONCLUSION: ChatGPT4 demonstrated comparable, possibly better in certain domains, to address FAQs from patients with SLE, when compared with the answers provided by specialists. This study showed the potential of applying ChatGPT4 to improve consultation in SLE patients.

Multi-epitope vaccine design for hepatitis E virus based on protein ORF2 and ORF3.

Introduction: Hepatitis E virus (HEV), with heightened virulence in immunocompromised individuals and pregnant women, is a pervasive threat in developing countries. A globaly available vaccine against HEV is currently lacking. Methods: We designed a multi-epitope vaccine based on protein ORF2 and ORF3 of HEV using immunoinformatics. Results: The vaccine comprised 23 nontoxic, nonallergenic, soluble peptides. The stability of the docked peptide vaccine-TLR3 complex was validated by molecular dynamic simulations. The induction of effective cellular and humoral immune responses by the multi-peptide vaccine was verified by simulated immunization. Discussion: These findings provide a foundation for future HEV vaccine studies.

PREDAC-CNN: predicting antigenic clusters of seasonal influenza A viruses with convolutional neural network.

Vaccination stands as the most effective and economical strategy for prevention and control of influenza. The primary target of neutralizing antibodies is the surface antigen hemagglutinin (HA). However, ongoing mutations in the HA sequence result in antigenic drift. The success of a vaccine is contingent on its antigenic congruence with circulating strains. Thus, predicting antigenic variants and deducing antigenic clusters of influenza viruses are pivotal for recommendation of vaccine strains. The antigenicity of influenza A viruses is determined by the interplay of amino acids in the HA1 sequence. In this study, we exploit the ability of convolutional neural networks (CNNs) to extract spatial feature representations in the convolutional layers, which can discern interactions between amino acid sites. We introduce PREDAC-CNN, a model designed to track antigenic evolution of seasonal influenza A viruses. Accessible at http://predac-cnn.cloudna.cn, PREDAC-CNN formulates a spatially oriented representation of the HA1 sequence, optimized for the convolutional framework. It effectively probes interactions among amino acid sites in the HA1 sequence. Also, PREDAC-CNN focuses exclusively on physicochemical attributes crucial for the antigenicity of influenza viruses, thereby eliminating unnecessary amino acid embeddings. Together, PREDAC-CNN is adept at capturing interactions of amino acid sites within the HA1 sequence and examining the collective impact of point mutations on antigenic variation. Through 5-fold cross-validation and retrospective testing, PREDAC-CNN has shown superior performance in predicting antigenic variants compared to its counterparts. Additionally, PREDAC-CNN has been instrumental in identifying predominant antigenic clusters for A/H3N2 (1968-2023) and A/H1N1 (1977-2023) viruses, significantly aiding in vaccine strain recommendation.

Improving Kidney Outcomes in Patients With Nondiabetic Chronic Kidney Disease Through an Artificial Intelligence-Based Health Coaching Mobile App: Retrospective Cohort Study.

BACKGROUND: Chronic kidney disease (CKD) is a global health burden. However, the efficacy of different modes of eHealth care in facilitating self-management for patients with CKD is unclear. OBJECTIVE: The aim of this study was to evaluate the effectiveness of a mobile app-based intelligent care system in improving the kidney outcomes of patients with CKD. METHODS: Our study was a retrospective analysis based on the KidneyOnline intelligent system developed in China. Patients with CKD but not dependent on dialysis who registered on the KidneyOnline app between January 2017 and January 2021 were screened. Patients in the the KidneyOnline intelligent system group and those in the conventional care group were 1:1 matched according to their baseline characteristics. The intervention group received center-based follow-up combined with the KidneyOnline intelligent patient care system, which was a nurse-led, patient-oriented collaborative management system. Health-related data uploaded by the patients were integrated using deep learning optical character recognition (OCR). Artificial intelligence (AI)-generated personalized recipes, lifestyle intervention suggestions, early warnings, real-time questions and answers, and personalized follow-up plans were also provided. Patients in the conventional group could get professional suggestions from the nephrologists through regular clinical visits, but they did not have access to the service provided by AI and the health coach team. Patients were followed for at least 3 months after recruitment or until death or start of renal replacement therapy. RESULTS: A total of 2060 eligible patients who registered on the KidneyOnline app from 2017 to 2021 were enrolled for the analysis. Of those, 902 (43.8%) patients were assessed for survival analysis after propensity score matching, with 451(50%) patients in the KidneyOnline intelligent patient care system group and 451(50%) patients in the conventional care group. After a mean follow-up period of 15.8 (SD 9.5) months, the primary composite kidney outcome occurred in 28 (6%) participants in the KidneyOnline intelligent patient care system group and 32 (7%) in the conventional care group, with a hazard ratio of 0.391 (95% CI 0.231-0.660; P<.001). Subgroup survival analysis demonstrated that the KidneyOnline care system significantly reduced the risk of composite kidney outcome, irrespective of age, sex, baseline estimated glomerular filtration rate (eGFR), and proteinuria. In addition, the mean arterial pressure (MAP) significantly decreased from 88.9 (SD 10.5) mmHg at baseline to 85.6 (SD 7.9) mmHg at 6 months (P<.001) in the KidneyOnline intelligent patient care system group and from 89.3 (SD 11.1) mmHg to 87.5 (SD 8.2) mmHg (P=.002) in the conventional CKD care group. CONCLUSIONS: The utilization of the KidneyOnline intelligent care system was associated with reduced risk of unfavorable kidney outcomes in nondiabetic patients with CKD.

