Objective:To investigate the prognostic factors for esophageal cancer after radical resection and the application value of machine learning prediction model.Methods:The retrospective cohort study was conducted. The clinicopatholigical data of 406 esophageal cancer patients who were admitted to Qilu Hospital of Shandong University from January 2018 to March 2022 were collected. There were 357 males and 49 females, aged (64±8)years. All patients underwent radical resection of esophageal cancer. The 406 patients were randomly divided into a training set of 285 cases and a validation set of 121 cases at a 7∶3 ratio based on a random number table. The training set was used to construct prediction model, and the validation set was used to validate prediction model. Patients were divided into high-risk group and low-risk group based on risk scores. Observation indicators: (1) follow-up of patients and analysis of influencing factors for prognosis; (2) construction and validation of machine learning prediction models. Comparison of measurement data with normal distribution between groups was conducted using the independent sample t test. Comparison of measurement data with skewed distribution between groups was conducted using the Mann-Whitney U test. Comparison of count data between groups was conducted using the chi-square test. Comparison of ordinal data between groups was conducted using the rank sum test. The Kaplan-Meier method was used to calculate survival rate and plot survival curve, and the Log-rank test was used for survival analysis. The Cox proportional hazard regression model was used for univariate and multivariate analyses. Independent influencing factors were included, and data processing, machine learning model construction, and visualization were performed using R packages including random survival forest (RSF), gradient boosting machine (GBM), least absolute shrinkage and selection operator Cox regression (LASSO-Cox), Cox proportional hazards model boosting (CoxBoost), survival support vector machine (survivalsvm), extreme gradient boosting (XGBoost), supervised principal component analysis (SuperPC), and Cox partial least squares regression (plsRcox). Receiver operating characteristic (ROC) curves were drawn, and sensitivity, specificity, and area under the curve (AUC) were calculated. The Delong test was used to assess the differences in AUC among different models in the training set, and the time-dependent ROC was used to compare the predictive performance of different models. Calibration curves were used to evaluate model accuracy, and decision curve analysis (DCA) was used to evaluate overall net benefit. Results:(1) Follow-up of patients and analysis of influencing factors for prognosis. All 406 patients were followed up postoperatively for 28(range, 6-36)months, with 1- and 3-year overall survival rate of 86.5% and 40.9%, respectively. The 285 patients in the training set were followed up postoperatively for 30(range, 6-36)months, with 1- and 3-year overall survival rate of 85.1% and 35.5%, respectively. The 121 patients in the validation set were followed up postoperatively for 25(range, 6-36)months, with 1- and 3-year overall survival rate of 87.0% and 43.2%, respectively. There was no significant difference in postoperative overall survival rate between the training set and the validation set ( χ2=3.20, P>0.05). Results of multivariate analysis showed that left thoracic surgical approach, preopera-tive neutrophil count, vascular invasion, perineural invasion, pathological T2-4 stage, pathological N2-3 stage, and postoperative pneumonia were independent risk factors affecting postoperative survival of 285 patients in the training set ( hazard ratio=1.466, 1.037, 1.482, 1.549, 5.268, 7.727, 22.202, 2.539, 2.686, 1.425, 95% confidence interval as 1.026-2.096, 1.003-1.073, 1.008-2.179, 1.105-2.170, 1.201-23.099, 1.833-32.576, 4.734-104.128, 1.577-4.087, 1.631-4.422, 1.018-1.994, P<0.05). (2) Construction and validation of machine learning prediction models. Independent risk factors affecting postoperative survival were included to construct RSF, GBM, LASSO-Cox, CoxBoost, survivalsvm, XGBoost, SuperPC, and plsRcox machine learning prediction models. Results of Delong test showed that there were significant differences in the AUC of RSF and GBM from the other six models ( P<0.05). Results of time-dependent ROC curve showed that all 8 machine learning predic-tion models had good discriminative ability in the training cohort, among which the RSF machine learning prediction model had the best predictive performance. Results of calibration curve showed that the RSF machine learning prediction model fitted well for predicting postoperative 1-, 2-, and 3-year overall survival in the training cohort, with high consistency with actual results. Results of decision curve analysis showed that within a threshold range of 0-0.80, the RSF machine learning prediction model provided a better overall net benefit. Further analysis showed that in the validation set, the AUC of RSF machine learning prediction model for postoperative 1-, 2-, and 3-year survival prediction were 0.786 (95% confidence interval as 0.609-0.962), 0.774 (95% confidence interval as 0.676-0.873), and 0.750 (95% confidence interval as 0.652-0.848), respectively. Results of calibration curve showed that the RSF machine learning prediction model fitted well for predicting postopera-tive 1-, 2-, and 3-year overall survival in the validation set, with high consistency with actual results. In the training set, the optimal cutoff value of the RSF machine learning prediction model risk score was 11.7. Patients with risk score ≥11.7 were classified as the high-risk group, and those with risk score <11.7 as the low-risk group. The median survival times of the two groups were 18.0 months and >36.0 months, respectively, showing a significant difference between them ( χ2=73.30, P<0.05). In the validation set, the optimal cutoff value of the RSF machine learning prediction model risk score was 11.7. Patients with risk score ≥11.7 were classified as the high-risk group, and those with risk score<11.7 as the low-risk group. The median survival times of the two groups were 17.0 months and>36.0 months for the high-risk and low-risk groups, respectively, showing a significant difference between them ( χ2=35.20, P<0.05). Conclusions:Left thoracic surgical approach, preoperative neutrophil count, vascular invasion, perineural invasion, pathological T2-4 stage, pathological N2-3 stage, and postoperative pneumonia are independent risk factors affecting survival of esophageal cancer patients after radical resection. The RSF machine learning prediction model constructed based on these factors can effectively distinguish the survival prognosis of high-risk and low-risk patients.

