The rapid development of artificial intelligence （AI） technology provides new opportunities for the modernisation of traditional Chinese medicine （TCM） diagnosis. By analysing the foundation， research progress and difficulties of the combination of AI and TCM diagnosis， it is concluded that AI has made remarkable development in intelligence-driven modernization of TCM tongue diagnosis， pulse diagnosis， listening and smelling diagnosis and text processing， and there are useful explorations in the field of constructing data-driven TCM diagnostic model and multidisciplinary integration of TCM diagnostic models. However， the current integration of AI technology in TCM diagnosis still faces many challenges， such as the scarcity and uneven quality of clinical data， the limited ability of AI algorithms to express TCM thinking model of syndrome differentiation and empirical knowledge， and the possible existence of ethical and privacy issues. By systematically sorting out the current research status and development direction of AI-empowered TCM diagnostics， it is proposed to promote the application of AI technology in TCM diagnostics in four aspects， namely， strengthening the construction of TCM big data and talent cultivation， encouraging cross-disciplinary cooperation， improving the legal and ethical framework， and promoting the popularity of the technology in primary care， so as to enhance the modernisation of TCM diagnostics.

This paper presents an automatic acquisition and analytic procedure of acupuncture manipulation based on optical navigation, aiming at solving the shortcomings of existing acquisition methods of acupuncture manipulation. An acquisition holder installed at the handle tail of filiform needle was designed to display the movement trajectory of the needle during acupuncture delivery by collecting the movement trajectory of holder. The 3-month old male Bama miniature pig was selected as the experimental subject, and 6 points, "Bojian" "Qiangfeng" "Housanli" "Xiaokua" "Huiyang" (BL35) and "Baihui" (GV20), were selected during acupuncture manipulation. The optical navigation system was used to collect the real-time data, and these data were per-processed and analyzed using mean filtering and Fourier transform. The acupuncture procedure was divided into 3 stages, inserting, lifting-thrusting, and twisting. The results showed that the accuracy was 96.3% at lifting-thrusting stage, and that was 100.0% at twisting stage. The decomposition effect of the entire procedure was satisfactory. This study provides a new approach to the quantitative analysis of acupuncture manipulation. In the future, it needs to further optimize the algorithm and expand the sample size so as to improve the accuracy of this analytic technique.
Acupuncture Therapy/methods* ; Male ; Animals ; Swine ; Acupuncture Points ; Humans ; Swine, Miniature ; Needles

Objective:To evaluate the value of ultrasound radiomics combined with machine learning for early diagnosis of seronegative Hashimoto’s thyroiditis (SN-HT) .Methods:This retrospective study included 164 patients from Liaoning Provincial People’s Hospital , Lixin County People’s Hospital, Linghai Dalinghe Hospital, Fengcheng Phoenix Hospital, who underwent thyroidectomy for solitary nodules with normal thyroid function between Nov. 2016 and Jan. 2024. Postoperative pathology confirmed Hashimoto’s thyroiditis (HT) in some cases, who were further categorized into antibody-positive and antibody-negative groups based on serum antibody status. Patients without Hashimoto’s thyroiditis served as the control group. A total of 298 ultrasound images were analyzed. Radiomics features were extracted from hypoechoic non-nodular areas within 0.5 cm surrounding the tumor. Two senior pathologists and two senior ultrasound physicians independently assessed lymphocytic infiltration, eosinophilic changes of follicular epithelium, and the proportion of hypoechoic areas in pathology and ultrasound images, respectively. A machine learning model, CCH-NET, was developed using linear regression and t-distributed stochastic neighbor embedding (t-SNE) techniques. The dataset was divided into a training set (80%) and a validation set (20%) to compare the diagnostic accuracy of CCH-NET with that of senior ultrasound physicians. Results:In internal validation, CCH-NET achieved a diagnostic accuracy of 88.89% for both antibody-positive and antibody-negative groups, significantly higher than the 66.67% accuracy of senior ultrasound physicians ( P<0.01). In external validation, CCH-NET achieved 75.00% and 66.67% accuracy for the two groups, compared to 50.00% by senior ultrasound physicians. For the control group, both methods achieved 93.33% accuracy. The AUC of CCH-NET was 0.848, outperforming senior ultrasound physicians (0.681) ,demonstrating superior diagnostic performance. Conclusion:The radiomics-based CCH-NET model, using non-nodular hypoechoic areas as a specific indicator, can accurately identify early SN-HT in euthyroid patients. It significantly outperforms senior ultrasound physicians, improving diagnostic accuracy and reducing missed diagnoses.

