Artificial intelligence (AI) for science (AI4S) technology, the AI technology for scientific research, has shown tremendous potential and influence in the field of healthcare, redefining the research paradigm of medical science under the guidance of computational medicine. We reviewed the main technological trends of AI4S in reshaping healthcare paradigm: knowledge-driven AI, leveraging extensive literature mining and data integration, emerges an important tool for understanding disease mechanisms and facilitating novel drug development; data-driven AI, delving into clinical and human-related omics data, unveils individual variances and disease mechanisms, and further establishes patient-centric digital twins to guide drug development and personalized medicine. Meanwhile, based on authentic patient digital twin models, adaptable strategies are employed to further propel the development of "e-drugs" that mimic the authentic mechanisms. These digital twins of drugs are evaluated for drug efficacy and safety through large-scale cloud-based virtual clinical trials, and followed by rationally designed real-world clinical trials, thus notably reducing drug development costs and enhancing success rates. Despite encountering challenges such as data scale, quality control, model interpretability, the transition from science insights to engineering solutions, and regulatory hurdles, we anticipate the integration of AI4S technology to revolutionize drug development and clinical practices. This transformation brings revolutionary changes to the medical field, offering novel opportunities and challenges for the development of medical science, and more importantly, providing necessary but personalized healthcare solutions for humankind.
Objective To evaluate the clinical efficacy and safety of domestic cefepime in the treatment of acute bacterial lower respiratory tract infection. Methods A randomized, single-blind, controlled clinical trial was performed. The positive control was imported cefepime. The dosages of cefepime were 1g for moderate infection and 2g for severe infection, twice a day intravenously. The duration of the treatment was 7-10 days. Results Thirty-one patients were enrolled in the trial, of whom 30 were evaluable (15 in the triagroup and 15 in the control group). No significant differences were observed between the trial group and the control group with respect to the cure rate (40% vs. 27%), the effective rate (80% vs. 87%), the bacterial clearance rate (92% vs. 100%), and the incidence of adverse drug reactions (12.5% vs. 13%) (Pgt;0.05). Conclusion Domestic cefepime injection is effective and safe in the treatment of acute bacterial lower respiratory tract infection.
Objective To identify and investigate the quality of randomized controlled trials (RCTs) of traditional Chinese medicine (TCM) in 11 non-key Chinese medical journals so as to learn about the current status and problems. Methods Eleven non-key medical journals of TCM from 1995 to 2000 were hand searched to identify the RCT and controlled clinical trials (CCTs). Each identified RCT or CCT was page by page verified by handsearchers based on the criteria developed by the Cochrane Handbook; the RCTs’ design, randomization method description, blind, baseline comparison, inclusion and exclusion criteria, diagnostic criteria,criteria for theraputic effectiveness, sample size, statistical method，described outcome, side effects, and follow up etc. were analyzed. Results In the related journals from 1995 to 2000, a total of 66 volumes and 390 issues were checked. As a result, 22 739 clinical studies were identified, of which 1 416 RCTs, only 24 (1.69%) were done with double blinding. There were 141 CCTs from 1995 to 2000, the total number of RCT increased from 95 to 1 416 and most of studies were on digestives diseases. Most of these studies had no detailed randomization method description, only 38 (2.68%) studies provided a methodology description. In addition, 1 220 (86.16% ) described outcome index, 1 203 (84.96%) used statistical method，934 (65.96%) had baseline comparison，828 (58.47%) described diagnostic criteria, 197 (13.91%) had inclusion and exclusion criteria，finally only 89 (6.29%) reported side effects. Conclusions Although the number of RCT has increased in the 11 non-key medical journals of TCM in the past six years, the quality of these RCTs needs to be improved.
