1.Specific effect of inserted sham acupuncture and its impact on the estimation of acupuncture treatment effect in randomized controlled trials: A systematic survey.
Xiao-Chao LUO ; Jia-Li LIU ; Ming-Hong YAO ; Ye-Meng CHEN ; Arthur Yin FAN ; Fan-Rong LIANG ; Ji-Ping ZHAO ; Ling ZHAO ; Xu ZHOU ; Xiao-Ying ZHONG ; Jia-Hui YANG ; Bo LI ; Ying ZHANG ; Xin SUN ; Ling LI
Journal of Integrative Medicine 2025;23(6):630-640
BACKGROUND:
The use of inserted sham acupuncture as a placebo in randomized controlled trials (RCTs) is controversial, because it may produce specific effects that cause an underestimation of the effect of acupuncture treatment.
OBJECTIVE:
This systematic survey investigates the magnitude of insert-specific effects of sham acupuncture and whether they affect the estimation of acupuncture treatment effects.
SEARCH STRATEGY:
PubMed, Embase and Cochrane Central Register of Controlled Trials were searched to identify acupuncture RCTs from their inception until December 2022.
INCLUSION CRITERIA:
RCTs that evaluated the effects of acupuncture compared to sham acupuncture and no treatment.
DATA EXTRACTION AND ANALYSIS:
The total effect measured for an acupuncture treatment group in RCTs were divided into three components, including the natural history and/or regression to the mean effect (controlled for no-treatment group), the placebo effect, and the specific effect of acupuncture. The first two constituted the contextual effect of acupuncture, which is mimicked by a sham acupuncture treatment group. The proportion of acupuncture total effect size was considered to be 1. The proportion of natural history and/or regression to the mean effect (PNE) and proportional contextual effect (PCE) of included RCTs were pooled using meta-analyses with a random-effect model. The proportion of acupuncture placebo effect was the difference between PCE and PNE in RCTs with non-inserted sham acupuncture. The proportion of insert-specific effect of sham acupuncture (PIES) was obtained by subtracting the proportion of acupuncture placebo effect and PNE from PCE in RCTs with inserted sham acupuncture. The impact of PIES on the estimation of acupuncture's treatment effect was evaluated by quantifying the percentage of RCTs that the effect of outcome changed from no statistical difference to statistical difference after removing PIES in the included studies, and the impact of PIES was externally validated in other acupuncture RCTs with an inserted sham acupuncture group that were not used to calculate PIES.
RESULTS:
This analysis included 32 studies with 5492 patients. The overall PNE was 0.335 (95% confidence interval [CI], 0.255-0.415) and the PCE of acupuncture was 0.639 (95% CI, 0.567-0.710) of acupuncture's total effect. The proportional contribution of the placebo effect to acupuncture's total effect was 0.191, and the PIES was 0.189. When we modeled the exclusion of the insert-specific effect of sham acupuncture, the acupuncture treatment effect changed from no difference to a significant difference in 45.45% of the included RCTs, and in 40.91% of the external validated RCTs.
CONCLUSION
The insert-specific effect of sham acupuncture in RCTs represents 18.90% of acupuncture's total effect and significantly affects the evaluation of the acupuncture treatment effect. More than 40% of RCTs that used inserted sham acupuncture would draw different conclusions if the PIES had been controlled for. Considering the impact of the insert-specific effect of sham acupuncture, caution should be taken when using inserted sham acupuncture placebos in RCTs. Please cite this article as: Luo XC, Liu JL, Yao MH, Chen YM, Fan AY, Liang FR, Zhao JP, Zhao L, Zhou X, Zhong XY, Yang JH, Li B, Zhang Y, Sun X, Li L. Specific effect of inserted sham acupuncture and its impact on the estimation of acupuncture treatment effect in randomized controlled trials: A systematic survey. J Integr Med. 2025; 23(6):630-640.
Acupuncture Therapy/methods*
;
Humans
;
Randomized Controlled Trials as Topic
;
Placebo Effect
;
Placebos
;
Treatment Outcome
2.Effects of Hot Night Exposure on Human Semen Quality: A Multicenter Population-Based Study.