The imbalance of circulating monocyte subgroups with a higher proportion of the CD14+CD16+CD163+ phenotype in patients with preeclampsia.

BACKGROUND: Preeclampsia is a major cause of increased maternal and fetal morbidity and mortality, which is closely related to the abnormal maternal immune response. The skew of decidual macrophage polarization toward M1 phenotype has been proved to promote the pathogenesis of preeclampsia. However, it's not easy to monitor the change of decidual macrophage subtypes. The current study aims to examine the distribution of different circulating monocyte subtypes and analyze whether certain monocyte subtypes act as potential clinical indicators for preeclampsia. METHODS: A total of 50 pregnant women [mild preeclampsia (n = 20); severe preeclampsia (n = 15); healthy pregnancy (n = 15)] and 15 healthy donors were included in the study. Medical information such as BMI, blood pressure, ALT, creatinine, thrombocyte, etc., were recorded. The frequency of different monocyte subtypes in venous blood were measured by flow cytometry. Serum level of IL-6 was detected using Roche-Hitachi cobas 8000. Serum concentration of inflammatory cytokines (IL-1ß, IL-4, IL-10 and TNF-α) were measured by ELISA. RESULTS: A circulating monocyte subset with both M1 and M2 markers (CD14+CD16+CD163+) was found to occupy an obvious higher proportion in the preeclampsia group than in the normal pregnancy group. The ratio of CD206+/CD206- M2-like monocytes was also increased in the preeclampsia group, and meanwhile, it had statistic difference between the mild- and the severe-preeclampsia group. Furthermore, the serum levels of IL-1ß and TNF-α were positively correlated with the frequency of CD14+CD16+CD163+ intermediate monocytes in the preeclampsia group. CONCLUSIONS: The increased proportion of CD14+C16+CD163+ circulating monocytes and the high ratio of CD206+/CD206- M2-like monocytes may act as potential clinical indicators for preeclampsia, with the superiority of convenience and dynamic monitoring.

Exploring Tumor Immune Microenvironment and Its Associations With Molecular Characteristics in Melanoma.

Background: The tumor microenvironment (TME), which involves infiltration of multiple immune cells into the tumor tissues, plays an essential role in clinical benefit to therapy. The chemokines and their receptors influence migration and functions of both tumor and immune cells. Also, molecular characteristics are associated with the efficacy of melanoma therapy. However, there lacked exploration of immune characteristics and the association with molecular characteristics. Methods: We collected the currently available 569 melanoma samples that had both the genomic and transcriptional data from TCGA and SRA databases. We first identified TME subtypes based on the developed immune signatures, and then divided the samples into two immune cohorts based on the immune score. Next, we estimated the compositions of the immune cells of the two cohorts, and performed differential expression genes (DEGs) and functional enrichments. In addition, we investigated the interactions of chemokines and their receptors under immune cells. Finally, we explored the genomic characteristics under different immune subtypes. Results: TME type D had a better prognosis among the four subtypes. The high-immunity cohort had significantly high 16 immune cells. The 63 upregulated and 384 downregulated genes in the high-immunity cohort were enriched in immune-related biological processes, and keratin, pigmentation and epithelial cells, respectively. The correlations of chemokines and their receptors with immune cell infiltration, such as CCR5-CCL4/CCL5 and CXCR3-CXCL9/CXCL10/CXCL11/CXCL13 axis, showed that the recruitments of 11 immune cells, such as CD4T cells and CD8T cells, were modulated by chemokines and their receptors. The proportions of the four TME subtypes in each molecular subtype were comparable. The two driver genes, CDKN2A and PRB2, had significantly different MAFs between the high-immunity and low-immunity. Conclusion: We dissected the characteristics of immune infiltration, the interactions of chemokines and their receptors under immune cells, and the correlation of molecular and immune characteristics. Our work will enable the reasonable selection of anti-melanoma treatments and accelerate the development of new therapeutic strategies for melanoma.

Adsorption and reduction from modified polypyrrole enhance electrokinetic remediation of hexavalent chromium-contaminated soil.

