BACKGROUND:Scoliosis is a three-dimensional deformity characterized by lateral bending and rotation of the spine.Its onset age covers the entire life cycle,becoming an important health issue that threatens people's health.Artificial intelligence continues to advance with the development of computer science.At present,artificial intelligence has great potential for application in medical diagnosis and treatment,and is gradually being applied in screening and diagnosis of scoliosis.OBJECTIVE:To comprehensively review the application of artificial intelligence in screening and diagnosis of scoliosis,elaborate on the progress of its application in recent years from multiple aspects,and look forward to its innovative points,providing reference for the future trend of intelligence.METHODS:Search covered databases such as PubMed,IEEE Xplore,CNKI,and WanFang,using Chinese and English search terms such as"scoliosis,artificial intelligence,machine learning,screen,diagnosis."Boolean logic was used to optimize the search strategy.Articles directly related to the application of artificial intelligence in screening and diagnosis of scoliosis were included,and articles with weak correlation,outdated experimental design,or poor credibility were excluded.Finally,83 articles were included for analysis.RESULTS AND CONCLUSION:(1)Artificial intelligence has shown unique application value and development prospects in multiple fields such as early screening of scoliosis,chest X-ray screening,smartphone screening,X-ray diagnosis,CT and MRI diagnosis,and reconstruction of three-dimensional spinal images.(2)The application of artificial intelligence in the screening and diagnosis of scoliosis has improved efficiency,reduced misdiagnosis rates,and alleviated the burden on medical staff,facilitating early detection and diagnosis of scoliosis and safeguarding spinal health.

BACKGROUND:Scoliosis is a three-dimensional deformity characterized by lateral bending and rotation of the spine.Its onset age covers the entire life cycle,becoming an important health issue that threatens people's health.Artificial intelligence continues to advance with the development of computer science.At present,artificial intelligence has great potential for application in medical diagnosis and treatment,and is gradually being applied in screening and diagnosis of scoliosis.OBJECTIVE:To comprehensively review the application of artificial intelligence in screening and diagnosis of scoliosis,elaborate on the progress of its application in recent years from multiple aspects,and look forward to its innovative points,providing reference for the future trend of intelligence.METHODS:Search covered databases such as PubMed,IEEE Xplore,CNKI,and WanFang,using Chinese and English search terms such as"scoliosis,artificial intelligence,machine learning,screen,diagnosis."Boolean logic was used to optimize the search strategy.Articles directly related to the application of artificial intelligence in screening and diagnosis of scoliosis were included,and articles with weak correlation,outdated experimental design,or poor credibility were excluded.Finally,83 articles were included for analysis.RESULTS AND CONCLUSION:(1)Artificial intelligence has shown unique application value and development prospects in multiple fields such as early screening of scoliosis,chest X-ray screening,smartphone screening,X-ray diagnosis,CT and MRI diagnosis,and reconstruction of three-dimensional spinal images.(2)The application of artificial intelligence in the screening and diagnosis of scoliosis has improved efficiency,reduced misdiagnosis rates,and alleviated the burden on medical staff,facilitating early detection and diagnosis of scoliosis and safeguarding spinal health.

ObjectiveTo explore the effect of cluster scalp acupuncture combined with Taijiquan training on depressive symptom, motor function, activities of daily living, serum markers, as well as brain functional connectivity (FC) and network topological properties in patients with post-stroke depression (PSD). MethodsA total of 40 PSD patients in the Second Affiliated Hospital of Heilongjiang University of Chinese Medicine from September, 2022 to September, 2023 were enrolled and randomly divided into control group (n = 20) and experimental group (n = 20). The control group received cluster scalp acupuncture alone, while the experimental group underwent Taijiquan training in addition, for four weeks. They were assessed with Hamilton Depression Scale-17 (HAMD-17), Fugl-Meyer Assessment (FMA) and Barthel Index (BI) before and after treatment, while the serum levels of dopamine (DA), 5-hydroxytryptamine (5-HT), interleukin-6 (IL-6) and tumor necrosis factor-α (TNF-α) were detected with enzyme-linked immunosorbent assay. Resting-state functional magnetic resonance imaging (rs-fMRI) was applied to assess brain FC, as well as the global efficiency (Eg) and small-world property (σ) of brain networks. ResultsThe scores of HAMD-17, FMA and BI improved in both groups (t > 2.922, P < 0.01) after treatment, and improved more in the experimental group than in the control group (t > 2.517, P < 0.05). The serum levels of DA and 5-HT increased in both groups (t > 2.637, P < 0.05), and increased more in the experimental group (t > 2.192, P < 0.05). The serum levels of IL-6 and TNF-α decreased in the experimental group after treatment (t > 4.059, P < 0.001), and they were less than those in the control group (t > 2.154, P < 0.05). FC between left middle frontal gyrus and right anterior cingulate gyrus, as well as between left hippocampus and right precuneus were higher in the experimental group than in the control group after treatment (t > 3.867, P < 0.001), while Eg and σ increased in both groups (t > 2.828, P < 0.05), and they were higher in the experimental group (t > 2.675, P < 0.05). ConclusionCombination of Taijiquan training is more effective on depressive symptoms, motor function and activities of daily living in PSD patients, which may be related to up-regulation of serum DA and 5-HT, reduction of inflammatory factors, enhancement of prefrontal-limbic system functional connectivity and optimization of brain network topological properties.