Ting Ting DAI ; Ting XU ; Qi Ling WANG ; Hao Bo NI ; Chun Ying SONG ; Yu Shan LI ; Fu Ping LI ; Tian Qing MENG ; Hui Qiang SHENG ; Ling Xi WANG ; Xiao Yan CAI ; Li Na XIAO ; Xiao Lin YU ; Qing Hui ZENG ; Pi GUO ; Xin Zong ZHANG
Biomedical and Environmental Sciences 2025;38(2):178-193
OBJECTIVE:
To explore and quantify the association of hot night exposure during the sperm development period (0-90 lag days) with semen quality.
METHODS:
A total of 6,640 male sperm donors from 6 human sperm banks in China during 2014-2020 were recruited in this multicenter study. Two indices (i.e., hot night excess [HNE] and hot night duration [HND]) were used to estimate the heat intensity and duration during nighttime. Linear mixed models were used to examine the association between hot nights and semen quality parameters.
RESULTS:
The exposure-response relationship revealed that HNE and HND during 0-90 days before semen collection had a significantly inverse association with sperm motility. Specifically, a 1 °C increase in HNE was associated with decreased sperm progressive motility of 0.0090 (95% confidence interval [ CI]: -0.0147, -0.0033) and decreased total motility of 0.0094 (95% CI: -0.0160, -0.0029). HND was significantly associated with reduced sperm progressive motility and total motility of 0.0021 (95% CI: -0.0040, -0.0003) and 0.0023 (95% CI: -0.0043, -0.0002), respectively. Consistent results were observed at different temperature thresholds on hot nights.
CONCLUSION
Our findings highlight the need to mitigate nocturnal heat exposure during spermatogenesis to maintain optimal semen quality.
Humans
;
Male
;
Semen Analysis
;
Adult
;
Sperm Motility
;
Hot Temperature/adverse effects*
;
China
;
Middle Aged
;
Spermatozoa/physiology*
;
Young Adult
3.Effect of Health Failure Mode and Effect Analysis in Optimizing the Management Process of Postoperative Diabetes Insipidus in Children Undergoing Neurosurgery.
Hui-Yun ZHAO ; Xiao-Ying XU ; Bo WU ; Shi TANG ; Xin-Meng LI
Acta Academiae Medicinae Sinicae 2025;47(4):582-589
Objective To investigate the effect of health failure mode and effect analysis(HFMEA)in optimizing the management process of postoperative diabetes insipidus in children undergoing neurosurgery.Methods Based on HFMEA,a management flowchart for postoperative diabetes insipidus in children undergoing neurosurgery was created.Brainstorming was adopted to identify failure modes in the workflow,analyze risk factors,and develop improvement measures,thereby refining the management flowchart.The amelioration and prognosis of diabetes insipidus in these children before(October 2022 to November 2023)and after(January 2024 to February 2025)implementation of the management flowchart were compared.Results The HFMEA-based management process for postoperative diabetes insipidus in children undergoing neurosurgery alleviated the symptoms of diabetes insipidus regarding the number of diabetes insipidus in the pediatric intensive care unit(P=0.006),the average daily urine output in the pediatric intensive care unit(P=0.001),the proportion of electrolyte abnormalities at discharge/transfer(P=0.037),the duration of mechanical ventilation(P=0.007),and the length of stay in the intensive care unit(P=0.001).Conclusion The HFMEA-based management process for postoperative diabetes insipidus in children undergoing neurosurgery is beneficial to the optimization of the management process,the alleviation of postoperative diabetes insipidus,and the improvement of prognosis in these children.