Toxic metal pollutant Cr(VI) in the environment will pose a severe threat to animal and human health. In this work, Fe3O4@PPy, Arg@PPy, and Arg/Fe3O4@PPy were prepared to enhance adsorption of Cr(VI) by doping Fe3O4 nanoparticles and amino radicals into the original PPy structure. Their characteristics were investigated by FTIR, SEM, EDS, BET analysis, and batch adsorption experiments. And they were used as permeable reaction barriers (PRB) to combine with electrokinetic remediation (EKR) to remediate Cr-contaminated soil. Adsorption experiment results showed that the maximum adsorption capacities of PPy, Fe3O4@PPy, Arg@PPy, and Arg/Fe3O4@PPy for Cr(VI) were 60.43 mg/g, 67.12 mg/g, 159.86 mg/g, and 141.50 mg/g, respectively. They all followed the kinetic pseudo-second-order model and the Langmuir isothermal model with a monolayer adsorption behavior. In the EKR/PRB system, the presence of Fe3O4@PPy, Arg@PPy, and Arg/Fe3O4@PPy obtained the higher Cr(VI) removal efficiency near the anode than that of the PPy, increasing by 74.60%, 26.04%, and 68.64%, respectively. A strong electrostatic attraction between anion contaminants and protonated modified PPy and a reduction from Cr(VI) to Cr(III) appeared in the EKR remediation process under acid conditions. This study opened up a prospect for applying modified PPy composites to treat toxic metal-contaminated soil.

Diagnosis of gastric lesions through a deep convolutional neural network.

BACKGROUND AND AIMS: A deep convolutional neural network (CNN) was used to achieve fast and accurate artificial intelligence (AI)-assisted diagnosis of early gastric cancer (GC) and other gastric lesions based on endoscopic images. METHODS: A CNN-based diagnostic system based on a ResNet34 residual network structure and a DeepLabv3 structure was constructed and trained using 21,217 gastroendoscopic images of five gastric conditions, peptic ulcer (PU), early gastric cancer (EGC) and high-grade intraepithelial neoplasia (HGIN), advanced gastric cancer (AGC), gastric submucosal tumors (SMTs), and normal gastric mucosa without lesions. The trained CNN was evaluated using a test dataset of 1091 images. The accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of the CNN were calculated. The CNN diagnosis was compared with those of 10 endoscopists with over 8 years of experience in endoscopic diagnosis. RESULTS: The diagnostic specificity and PPV of the CNN were higher than that of the endoscopists for the EGC and HGIN images (specificity: 91.2% vs. 86.7%, by 4.5%, 95% CI 2.8-7.2%; PPV: 55.4% vs. 41.7%, by 13.7%, 95% CI 11.2-16.8%) and the diagnostic accuracy of the CNN was close to those of the endoscopists for the lesion-free, EGC and HGIN, PU, AGC, and SMTs images. The CNN had image recognition time of 42 s for all the test set images. CONCLUSION: The constructed CNN system could be used as a rapid auxiliary diagnostic instrument to detect EGC and HGIN, as well as other gastric lesions, to reduce the workload of endoscopists.

Synthesis and biological evaluation of a series of 2-(((5-akly/aryl-1H-pyrazol-3-yl)methyl)thio)-5-alkyl-6-(cyclohexylmethyl)-pyrimidin-4(3H)-ones as potential HIV-1 inhibitors.

A series of 2-(((5-akly/aryl-1H-pyrazol-3-yl)methyl)thio)-5-alkyl-6-(cyclohexylmethyl)-pyrimidin-4(3H)-ones were synthesized and their anti-HIV-1 activities were evaluated. Most of these compounds were highly active against wild-type (WT) HIV-1 strain (IIIB) with EC50 values in the range of 0.0038-0.4759 µmol/L. Among those compounds, I-11 had an EC50 value of 3.8 nmol/L and SI (selectivity index) of up to 25,468 indicating excellent activity against WT HIV-1. In vitro anti-HIV-1 activity and resistance profile studies suggested that compounds I-11 and I-12 displayed potential anti-HIV-1 activity against laboratory adapted strains and primary isolated strains including different subtypes and tropism strains (EC50s range from 4.3 to 63.6 nmol/L and 18.9-219.3 nmol/L, respectively). On the other hand, it was observed that those two compounds were less effective with EC50 values of 2.77 and 4.87 µmol/L for HIV-1A17 (K103N + Y181C). The activity against reverse transcriptase (RT) was also evaluated for those compounds. Both I-11 and I-12 obtained sub-micromolar IC50 values showing their potential in RT inhibition. The pharmacokinetics examination in rats indicated that compound I-11 has acceptable pharmacokinetic properties and bioavailability. Preliminary structure-activity relationships and molecular modeling studies were also discussed.

Genome Composition and Divergence of the Novel Coronavirus (2019-nCoV) Originating in China.