Objective: To investigate independent risk factors for lower extremity amputation (LEA) in hospitalized patients with diabetic foot ulcers ( DFUs) . Methods: A multicenter retrospective analysis was conducted on the clinical data of 329 DFUs hospitalized patients with diabetic foot ulcers from four general hospitals across the na⁃tion. A multivariate Logistic regression model was constructed , and prediction analysis was performed using R 4. 2. 1 . The discriminative ability of the model was assessed using receiver operating characteristic curves , while calibration accuracy and clinical applicability were evaluated via calibration curves and decision curve analysis. Results : The study revealed that patients with higher education backgrounds showed lower disease severity (Wagnergrade) (Z = - 4. 331 , P < 0. 05) . A history of amputation , pre⁃existing lower extremity vascular disease , abnormal dorsalis pedis artery pulsation , and a history of coronary heart disease were significantly associated with the severity of DFUs , resulting in higher Wagner scores (P < 0. 05) . In the amputation prognosis analysis , prolonged duration of diabetes and elevated white blood cell count were positively correlated with amputation risk ( both P < 0. 01) .Multivariable regression identified non⁃higher education , low hemoglobin levels , decreased total cholesterol , and abnormally elevated platelet counts as independent risk factors for high Wagner grades ( ≥ grade 3 ) ( all P <0. 05) . The integrated predictive model incorporating these factors demonstrated strong discriminative performance ,with an area under curve of 0. 880 (95% CI: 0. 801 - 0. 960) . The calibration curve slope approached the ideal value , and decision curve analysis confirmed the model ′s clinical net benefit within a threshold probability range of 10% - 65% . Conclusion Lower education level , poor baseline nutritional status , infection , hypercoagulability ,and underlying vascular diseases collectively constitute key factors contributing to elevated amputation risk in DFUs patients. The developed predictive model exhibits high accuracy and may assist clinicians in formulating individual⁃ized intervention strategies.

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.

Acute respiratory distress syndrome(ARDS)is a common respiratory emergency,but current clinical treatment remains at the level of symptomatic support and there is a lack of effective targeted treatment measures.Our previous study confirmed that inhalation of hydrogen gas can reduce the acute lung injury of ARDS,but the application of hydrogen has flammable and explosive safety concerns.Drinking hydrogen-rich liquid or inhaling hydrogen gas has been shown to play an important role in scavenging reactive oxygen species and maintaining mitochondrial quality control balance,thus improving ARDS in patients and animal models.Coral calcium hydrogenation(CCH)is a new solid molecular hydrogen carrier prepared from coral calcium(CC).Whether and how CCH affects acute lung injury in ARDS re-mains unstudied.In this study,we observed the therapeutic effect of CCH on lipopolysaccharide(LPS)induced acute lung injury in ARDS mice.The survival rate of mice treated with CCH and hydrogen inhalation was found to be comparable,demonstrating a significant improvement compared to the untreated ARDS model group.CCH treatment significantly reduced pulmonary hemorrhage and edema,and improved pulmonary function and local microcirculation in ARDS mice.CCH promoted mitochon-drial peripheral division in the early course of ARDS by activating mitochondrial thioredoxin 2(Trx2),improved lung mitochondrial dysfunction induced by LPS,and reduced oxidative stress damage.The results indicate that CCH is a highly efficient hydrogen-rich agent that can attenuate acute lung injury of ARDS by improving the mitochondrial function through Trx2 activation.