Objective To evaluate the value of imaging quantification parameters in artificial intelligence (AI) assisted diagnosis systems in clinical decision-making for lung nodules≤2 cm and the diagnostic efficacy of AI. Methods Lung nodule patients admitted to Affiliated Zhongshan Hospital of Dalian University from 2020 to 2023 were included. Imaging parameters of lung nodules were extracted using AI assisted diagnosis systems. Multifactor analysis was used to screen predictors for distinguishing benign and malignant nodules and high-risk predictors for recurrent invasive adenocarcinoma, and a diagnostic model was established and its performance evaluated. The diagnostic efficacy of the AI system was judged according to pathological results. Results A total of 594 patients with lung nodules were included, including 202 males and 392 females, with an average age of (58.75±11.55) years. Volume, average CT value, and 3D maximum diameter of non-solid nodules were independent predictors of malignant nodules, with thresholds of 287.4 mm3, −491 HU, and 12.0 mm, respectively. The area under the curve (AUC) for diagnostic efficacy was ranked from high to low as combined model (0.802), volume (0.783), average CT value (0.749), and 3D maximum diameter (0.714). The average CT value and 3D long diameter of solid nodules were independent predictors of malignant nodules, with thresholds of −81 HU and 17.5 mm, respectively, and AUC values of 0.874 and 0.686, respectively, with the combined prediction AUC of 0.957. The mass of cystic nodules was an independent predictor of malignancy when the mass>180.7 mg. Independent predictors of high recurrence risk of invasive adenocarcinoma in non-solid nodules were consolidation-tumor ratio (CTR), average CT value, 3D long diameter, and volume, with thresholds of 0.14, −386 HU, 15.6 mm, and 1018.9 mm3, respectively, and diagnostic efficacy was ranked from high to low as combined model (0.788), 3D long diameter (0.735), volume (0.725), average CT value (0.720), and CTR (0.697). The accuracy of AI in predicting benign and malignant target nodules was 87.4%, with positive predictive value of 96.6% and negative predictive value of 58.9%. Conclusion In clinical decision-making for lung nodules ≤2 cm, AI assisted diagnosis systems have high application value.

Objective To investigate the short-term efficacy of the retrograde semi-retrieval technique(RESET)in the treatment of patients with acute intracranial large vessel occlusion.Methods This retrospective study involved 286 patients with acute intracranial large vessel occlusion who underwent mechanical thrombectomy using RESET at Tianjin Huanhu Hospital from November 2017 to March 2019.The patients were divided into two groups based on the presence or absence of intracranial atherosclerotic stenosis(ICAS):ICAS group(n=186,65％)and non-ICAS group(n=100,35％).Baseline characteristics,procedural outcomes,and 90-day modified Rankin Scale(mRS)scores were compared between the two groups.Results The two groups did not significantly differ in baseline characteristics,including age,gender,past medical history,on-admission National Institutes of Health Stroke Scale(NIHSS)score,and Alberta Stroke Program Early CT(ASPECT)score(all P＞0.05).Successful vascular recanalization was achieved in 272 patients(95.1％),with 209 patients(73.1％)achieving complete recanalization with a single thrombectomy attempt.Rescue therapy was required in 33 patients(11.5％).Two patients in the ICAS group died due to postoperative symptomatic intracranial hemorrhage,and one patient in the non-ICAS group died due to postoperative multiple organ failure.Compared with the non-ICAS group,the ICAS group had a significantly longer puncture-to-recanalization time[141.36(124.11,156.53)min vs.65.17(53.92,83.25)min,P＜0.001]but a significantly smaller number of thrombectomy attempts[1.00(1.00,1.00)vs.1.00(1.00,2.00),P=0.002].However,there were no significant differences between the two groups in terms of final recanalization rate,complete recanalization rate with a single thrombectomy attempt,distal embolism or embolization of new territory,symptomatic intracranial hemorrhage,perioperative death,or 90-day mRS score(all P＞0.05).Conclusion RESET demonstrates satisfactory short-term efficacy in the treatment of acute intracranial large vessel occlusion.The number of thrombectomy attempts required for complete recanalization is significantly lower in the ICAS group than in the non-ICAS group,suggesting that RESET is particularly suitable for patients with ICAS.