Humans
;
Diabetes Insipidus/etiology*
;
Neurosurgical Procedures/adverse effects*
;
Child
;
Postoperative Complications/therapy*
;
Healthcare Failure Mode and Effect Analysis
;
Intensive Care Units, Pediatric
;
Risk Factors
4.Analysis of quality control and radiation protection testing data of selected medical electron linear accelerators in Shandong Province, China
Bao TAO ; Hui SHANG ; Lihei DE ; Ying GUO ; Tao XU ; Yiwei ZHANG
Chinese Journal of Radiological Health 2025;34(6):824-829
Objective To investigate the status of quality control of medical electron linear accelerators and radiation protection of machine rooms housing these accelerators in Shandong Province. Methods A total of 52 medical electron linear accelerators in 40 hospitals across Shandong Province were selected as the study subjects. A series of indicators were tested according to relevant quality control testing specifications and radiation protection testing standards. Statistical analysis was performed using SPSS 25.0. Results The five performance indicators of the 52 medical electron linear accelerators, including offset of the radiation beam axis relative to the equal center point (hereinafter referred to as the equal center point offset), dose deviation, output dose repeatability, output dose linearity, and uniformity of the square X-ray radiation field (10 cm × 10 cm), all had a qualified rate of 100%. The dose deviation of accelerators in secondary hospitals was superior to that in tertiary hospitals. The output dose linearity and uniformity of the square X-ray radiation field of accelerators in tertiary hospitals were superior to those in secondary hospitals. All machine rooms housing the investigated medical electron linear accelerators were qualified in radiation protection testing. Conclusion The performance indicators of the medical electron linear accelerators investigated in this study and the radiation protection of machine rooms all complied with national standards. Relevant hospitals should continue to strictly implement radiation protection standards and strengthen the supervision of the equipment sites.
5.HIV-1 pretreatment drug resistance and molecular transmission network characteristics in Yubei District,Chongqing
Difei LI ; Ying XU ; Mao YE ; Xin HUANG ; Xuemei MA ; Yi JIN ; Songsong SUN ; Jinping XIONG ; Hui LIU ; Guohui WU
Chongqing Medicine 2025;54(3):719-724,730
Objective To analyze the characteristics of HIV-1 pretreatment drug resistance(PDR)and molecular transmission networks in Yubei District,Chongqing,providing evidence for targeted interventions.Methods Using a cross-sectional design,plasma samples were collected from HIV/AIDS patients receiving antiretroviral therapy(ART)in Yubei District from January 2022 to December 2023.Pol gene fragments were extracted and amplified for HIV-1 genotyping and drug resistance analysis.Molecular transmission networks were constructed based on genetic distance calculations.Results Among 478 HIV-1 pol sequences,eight geno-types were identified:with CRF07_BC(60.4%,289/478),CRF08_BC(15.5%,74/478),CRF01_AE(11.7%,56/478),and CRF85_BC(5.9%,28/478).The overall PDR rate was 6.3%(30/478),with resistance to nucleoside reverse transcriptase inhibitors(NRTIs)and non-nucleoside reverse transcriptase inhibitors(NNRTIs)at 1.7%(8/478)and 5.2%(25/478),respectively.No protease inhibitor(PI)resistance was de-tected.The molecular network included 177 cases(37.0%network entry rate),forming 53 clusters with 198 connections.Cluster sizes ranged from 2 to 17 nodes,and 75.3%(149/198)of connections were associated with five subdistricts/towns:Shuanglonghu Street,Huixing Street,Luoqi Town,Gulu Town,and Baoshenghu Street.Conclusion HIV-1 genotypes in Yubei District exhibit diversity and complexity,with moderate PDR prevalence.Regional clustering of transmission networks suggests the need for enhanced molecular surveil-lance and targeted interventions based on analytical findings.
