RESUMO
BACKGROUND: Given the high cost of endoscopy in gastric cancer (GC) screening, there is an urgent need to explore cost-effective methods for the large-scale prediction of precancerous lesions of gastric cancer (PLGC). We aim to construct a hierarchical artificial intelligence-based multimodal non-invasive method for pre-endoscopic risk screening, to provide tailored recommendations for endoscopy. METHODS: From December 2022 to December 2023, a large-scale screening study was conducted in Fujian, China. Based on traditional Chinese medicine theory, we simultaneously collected tongue images and inquiry information from 1034 participants, considering the potential of these data for PLGC screening. Then, we introduced inquiry information for the first time, forming a multimodality artificial intelligence model to integrate tongue images and inquiry information for pre-endoscopic screening. Moreover, we validated this approach in another independent external validation cohort, comprising 143 participants from the China-Japan Friendship Hospital. RESULTS: A multimodality artificial intelligence-assisted pre-endoscopic screening model based on tongue images and inquiry information (AITonguequiry) was constructed, adopting a hierarchical prediction strategy, achieving tailored endoscopic recommendations. Validation analysis revealed that the area under the curve (AUC) values of AITonguequiry were 0.74 for overall PLGC (95% confidence interval (CI) 0.71-0.76, p < 0.05) and 0.82 for high-risk PLGC (95% CI 0.82-0.83, p < 0.05), which were significantly and robustly better than those of the independent use of either tongue images or inquiry information alone. In addition, AITonguequiry has superior performance compared to existing PLGC screening methodologies, with the AUC value enhancing 45% in terms of PLGC screening (0.74 vs. 0.51, p < 0.05) and 52% in terms of high-risk PLGC screening (0.82 vs. 0.54, p < 0.05). In the independent external verification, the AUC values were 0.69 for PLGC and 0.76 for high-risk PLGC. CONCLUSION: Our AITonguequiry artificial intelligence model, for the first time, incorporates inquiry information and tongue images, leading to a higher precision and finer-grained pre-endoscopic screening of PLGC. This enhances patient screening efficiency and alleviates patient burden.
RESUMO
Background: Osteoking has been extensively used for the treatment of knee osteoarthritis (KOA). However, it is lack of high-quality evidence on the clinical efficacy of Osteoking against KOA and the comparison with that of nonsteroidal anti-inflammatory drugs (NSAIDs). Aims: To evaluate the efficacy and safety of Osteoking in treating KOA. Methods: In the current study, a total of 501 subjects were recruited from 20 medical centers, and were divided into the Osteoking treatment group (n = 428) and the NSAIDs treatment group (n = 73). The Propensity Score Matching method was used to balance baseline data of different groups. Then, the therapeutic effects of Osteoking and NSAIDs against KOA were evaluated using VAS score, WOMAC score, EQ-5D-3L and EQ-VAS, while the safety of the two treatment were both assessed based on dry mouth, dizziness, diarrhea, etc. Results: After 8 weeks of treatment, the Osteoking group was compared with the NSAIDs group, the VAS score [2.00 (1.00, 3.00) vs. 3.00 (2.00, 4.00)], WOMAC pain score [10.00 (8.00, 13.00) vs. 11.00 (8.00, 16.00) ], WOMAC physical function score [32.00 (23.00, 39.00) vs. 39.07 ± 16.45], WOMAC total score [44.00 (31.00, 55.00) vs. 53.31 ± 22.47) ], EQ-5D-3L score [0.91 (0.73, 0.91) vs. 0.73 (0.63, 0.83) ] and EQ-VAS score [80.00 (79.00, 90.00) vs. 80.00 (70.00, 84.00) ] were improved by the treatment of Osteoking for 8 weeks more effectively than that by the treatment of NSAIDs. After 8 weeks of treatment with Osteoking, the VAS scores of KOA patients with the treatment of Osteoking for 8 weeks were reduced from 6.00 (5.00, 7.00) to 2.00 (1.00, 3.00) (p < 0.05), which was better than those with the treatment of NSAIDs starting from 2 weeks during this clinical observation. Importantly, further subgroup analysis revealed that the treatment of Osteoking was more suitable for alleviating various clinical symptoms of KOA patients over 65 years old, with female, KL II-III grade and VAS 4-7 scores, while the clinical efficacy of NSAIDs was better in KOA patients under 65 years old and with VAS 8-10 scores. Of note, there were no differences in adverse events and adverse reactions between the treatment groups of the two drugs. Conclusion: Osteoking may exert a satisfying efficacy in relieving joint pain and improving life quality of KOA patients without any adverse reactions, especially for patients with KL II-III grades and VAS 4-7 scores. Clinical Trial Registration: https://www.chictr.org.cn/showproj.html?proj=55387, Identifier ChiCTR2000034475.
RESUMO
PURPOSE: Chronic musculoskeletal pain (CMP) is defined as persistent or recurrent pain that occurs in the joints, musculo-soft tissue, spine or bones for more than three months and is not completely curable. Although topical Chinese patent medicine (CPM) is the most extensively utilized medication in Asia and is widely used for pain management, its efficacy remains controversial. This article presents a systematic review of clinical studies on the therapeutic properties of topical CPM for CMP patients to better inform clinical decision-making and provide additional and safer treatment options for patients with CMP. METHOD: We performed a comprehensive search on PubMed, Cochrane Library, web of science and Chinese databases (CNKI and WanFang data) from 2010 to 2022. In all the studies, knee osteoarthritis, cervical spondylosis, low back pain, and periarthritis of shoulder met the International Pain Association definition of chronic musculoskeletal pain. We included only randomized controlled trials (RCTs) using topical CPM primarily for chronic musculoskeletal pain in adults. To determine the effect of topical CPM on clinical symptoms, we extracted the Visual Analog Scale (VAS, range 0-10) and the Western Ontario and McMaster Universities Arthritis Index pain scores (WOMAC pain, range 0-20), in which the lower the score, the better the results. We also accepted the comprehensive outcome criteria developed by the Chinese National Institute of Rheumatology as an endpoint (total effectiveness rate, range 0-100%, higher score = better outcome), which assesses the overall pain, physical function and wellness. Finally, trial sequential analysis of VAS pain score and total effectiveness rate was performed using TSA software. RESULTS: Twenty-six randomized controlled trials (n = 3180 participants) compared topical CPM with oral Nonsteroidal Anti-inflammatory Drugs (NSAIDs) (n = 15), topical NSAIDs (n = 9), physiotherapy (n = 5), exercise therapy (n = 4), and intra-articular Sodium hyaluronate injection (n = 2). Sixteen studies found that topical CPM was statistically significant in improving CMP pain (measured by VAS pain and Womac pain scores)(p < 0.05), and 12 studies found topical CPMs to be more clinically effective (assessed by ≥ 30% reduction in symptom severity) in treating patients with CMP (p < 0.05). Trial sequential analysis indicates that the current available evidence is robust, and further studies cannot reverse this result. In most of the studies, randomisation, allocation concealment and blinding were not sufficiently described, and no placebo-controlled trials were identified. CONCLUSION: Most studies showed superior analgesic effects of topical CPM over various control treatments, suggesting that topical CPM may be effective for CMP and is an additional, safe and reasonable treatment option. These reported benefits should be validated in higher-quality RCTs.