Objective:To systematically analyze the incidence and influencing factors of frailty in elderly patients with hematologic malignancies.Methods:Research on frailty in elderly patients with hematologic malignancies was retrieved from Chinese and English databases such as China National Knowledge Infrastructure, Wanfang Data, PubMed, and Web of Science. The search period was from database establishment to August 23, 2024. Two researchers screened the included studies, conducted quality assessment, and extracted data. Meta-analysis was conducted using Stata 18 and RevMan 5.4.Results:A total of seven studies were included, encompassing 19 076 elderly hematologic malignancy patients, with a frailty incidence of 59% [95% CI (0.48, 0.69) ]. Meta-analysis revealed that age [ MD=4.31, 95% CI (3.67, 4.96) ], gender [ OR=0.88, 95% CI (0.83, 0.93) ], alcohol consumption [ OR=1.67, 95% CI (1.15, 2.44) ], self-care ability [ MD=-1.79, 95% CI (-3.17, -0.41) ], anemia [ OR=6.67, 95% CI (2.94, 15.14) ], infection [ OR=1.81, 95% CI (1.16, 2.84) ], and neuropathy [ OR=2.52, 95% CI (1.38, 4.61) ] were the influencing factors of frailty in elderly patients with hematologic malignancies. Conclusions:The incidence of frailty is high in elderly patients with hematologic malignancies. Elderly patients with hematologic malignancies who are older, female, consume alcohol, have low self-care ability, anemia, infections, and neuropathy are prone to frailty. Healthcare providers can conduct early screening and intervention for high-risk populations of frailty based on risk factors to improve the quality of life for elderly hematologic malignancy patients.

Objective:To evaluate the association between heatwaves and fall-related mortality.Methods:A total of 61 421 fall-related mortality from 2013 to 2022 in 7 provinces of China were included in a time-stratified case-crossover design, with daily meteorological data derived from the fifth generation European Reanalysis dataset produced by the European Centre for Medium-Range Weather Forecasts. Conditional logistic regression chimeric distributed lag nonlinear model was used to analyze the association between heatwaves and fall-related mortality and stratified analysis was conducted according to gender and age.Results:Heatwaves were associated with an increased risk of fall-related morality. The risk of fall-related mortality during heatwaves was higher than during non-heatwave periods ( OR=1.11, 95% CI: 1.05-1.18). The attributable fraction of fall-related motality due to heatwaves was 10.25% (95% CI: 4.49%-15.36%). For each 1 ℃ increase above the heatwave threshold, the risk of fall-related mortality increased by 34% ( OR=1.34, 95% CI: 1.02-1.76). The effect of heatwave duration on fall-related mortality was not statistically significant. Stratified analyses indicated that women experienced a higher risk of fall-related mortality during heatwaves ( OR=1.13, 95% CI: 1.04-1.22) compared to man ( OR=1.10, 95% CI: 1.04-1.17). Conclusions:Heatwave increases the risk of fall-related mortality, and the intensity of heatwaves modify this risk. Women are vulnerable populations.

Objective:To evaluate the impact of short-term exposure to daytime heatwaves, nighttime heatwaves, and compound heatwaves on the risk of road traffic mortality and calculate the attributable mortality burden.Methods:This study collected road traffic mortality data from the Disease Surveillance System in Guangdong, Hunan, Zhejiang, Yunnan, and Jilin Provinces from 2013 to 2018. A time-stratified case-crossover design was used in this study, with the death date for each case serving as the case day. Control days were selected from the same year, month, and day of the week as the case day. A conditional logistic regression model was employed to estimate the cumulative associations of short-term exposure to daytime heatwaves, nighttime heatwaves, and compound heatwaves on the risk of road traffic mortality (lag 0-1 day) and to calculate the attributable fractions (AF).Results:Compared to non-heatwave days, the excess risk ( ER) of road traffic mortality on daytime heatwave days, nighttime heatwave days, and compound heatwave days was 5.3% (95% CI: 0.5%-10.2%), 4.9% (95% CI: 0.5%-9.4%) and 7.5% (95% CI: 2.3%- 12.9%), with corresponding AF of 5.0% (95% CI: 0.5%-9.3%), 4.7% (95% CI: 0.5%-8.6%), and 6.9% (95% CI: 2.3%-11.4%), respectively. Stratified analysis showed that the risk of traffic mortalities caused by daytime heatwaves was higher in females ( ER=15.7%, 95% CI: 5.8%-26.5%) than in males ( ER=1.8%, 95% CI: -3.6%-7.4%). Elderly individuals over 64 years old ( ER=10.9%, 95% CI: 0.3%- 22.6%) had a higher risk of road traffic mortalities from compound heatwaves than those under 45 years old ( ER=2.6%, 95% CI: -5.4%-11.2%). The risk of road traffic injury mortality from motor vehicle accidents caused by compound heatwaves ( ER=16.6%, 95% CI:2.4%-32.7%) was higher than that from non-motor vehicle accidents ( ER=5.7%, 95% CI:0.1%-11.5%). Conclusions:Short-term exposure to daytime heatwaves, nighttime heatwaves, and compound heatwaves was associated with an increased risk of road traffic mortality, with the strongest association observed for compound heatwaves. The mortality burden attributable to compound heatwaves was higher than that for daytime and nighttime heatwaves. Heatwaves were more significantly associated with road traffic mortality risk among females, elderly individuals over 64 years old, and motor vehicle accidents.