6.Changing resistance profiles of Haemophilus influenzae and Moraxella catarrhalis isolates in hospitals across China:results from the CHINET Antimicrobial Resistance Surveillance Program,2015-2021
Hui FAN ; Chunhong SHAO ; Jia WANG ; Yang YANG ; Fupin HU ; Demei ZHU ; Yunsheng CHEN ; Qing MENG ; Hong ZHANG ; Chun WANG ; Fang DONG ; Wenqi SONG ; Kaizhen WEN ; Yirong ZHANG ; Chuanqing WANG ; Pan FU ; Chao ZHUO ; Danhong SU ; Jiangwei KE ; Shuping ZHOU ; Hua ZHANG ; Fangfang HU ; Mei KANG ; Chao HE ; Hua YU ; Xiangning HUANG ; Yingchun XU ; Xiaojiang ZHANG ; Wenen LIU ; Yanming LI ; Lei ZHU ; Jinhua MENG ; Shifu WANG ; Bin SHAN ; Yan DU ; Wei JIA ; Gang LI ; Jiao FENG ; Ping GONG ; Miao SONG ; Lianhua WEI ; Xin WANG ; Ruizhong WANG ; Hua FANG ; Sufang GUO ; Yanyan WANG ; Dawen GUO ; Jinying ZHAO ; Lixia ZHANG ; Juan MA ; Han SHEN ; Wanqing ZHOU ; Ruyi GUO ; Yan ZHU ; Jinsong WU ; Yuemei LU ; Yuxing NI ; Jingrong SUN ; Xiaobo MA ; Yanqing ZHENG ; Yunsong YU ; Jie LIN ; Ziyong SUN ; Zhongju CHEN ; Zhidong HU ; Jin LI ; Fengbo ZHANG ; Ping JI ; Yunjian HU ; Xiaoman AI ; Jinju DUAN ; Jianbang KANG ; Xuefei HU ; Xuesong XU ; Chao YAN ; Yi LI ; Shanmei WANG ; Hongqin GU ; Yuanhong XU ; Ying HUANG ; Yunzhuo CHU ; Sufei TIAN ; Jihong LI ; Bixia YU ; Cunshan KOU ; Jilu SHEN ; Wenhui HUANG ; Xiuli YANG ; Likang ZHU ; Lin JIANG ; Wen HE ; Chunlei YUE
Chinese Journal of Infection and Chemotherapy 2025;25(1):30-38
Objective To investigate the distribution and antimicrobial resistance profiles of clinically isolated Haemophilus influenzae and Moraxella catarrhalis in hospitals across China from 2015 to 2021,and provide evidence for rational use of antimicrobial agents.Methods Data of H.influenzae and M.catarrhalis strains isolated from 2015 to 2021 in CHINET program were collected for analysis,and antimicrobial susceptibility testing was performed by disc diffusion method or automated systems according to the uniform protocol of CHINET.The results were interpreted according to the CLSI breakpoints in 2022.Beta-lactamases was detected by using nitrocefin disk.Results From 2015 to 2021,a total of 43 642 strains of Haemophilus species were isolated,accounting for 2.91%of the total clinical isolates and 4.07%of Gram-negative bacteria in CHINET program.Among the 40 437 strains of H.influenzae,66.89%were isolated from children and 33.11%were isolated from adults.More than 90%of the H.influenzae strains were isolated from respiratory tract specimens.The prevalence of β-lactamase was 53.79%in H.influenzae strains.The H.influenzae strains isolated from children showed higher resistance rate than the strains isolated from adults.Overall,779 strains of H.influenzae did not produce β-lactamase but were resistant to ampicillin(BLNAR).Beta-lactamase-producing strains showed significantly higher resistance rates to these antimicrobial agents than the β-lactamase-nonproducing strains.Of the 16 191 M.catarrhalis strains,80.06%were isolated from children and 19.94%isolated from adults.M.catarrhalis strains were mostly susceptible to both amoxicillin-clavulanic acid and cefuroxime,evidenced by resistance rate lower than 2.0%.Conclusions The emergence of antibiotic-resistant H.influenzae due to β-lactamase production poses a challenge for clinical anti-infective treatment.Therefore,it is very important to implement antibiotic resistance surveillance for H.influenzae and guide rational antibiotic use.All local clinical microbiology laboratories should actively improve antibiotic susceptibility testing and strengthen antibiotic resistance surveillance for H.influenzae.