Objective To investigate pharmacologically active components of Yiqi Zishen Formula(YZF)and their mechanisms for alleviating airway inflammation in mice with chronic obstructive pulmonary disease(COPD).Methods Ultra-high-performance liquid chromatography coupled with quadrupole-orbitrap mass spectrometry was employed to characterize the chemical components in YZF and YZF-medicated rat serum.A compound-disease target network was constructed based on serum components of YZF to screen the key pathways and targets using enrichment analysis.A mouse model of cigarette smoke-induced COPD was used to evaluate the anti-inflammatory effect of YZF and validate the expression of key proteins in network pharmacology-enriched pathways.Fifty male C57BL/6J mice were randomized equally into control group,COPD model group,high-and low-dose YZF treatment groups,and N-acetylcysteine treatment group.Pulmonary function of the mice was assessed using whole-body plethysmography,and lung histopathology,alveolar structure,and airway remodeling were analyzed using HE staining.The levels of IL-1β,IL-6,and TNF-α in bronchoalveolar lavage fluid(BALF)were determined with ELISA,and pulmonary expressions of PI3K,Akt,phosphorylated Akt(p-Akt),p65,and phosphorylated p65(p-p65)were detected using immunohistochemistry.Results We identified a total of 156 chemical components(including 26 flavonoids or flavonoid glycosides,27 alkaloids,and 11 saponins)in YZF and 43 prototype components in medicated rat serum.Network pharmacology revealed 704 YZF-related targets and 1199 COPD-associated targets.Integrated analysis suggested that the anti-COPD effects of YZF were associated with the PI3K-Akt signaling pathway.In mouse models of COPD,YZF treatment significantly increased mean alveolar number and peak expiratory flow(P<0.05),reduced mean linear intercept,bronchial wall thickness,lung coefficient,and BALF cytokine levels,and suppressed the expressions of PI3K,Akt,p-Akt,p65,and p-p65 in the lung tissues.Conclusion YZF alleviates COPD symptoms and airway inflammation in mice possibly by inhibiting the PI3K/Akt/NF-κB pathway through its multiple components that interact with multiple targets.

Objective:To investigate the differential impact of ultra-high-resolution photon-counting detector CT (UHR PCD-CT) and energy-integrating detector CT (EID-CT) on image quality and calcified plaque-induced luminal stenosis in coronary CT angiography (CCTA).Methods:This retrospective analysis was conducted on patients who underwent both EID-CT and UHR PCD-CT CCTA at the Geriatric Hospital of Nanjing Medical University between January 2021 and November 2024. A total of 141 patients were included in the study, within 46 patients having scans within a 12-month interval. Image quality of all coronary artery segments was subjectively evaluated. Patients with paired scans (interval≤12 months) were included for calcified plaque analysis. Subjective visualization of calcified plaques evaluated. The blooming artifact was calculated as an objective evaluation index for assessing the calcified plaques. Additionally, the degree of coronary artery lumen stenosis resulting from calcified plaques was assessed, along with the measurement of plaque volume and the Agatston score. Changes in lumen stenosis between the two scans were also evaluated. The Wilcoxon signed-rank test was used to compare the subjective scores of coronary artery image quality and calcified plaques between the two groups, and paired-sample t-tests were used to compare the blooming artifact and lumen stenosis degree. Results:The PCD-CT image quality score was significantly higher than that of EID-CT [PCD-CT : 5 (4,5), EID-CT: 4 (4,5); Z=-21.38, P<0.001]. Compared to EID-CT, PCD-CT reduced the blooming artifact (PCD-CT: 38.88%±9.09%, EID-CT: 50.11%±11.52%; t=-12.97, P<0.001), significantly improving the subjective score for visualization of calcified plaques [PCD-CT: 5 (4,5), EID-CT: 3 (2,3); Z=-9.68, P<0.001], and the measured lumen stenosis was notably lower in PCD-CT(PCD-CT:34.88%±18.20%, EID-CT:45.31%±23.42%; t=-9.93, P<0.001). Among 129 analyzed calcified plaques, luminal stenosis was reduced on PCD-CT in 110 plaques (85.3%) and increased in 19 (14.7%), including 4 plaques that had unclear boundaries with the adjacent lumen in EID-CT CCTA images, making the stenosis difficult to assess. Conclusion:Compared to EID-CT, UHR PCD-CT for CCTA significantly improves coronary artery image quality, provides clearer visualization of calcified plaques and adjacent lumen details, and it can reduce the overestimation of coronary artery caleified plaque stenosis.