Objective:To explore the risk fall death associated with compound hot extremes.Methods:This study collected data on fall deaths in Guangdong, Hunan, and Zhejiang Provinces from 2013 to 2018 and matched their exposure to meteorological data. Based on a time-stratified case-crossover design, a conditional logistic regression model embedded with a cross-basis function of the distributed lag nonlinear model was applied to estimate the risk of fall to death due to compound hot extremes.Results:Compared with regular days, compound hot extremes significantly increased the risk of death from falls ( OR=1.19, 95% CI: 1.09-1.30), and women ( OR=1.27, 95% CI: 1.11-1.45) and the elderly age 65 and above ( OR=1.24, 95% CI: 1.12-1.39) were more sensitive to compound hot extremes. The maximum duration of compound hot extremes was 7 days, and the maximum intensity was 6.2 ℃, and the duration and intensity were proportional to the risk of death from falls. The risk of death from falls increased by 12% ( OR=1.12, 95% CI: 1.06-1.18) each day, increasing in duration after linearization. The risk of death from falls increased by 16% ( OR=1.16, 95% CI: 1.10-1.22) for each 1 ℃ increase in linearized intensity. Conclusion:Compound hot extremes increase the risk of death cases from falls.

Objective:To assess the association between temperature and risk of animal injury, and identifying vulnerable populations.Methods:Based on a time-stratified case-crossover design, the number of animal injuries monitored in hospitals of Guangdong Provincial Injury Surveillance System in 2011 and 2015-2016 was included, and the daily meteorological data were derived from the fifth generation of European ReAnalysis-Land, which was produced by the European Centre for Medium-Range Weather Forecasts. Conditional logistic regression combined with a distributed lagged nonlinear model was applied to analyze the association of temperature and animal-specific injuries. We also conducted stratified analysis by region, sex, age, occupation, and location of injury occurrence.Results:There was an almost linear relationship between temperature and the occurrence of animal injury. The excess risk ( ER) of animal injury was 2.65% (95% CI: 2.27%-3.04%) for a 1 ℃ rise in temperature with much higher risk of occurrence ( ER=9.34%, 95% CI: 7.57%-11.13%) for non-mammalian injury than that for mammalian injuries ( ER=2.30%, 95% CI: 1.90%-2.70%). Stratified analysis revealed that the occurrence of animal injury was more susceptible to temperature influences in urban ( ER=2.78%, 95% CI: 2.35%-3.21%), female ( ER=2.71%, 95% CI: 2.16%-3.27%), the elderly aged 60 years and above ( ER=3.05%, 95% CI: 1.65%- 4.47%), farmer ( ER=4.66%, 95% CI: 3.03%-6.32%) and agricultural area ( ER=10.63%, 95% CI: 7.57%-13.79%) than their correspondents. In terms of mammalian injury, dog bites showed the highest risk ( ER=2.71%, 95% CI: 2.12%-3.30%). In terms of non-mammalian,snake injuries were highly influenced by temperature ( ER=16.74%, 95% CI: 11.33%-22.40%). Conclusions:The ambient temperature rises could increase the risk of animal injury with much higher risk for non-mammalian than that for mammalian injuries. Our findings suggest that global warming may increase the risk and disease burden from animal injuries.