7.Research of miR-508-3p involvement in ovarian cancer progression by regulating ZEB1
Yu-hong XU ; Shuai-ying ZHU ; Jiang-jing SHAN ; Wei-ping ZHENG ; Hui-ya ZHANG ; Yun-gen WANG
The Chinese Journal of Clinical Pharmacology 2025;41(2):193-197
Objective To investigate the expression of microRNA-508-3p(miR-508-3p)in epithelial ovarian cancer(EOC)tissue,its impact on the migration and invasion of ovarian cancer cells,and its regulatory relationship with zinc-finger E-box-binding homeobox 1(ZEB1).Methods The surgical resection of EOC cancer tissues and paired adjacent normal tissues were collected.SKOV3 cells were divided into the NC mimic group(transfected with NC mimic),miR-508-3p mimic group(transfected with miR-508-3p mimic),si-NC group(transfected with si-NC),si-ZEB1 group(transfected with si-ZEB1)and co-transfection group(co-transfected with si-ZEB1 and miR-508-3p mimic).The mRNA expression levels of miR-508-3p and ZEB1 in EOC cancer tissues,adjacent normal tissues and five groups of cells were measured by real-time quantitative polymerase chain reaction.The Transwell assay was used to detect the cell migration and invasion abilities.Results The relative expression levels of miR-508-3p in EOC tissues and adjacent normal tissues were 0.77±0.36 and 1.07±0.40,the relative expression levels of ZEB1 mRNA in EOC tissues and adjacent normal tissues were 2.10±1.21 and 1.29±0.95,and the differences were statistically significant(all P<0.01).The migration cell number of the NC mimic,miR-508-3p mimic,si-NC,si-ZEB1 and co-transfection groups was 633.00±32.49,319.20±19.89,650.40±25.85,375.00±17.25 and 129.40±17.10;the invasion cell number was 527.20±25.01,288.60±16.68,520.00±25.83,293.40±18.37 and 76.60±8.76;the relative expression levels of miR-508-3p were 1.05±0.37,3.94±1.21,1.01±0.21,1.26±0.34 and 3.40±0.41;the relative expression levels of ZEB1 mRNA were 1.00±0.04,0.58±0.05,1.00±0.08,0.54±0.07 and 0.29±0.03,respectively.The above indicators showed statistically significant differences between the miR-508-3p mimic group and the NC mimic group,between the si-NC group and the co-transfection group(P<0.01,P<0.05).Conclusion MiR-508-3p is lowly expressed in EOC cancer tissue,and it may inhibit the migration and invasion of ovarian cancer cells by targeting ZEB1 expression.
8.Sequent optimization of AI-assisted compressive sensing techniques in brain 3D-TOF-MRA
Kai NING ; Hui XU ; Xiangming LI ; Lixin ZHANG ; Weifeng WANG ; Ying YUAN
China Medical Equipment 2025;22(10):15-19
Objective:To explore the influence of artificial intelligence(AI)-assisted compressive sensing(ACS)technique with different acceleration factors on the image quality and scan time of three dimensional time-of-flight magnetic resonance angiography(3D-TOF-MRA)for brain.Methods:Thirty participants who underwent brain magnetic resonance imaging(MRI)at Tongzhou Branch of Beijing Friendship Hospital were recruited.All subjects underwent imaging scans about four different parameters:a non-accelerated technique(control group),ACS technique integrated with acceleration factor of 4.03(ACS4 group),ACS technique integrated with acceleration factor of 5.02(ACS5 group),and ACS technique integrated with acceleration factor of 6.06(ACS6 group).The image clarity,ranking of imaging capabilities of distal branch blood vessels and the ratio of pseudo-stenosis were qualitatively analyzed.The signal-to-noise ratio(SNR),contrast-to-noise ratio(CNR),edge sharpness,and scan time were quantitatively analyzed.Results:There was not difference in vessel clarity among three ACS groups at the proximal and middle intracranial segments.For distal segments of blood vessel,the ACS4 group[3.0(3.0,3.0)]and ACS5 group[3.0(3.0,3.0)]were better than ACS6[2.5(2.0,3.0)](q=29.800,27.500,P<0.05).The imaging capabilities of distal-branch vessel of ACS4 group and ACS5 group were better than ACS6 group.There was no stenosis in the proximal and middle segments of the images of the three ACS group,and there were no stenosis in the images of distal vessels of ACS4 group and ACS5 group.A total of 5 cases were pseudo-stenosis in the distal vessels of ACS6 group.Compared with the control group,the incidence of pseudo-stenosis in the distal vessels of ACS6 group was 16.7%.The SNR and CNR values of quantitative analysis for proximal vessels in ACS6 group were higher than them in ACS4 group(q=27.800,26.200,P<0.05),and there was not significant difference in them among ACS4 group,ACS6 group and