Population pharmacokinetics is a research technique based on computer simulation and data analysis, and it has been employed to investigate the dynamic behavior of drug metabolism in different populations. This approach could address practical challenges such as prolonged clinical trial durations, high costs, and increased difficulty in traditional clinical trials. By comprehensively analyzing differences in the internal drug metabolism processes across populations with varying physiological and pathological conditions, population pharmacokinetics has emerged as an effective method to optimize drug development and clinical applications. This article provides a preliminary overview of the essence of population pharmacokinetics, its application in clinical trials, and potential future trends. We hope to serve as a reference and guidance for the application of new technologies and methods in clinical trials.
Virtual clinical trials are clinical trials conducted through computer simulation technology, which breaks through the limitations of traditional clinical trials and has the advantages of saving time, reducing costs, and reducing the risk of human trials. With the application of new computer technologies such as population pharmacokinetics, physiologically-based pharmacokinetics, quantitative systems pharmacology, and artificial intelligence, the field of virtual clinical trials in healthcare has become an important development direction. This article will give a preliminary review of the connotation, methods and future development trends of virtual clinical trials, aiming to provide reference for the application of new technologies and methods in clinical trials.
Objective To explore the feasibility of breast cancer patients in China with 1–2 positive sentinel lymph nodes (SLN) to avoid axillary lymph node dissection (ALND). Methods A total of 328 patients who received sentinel lymph node biopsy (SLNB) in our hospital from 2010 to 2016 were collected retrospectively, and patients met the criteria of Z0011 clinical trials (which required no acceptance of neoadjuvant therapy, clinical tumor size was in T1/T2 stage, two or less positive SLNs were detected, received breast-conservation surgery, acceptance of whole breast radiotherapy after surgery and neoadjuvant systemic treatment) were enrolled to breast-conservation group. Patients met the criteria of Z0011 clinical trials, excepting the surgery (received non-breast-conservation surgery), were enrolled to non- breast-conservation group. Comparison of clinicopathological features between the breast-conservation group/non-breast-conservation group and the Z0011 ALND group was performed. Results Among the 328 patients, only 29 patients (8.8%) completely correspond with the results of Z0011 clinical trials. There was no statistical significance between the breast-conservation group and the Z0011 ALND group in the age, clinical T stage, expression of estrogen (ER), expression of progesterone (PR), pathological type, histological grade, number of positive lymph nodes, and incidence of non-sentinel node metastasis (P>0.05). A total of 81 patients were included in the non-breast-conservation group. It showed no statistical significance between the non-breast-conservation group and the Z0011 ALND group in expressions of ER and PR, and histological grade (P>0.05), while there was statistically significant difference in age, clinical T stage, pathological type,number of positive lymph nodes, and incidence of non-sentinel node metastasis (P<0.05). Patients in the non-breast-conservation group showed a lower age, higher percentage of lobular carcinoma and T2 stage, more positive lymph nodes, and high incidence of non-sentinel node metastasis. Conclusion It’s feasible for Z0011 clinical trials results to be used in the clinical practice of our country, but the actual situation of breast conservation in our country may lead to low adaptive population.
Objective To assess the efficacy and safety of Chinese medicinal herbs for asymptomatic hepatitis B virus(HBV) infection. Data Source The trials registers of the Cochrane Hepato-Biliary Group, the Cochrane Library and the Cochrane Complementary Medicine Field were searched in combination with MEDLINE, EMBASE, and handsearches of Chinese journals and conference proceedings. Data Selection Randomized clinical trials with 3 months follow-up comparing Chinese medicinal herbs versus placebo, no intervention, non-specific treatment, or interferon treatment for asymptomatic HBV carriers were included. No language and blinding limitations were applied. Data Extraction Data were extracted independently by two reviewers. The methodological quality of trials was assessed by the Jadad-scale plus allocation concealment. Results Three randomized clinical trials (307 patients) with low methodological quality following patients for three months or more after the end of treatment were included. Herbal compound Jianpi Wenshen recipe showed significant effects on clearance of HBV markers compared to interferon: relative risk 2.40 (95 % CI 1.01 to 5.72) for clearance of serum HBsAg, and 2.54 (1.13 to 5.70) for seroconversion of HBeAg to anti-HBe. Phyllanthus amarus and Astragalus membranaceus showed no significant antiviral effect compared with placebo. Analysis of pooling eight randomized clinical trials with less than three months follow-up did not show a significant benefit of Chinese medicinal herbs on viral markers. No serious adverse event was observed. Conclusions There is insufficient evidence for treatment of asymptomatic HBVcarriers using Chinese medicinal herbs due to the low quality of the trials. Further randomized, double blind, placebo-controlled trials are needed.