Brain imaging abnormalities are present in schizophrenia (SZ) and bipolar disorder (BD), demonstrating disease-specific changes, yet they also share similarities in certain brain regions or functional characteristics, with SZ potentially exhibiting more extensive brain damage compared to BD. Structural magnetic resonance imaging (MRI) studies demonstrated widespread gray matter reductions in SZ, particularly in the prefrontal and temporal lobes. In BD, gray matter thickening was observed in the prefrontal lobes during manic episodes, while a reduction in gray matter was noted in the amygdala and hippocampus during depressive episodes. Both SZ and BD exhibited increased ventricular volume and reduced overall brain volume. Functional MRI studies revealed reduced functional connectivity in the prefrontal and temporal lobes in SZ, with decreased global and local efficiency in brain regions such as the hippocampus and cingulate gyrus. BD showed enhanced connectivity in the anterior cingulate gyrus and the default mode network (DMN). Both SZ and BD demonstrated altered functional connectivity in areas such as the striatum, salience network, central executive network and DMN. Diffusion tensor imaging studies showed decreased fractional anisotropy (FA) in the corpus callosum of SZ, with a decrease in FA in the left fronto-occipital fasciculus in BD. Both SZ and BD exhibited reduced FA in the uncinate fasciculus and corpus callosum. Magnetic resonance spectroscopy revealed decreased concentrations of glutathione, N-acetylaspartate (NAA) and inositol in the anterior cingulate gyrus of SZ. In BD, glutathione and inositol concentrations were elevated in the anterior cingulate gyrus, while NAA levels decreased during depressive episodes and increased during remission. Both SZ and BD showed increased levels of glutamate and gamma-aminobutyric acid in the prefrontal cortex. This article provides a review of the current evidence on the differences and similarities in multimodal magnetic resonance brain imaging between SZ and BD, aiming to offer a reference for future exploration of neuroimaging biomarkers and the neurobiological mechanisms of SZ and BD.

Objective:To compare the efficacy of ustekinumab (UST) and vedolizumab (VDZ) in achieving transmural healing in active Crohn′s disease (CD).Methods:From March 1, 2020 to November 30, 2024, 112 patients with active CD treated with UST or VDZ at the Department of Gastroenterology, Tenth People′s Hospital of Tongji University were retrospectively enrolled. According to the medication regimen, the 112 patients were divided into UST group (61 cases) and VDZ group (51 cases). Collected the data at baseline, such as the disease phenotype, other medication history, and clinical indicators including C-creative protein (CRP), etc. Clinical disease activity and endoscopic disease activity were assessed by Harvey-Bradshaw index (HBI) and simplified endoscopic score for Crohn′s disease (SES-CD), respectively. Transmural healing was evaluated according to the intestinal wall thickness measured by intestinal imaging examination of the affected intestinal segment. Transmural healing was defined as bowel wall thickness <0.3 cm and 110 obvious signs of inflammation, clinical remission was defined as HBI≤4, and endoscopic remission was defined as a reduction in SES-CD ≥50% or a score of ≤2. The primary endpoint was transmural healing rate within one year after treatment. The secondary endpoints were endoscopic healing rate and clinical remission rate at 13 to 24th week and 30 to 52nd week after treatment. Chi-square test or Fisher′s exact test was used to compare the efficacy of the 2 medications.Results:There was no significant difference in transmural healing rate between UST group and VDZ group within 1 year after treatment (16.4% (10/61) vs. 23.5% (12/51), χ2=0.90, P=0.344). There were no significant differences in the healing rate between UST group and VDZ group in patients with specific baseline characteristics before treatment, including CD with stenosis, with perianal disease, no history of glucocorticoid use, secondary loss of response to anti-tumor necrosis factor (TNF)-α, SES-CD 7 to 15, decreased body mass index, and increased CRP (18.2%(6/33) vs. 19.4%(7/36), 17.9%(7/39) vs. 19.4%(6/31), 17.1%(6/35) vs. 24.2%(8/33), 20.0%(8/40) vs. 3/18, 14.3%(5/35) vs. 19.2%(5/26), 15.0%(3/20) vs. 3/10, 21.4%(6/28) vs. 5/16), all P>0.05). There was no significant difference in the clinical remission rate or endoscopic remission rate between the UST group and the VDZ group from 13 to 24th week (7/14 vs. 9/18, 3/14 vs. 7/18, RR=1.000 and 0.551, 95% confidence interval: 0.497to 2.011, 0.173to 1.755, χ2=<0.01, Fisher′s exact test, both P>0.05). There was no significant difference in clinical remission rate or endoscopic remission rate between UST group and VDZ group from week 30 to week 52 after treatment (68.5% (37/54) vs. 74.4% (32/43), 27.8% (15/54) vs. 32.6% (14/43), RR=0.921 and 0.853, 95% confidence interval: 0.716 to 1.184, 0.464 to 1.568, χ2=0.41 and 0.26, both P>0.05). In UST group, the proportion of patients with normal hemoglobin after transmural healing was higher than that of patients without transmural healing (9/10 vs. 45.1% (23/51), and the difference was statistically significant ( χ2=5.08, P=0.024). However, there were no significant differences in the proportion of patients with normal body mass index, CRP, platelet count, prealbumin, albumin, interleukin-6 or TNF-α levels after treatment between those who achieved transmural healing and those who did not in either UST group or VDZ group (all P>0.05). And in VDZ group there was no significant difference in the proportion of patients with normal hemoglobin between those who achieved transmural healing and who did not (all P>0.05). Conclusion:UST and VDZ exhibit similar efficacy in transmural healing within one year of treatment in patients with active CD.