ACS5 group(P>0.05).The differences of SNR and CNR values in the middle and distal segments of blood vessels among different groups were not significant(P>0.05).There was not significant difference in the edge sharpness of blood vessels among ACS4 group,ACS5 group,and ACS6 group(P>0.05),while all of them were higher than those of control group,and the differences were significant(q=48.150,53.367,44.883,P<0.001).Compared with control group,the scan-time of ACS4 group was reduced by 55.19%,and that of ACS5 group was reduced by 64.07%,and that of ACS6 group was reduced by 70%.Conclusion:ACS technique can accelerate the imaging speed of brain 3D-TOF-MRA and ensure image quality.It is clinically recommended to set the ACS acceleration factor as 5.02 to undergo brain 3D-TOF-MRA scans.
9.A comparative study of radiotherapy using three distinct radiotherapy techniques following immediate breast reconstruction for breast cancer
Xiantao HE ; Zhuohua XU ; Yusong LONG ; Junwen TAN ; Gang LI ; Yongfu FENG ; Hui YANG ; Ying LU ; Zhanyu WANG
Chinese Journal of Radiological Medicine and Protection 2025;45(4):317-324
Objective:To investigate the differences in dosimetric parameters for target volumes and organs at risk (OARs), radiation doses to reconstructed tissues, and beam-on time in radiotherapy among helical tomotherapy (HT), volumetric modulated arc therapy (VMAT), and fixed-field intensity-modulated radiotherapy (F_IMRT) following immediate breast reconstruction for breast cancer, thereby providing a reference for the selection of clinical radiotherapy techniques.Methods:This study retrospectively investigated 15 breast cancer patients who underwent radiotherapy following modified radical mastectomy and immediate breast reconstruction at the Liuzhou Worker′s Hospital from August 2018 to July 2023. During target volume delineation, precautions were taken to avoid the reconstructed tissues, which were delineated separately. Customized HT, VMAT, and F_IMRT treatment plans were designed for each patient. The plans were categorized into the HT, VMAT, and F_IMRT groups based on different radiotherapy techniques employed. They were comparatively analyzed through one-way analysis of variance (ANOVA), with multiple comparisons further conducted in the case of significant differences.Results:Statistical analyses reveal significant differences in various parameters of target volumes among the three groups of plans ( F = 38.73, 14.95, 37.01, 48.05, 35.55, 22.56, 34.30, P < 0.05). Pairwise comparisons indicate that the maximum dose ( D2%), minimum dose ( D98%), mean dose ( Dmean), and the proportion of high-dose volumes within the target volume ( V107%and V110%) in both the HT and VMAT groups were significantly better than those in the F_IMRT group. The HT group demonstrated the optimal conformity index (CI), while the VMAT group displayed the superior homogeneity index (HI) compared to the other two groups. In terms of OAR, the V20 of the ipsilateral lung was the lowest in the HT group ( F = 14.31, P < 0.05) and the highest in the F_IMRT group ( F = 14.31, P < 0.05). However, the V5 and Dmean for both the ipsilateral and contralateral lungs in the HT group significantly surpassed those of the other groups ( F = 39.16, 31.91, P < 0.05). The mean dose Dmean ( F = 5.57, P < 0.05) of the contralateral breast was significantly reduced in the VMAT group compared to the other two groups. No statistically significant differences were observed for other OARs, including the heart, spinal cord PRV, thyroid, and humeral head ( P > 0.05). The radiation doses to reconstructed tissues ( Dmax, V53.5, Dmean) ascended in the order of HT, VMAT, and F_IMRT groups ( F = 17.69, 17.53, 15.11, P < 0.05). The HT and F_IMRT groups showed similar beam-on times ( P > 0.05), both exceeding that of the VMAT group by several folds ( F = 28.72, P < 0.05). Conclusions:The comparative analysis indicates that the three radiotherapy techniques exhibit distinct advantages and limitations, with F_IMRT demonstrating the least comprehensive advantage. HT can enhance the conformity of target volumes while reducing the overall radiation doses to reconstructed tissues and the crucial indicator V20 in the ipsilateral lung. VMAT demonstrates the highest treatment efficiency, yielding improved dose uniformity in the target volume and reduced radiation doses to the contralateral breast. It is advisable to prioritize HT or VMAT based on actual clinical conditions.