Clinical trial transparency, include clinical trial registration, unbiased reporting results and sharing individual participant data (IPD), is one of the most important revolutionary concepts following clinical epidemiology and evidence-based medicine in the medical field. Sharing IPD is a medical ethics issue reflected a new sense of worth and constructing new rules of clinical trials. Our viewpoint is that from the essential purpose of clinical research, IPD is a social public property. Sharing IPD is a one of the best ways for respecting the contributions of the participants, and one of the keys for changing face of clinical trials.
Since the outbreak of the coronavirus disease (COVID-19), more than 200 interventional clinical trials have been registered in Chinese Clinical Trial Registry (www.chictr.org.cn) and the US Clinical Trials Registry (www.clinicaltrials.gov), testing or going to test treatments of COVID-19 in China from January 23rd, 2020 to March 5th, 2020. This situation has drawn attentions from various sectors of society. This article summarizes the basic design features of 249 registered COVID-19 clinical trials in China, compares them with National Clinical Trials Network practices in the USA, and describes a concept of national clinical trials network as a strategy to enhance quality and efficiency of clinical research in cases like COVID-19 outbreak as well as other disease fields.
Objective To assess the effectiveness and safety of breviscapine on diabetic nephropathy. Methods All randomized or quasi-randomized controlled trials of breviscapine on diabetic nephropathy were performed. All of the clinical trials were searched from the Cochrane Controlled Trials Registered, Medline, Embase, National Knowledge Infrastructure Database, the Chinese Biological Medicine Database, the Chinese Science and Technology Journal Full-text and the references of all included trials. The selection of studies, assessment of methodological quality and data extraction were performed independently by two reviewers according to predefined inclusion and exclusion criteria. Results Thirty-three clinical trials including 2 322 patients of diabetic nephropathy met the inclusion criteria. But most included trials were of low quality and small sample. Until now, there were no clinical trials with multicentre, large sample and high quality. A “Funnel plot” showed asymmetry, which indicated possible publication bias and low quality in methodology. And publication bias showed that the trials with negative results might not be published. The results of meta-analysis indicated that: 1. Breviscapine showed more effects on the decrease of the 24-hour urinary albumin excretion rate (UAER), 24-hour urinary protein, serum creatinine (Scr), total cholesterol, triglyceride, plasma viscosity and fibrinogen. 2. Breviscapine showed less effect on the decrease of the 24-hour urinary protein when compared to angiotensin-converting enzyme inhibitor, it seemed as same effective as ACEI on decrease of 24-hour urinary albumin excretion rate (UAER), serum creatinine (Scr) and blood urea nitrogen (BUN); 3. Breviscapine showed more effect on the decrease of 24-hour urinary protein and fibrinogen when compared to other Chinese herbal medicine (Salvia miltiorrhiza); 4. Breviscapine showed less effect on decrease of the 24-hour urinary albumin excretion rate (UAER) when compeard to Prostaglandin E1. No significant adverse effects were reported. Conclusion Breviscapine shows some effects and relatively safe on diabetic nephropathy. However, the evidence is not b enough because of some of the low-quality trials and publications bias. Rigorous designs, randomized, double-blind, placebo-controlled trials of Breviscapine for diabetic nephropathy are needed to further assess the effect.