An in-depth annotation of the newly discovered coronavirus (2019-nCoV) genome has revealed differences between 2019-nCoV and severe acute respiratory syndrome (SARS) or SARS-like coronaviruses. A systematic comparison identified 380 amino acid substitutions between these coronaviruses, which may have caused functional and pathogenic divergence of 2019-nCoV.

The Status of Epstein-Barr Virus Infection in Intestinal Mucosa of Chinese Patients with Inflammatory Bowel Disease.

AIMS: This cross-sectional study is to investigate the presence of Epstein-Barr virus (EBV) in colonic mucosa of inflammatory bowel disease (IBD) patients and its correlation with the clinical disease activities and therapeutic regimens. METHODS: Subjects undergoing colonoscopy for screening of polyps were recruited as control. EBV DNA load was analyzed by means of quantitative real-time polymerase chain reaction and EBV-encoded RNAs were tested by in situ hybridization in intestinal mucosa of IBD patients. EBV infection was defined as positive with either method. Clinical disease activity was assessed using the Mayo Clinic Score for ulcerative colitis and Crohn's disease activity index for CD. RESULTS: EBV was detectable in 33 out of 99 IBD patients (33.3%). In controls, EBV prevalence was 7.5% (3/40). We found a significant correlation between EBV prevalence and clinical disease activities (mild [10.71%, 3/28] versus moderate [32.73%, 18/55], severe [75.00%, n = 12/16], p < 0.001). However, no significant difference was found in EBV prevalence between patients who received immunosuppressive therapy and those who did not. CONCLUSIONS: EBV infection is common in colonic mucosa of IBD patients. There is a significant correlation between EBV infection and clinical disease activities of IBD. However, prospective studies are still needed to explore the exact role of EBV in IBD.

Toxoplasmosis complicating lung cancer: a case report.

Toxoplasmosis complicating lung cancer has been described only rarely. Here, we report a case of acute Toxoplasma gondii infection in a patient with squamous lung cancer. A 64-year-old woman was admitted to our hospital with a history of cough of 6 months' duration and chest pain of 1 week's duration. Further examination revealed multiple swollen lymph nodes, palpable on the top of the right collarbone and without tenderness. The chest X-ray, bronchoscopy, and computed tomography scan confirmed squamous carcinoma of the right lung. The Wright-stained bronchoalveolar-lavage fluid cytology diagnosis was positive for T. gondii and tachyzoites were detected. All of them were of free type (ectocytic), without intracellular parasites. Serological examination revealed that the anti-T. gondii immunoglobulin (Ig) M and IgG antibodies were positive. Unfortunately the patient did not continue treatment and was lost to follow-up. Toxoplasmosis is a life-threatening opportunistic infection in patients with lung cancer. Prompt recognition of T. gondii infection among cancer patients with subsequent targeted treatment of toxoplasmosis could help alleviate symptoms and improve survival.

Utility of the Asia-Pacific colorectal screening scoring system and the presence of metabolic syndrome components in screening for sporadic colorectal cancer.

AIM: To determine the utility of the Asia-Pacific colorectal screening (APCS) scoring system and metabolic syndrome components in individual screening for sporadic colorectal cancer. METHODS: The subjects were patients admitted to the Peking University People's Hospital for colonoscopy between October 2012 and July 2013. Clinical information, including patient willingness to undergo colonoscopy, medical history, endoscopic findings, histology, and other information, was collected, and the patients were grouped according to APCS scores and the presence of metabolic syndrome components. Colorectal tumor detection rates were compared between the groups. RESULTS: A total of 219 patients were included in the study, 108 were male and 111 were female, resulting in a male-to-female ratio of 1:1.03. The average age of the patients was 56.8 ± 13.7 years. According to APCS scores, 88 (40.2%) patients were included in the average-risk (AR) group, 113 (51.6%) patients were included in the moderate-risk (MR) group, and 18 (8.2%) patients were included in the high-risk (HR) group. Colorectal tumors were detected in 69 (31.5%) subjects, and the detection rates in the AR, MR, and HR groups were 15.9%, 36.3%, and 77.8%, respectively. The difference in the detection rates between the three groups was statistically significant (P < 0.01). The combined detection rate of colorectal tumors in the APCS MR and HR groups was 42.0%. However, patients in the MR and HR groups who presented with metabolic syndrome components, in particular obesity, exhibited a significantly higher colorectal tumor detection rate (59.5%) than did those without these components (19.2%, P < 0.01) and those who underwent colonoscopy because of doctor's recommendation (36.5%, P < 0.01). CONCLUSION: The APCS scoring system can be used in individual screening for sporadic colorectal cancer. The combined use of APCS scores and the metabolic syndrome components, in particular obesity, will significantly improve the efficacy of individual colorectal cancer screening.