10.Construction of a machine learning model based on the Ki67 positive index to predict the recurrence risk of hepatocellular carcinoma
Haoran LI ; Yan YU ; Fangying FAN ; Wenzhen DING ; Hui FENG ; Minghua YING ; Jiawei LI ; Qingqing SUN ; Lele BIAN ; Haokai XU ; Zhanyue CHEN ; Jie YU ; Ping LIANG
Chinese Journal of Hepatology 2025;33(9):898-909
Objective:To screen the optimal machine learning model for predicting the recurrence condition of hepatocellular carcinoma (HCC) at different time points post-surgery, based on the cutoff value of the Ki67 positive proliferation index condition calculated from recurrence-free survival and combined with various clinical features.Methods:retrospective study included initially treated patients with solitary HCC who underwent radical surgery at the Fifth Medical Center of the PLA General Hospital from January 2013 to March 2023. Data included general clinical data, preoperative laboratory parameters, and surgical pathology information about the subjects. The postoperative recurrence status was assessed by querying the medical record system or by telephone follow-up. The Ki67 positive index cutoff value was determined by the X-tile software based on the patient's recurrence-free survival status and time analysis. Survival rates were calculated using the Kaplan-Meier method, and survival curves were plotted. The study population was randomly divided into training and testing groups in a 7:3 ratio using a computer-generated random number method. The minimum redundancy maximum relevance (mRMR) method was used for feature variable selection. Predictive models for postoperative HCC recurrence conditions in patients with HCC were constructed using random forest, support vector machine, logistic regression, and gradient boosting decision tree machine learning algorithms. Inter-group comparisons for continuous data were performed using the t-test or Mann-Whitney U test. Inter-group comparisons of enumeration data were performed using the Pearson χ2 test, continuity-corrected χ2 test, or Fisher's exact test. Results:The cutoff values for the Ki67 positivity index were 0.3 and 0.5 in 510 cases, with a follow-up time ranging from 1.2 to 11.4 years (median: 6.2 years). The recurrence-free survival time was between 1 and 135 months (median: 32 months), with recurrence-free survival rates post-surgery at 1, 2, 3, and 5 years were 87.5%, 77.1%, 61.2%, and 54.5%, respectively. The top five variables predicted HCC recurrence and non-recurrence conditions following surgical follow-up at 6 months, 1 year, 2 years, and beyond 2 years, in accordance with information obtained by the mRMR screen out. The Ki67 positivity index screened a successfully constructed machine learning model to predict HCC recurrence and non-recurrence conditions following surgical follow-up at 6 months, 1 year, 2 years, and beyond 2 years. The machine learning model based on the gradient boosting decision tree algorithm had the best prediction performance among them (areas under the receiver operating characteristic curves for predicting HCC recurrence within six months in the training and validation sets were 0.996 and 0.946, and accuracies were 0.972 and 0.935, respectively).Conclusion:A machine learning model was successfully constructed using the Ki67 positivity index combined with four readily available clinical features to predict HCC recurrence. The machine learning model based on the gradient boosting decision tree algorithm demonstrated the best performance in terms of predicting HCC recurrence within six months after surgery.

Result Analysis
Print
Save
E-mail