Objective:To explore differences in the efficacy and safety of ruxolitinib in patients with myelofibrosis by age and to identify prognostic factors by analyzing clinical features and characteristics of chromosomes and gene mutations.Methods:This study retrospectively analyzed 188 patients with myelofibrosis who received ruxolitinib in the Department of Hematology, Qilu Hospital, Shandong University from January 1, 2017, to July 1, 2024. According to age at diagnosis, the patients were divided into the middle-aged group (≤55 years), young elderly group (56-65 years), and elderly group (>65 years). Clinical features, the characteristics of chromosomes and gene mutations, and the efficacy and safety of ruxolitinib treatment were compared across the three age groups. Independent factors influencing overall survival were identified through Cox proportional risk regression analysis.Results:Before treatment, the elderly group had more underlying comorbidities, a heavier symptom burden, higher leukocyte count, higher proportion and frequency of JAK2 mutations, and lower proportion of CALR mutations. The incidence of nondriver gene mutations was significantly higher in the young elderly group. After ruxolitinib treatment, the degree of reduction in spleen size did not differ significantly among the three groups. The length of the palpable spleen below the left costal margin reduced by more than 50% from baseline in 50.9% (27/53) of the patients in the middle-aged group, 43.5% (27/62) in the young elderly group, and 45.5% (20/44) in the elderly group ( P=0.720). No significant difference was observed among the three groups in the degree of reduction in Myeloproliferative Neoplasm Symptom Assessment Form (10-item version) score ( P=0.153), with a reduction in total symptom score by more than 50% achieved by 54.0% (27/50), 60.3% (41/68), and 66.7% (34/51) of the patients from the three groups, respectively ( P=0.429). The most common hematological adverse events were anemia and thrombocytopenia, while the most common nonhematological adverse events were electrolyte disturbance, elevated transaminase activity, and pulmonary infection. Multivariate analysis indicated that in ruxolitinib-treated patients with myelofibrosis, poor overall survival was independently predicted by increased age, reduced hemoglobin, percentage of bone marrow blasts ≥ 1%, absence of JAK2 mutations, chromosomal abnormalities, ≥2 high-molecular-risk mutations, and TP53 mutations. Conclusions:Patients with myelofibrosis stratified by age exhibited heterogeneous clinical features and gene mutation profiles but similar efficacy of ruxolitinib treatment and occurrence of adverse events.

Objective:To investigate the prognostic factors for esophageal cancer after radical resection and the application value of machine learning prediction model.Methods:The retrospective cohort study was conducted. The clinicopatholigical data of 406 esophageal cancer patients who were admitted to Qilu Hospital of Shandong University from January 2018 to March 2022 were collected. There were 357 males and 49 females, aged (64±8)years. All patients underwent radical resection of esophageal cancer. The 406 patients were randomly divided into a training set of 285 cases and a validation set of 121 cases at a 7∶3 ratio based on a random number table. The training set was used to construct prediction model, and the validation set was used to validate prediction model. Patients were divided into high-risk group and low-risk group based on risk scores. Observation indicators: (1) follow-up of patients and analysis of influencing factors for prognosis; (2) construction and validation of machine learning prediction models. Comparison of measurement data with normal distribution between groups was conducted using the independent sample t test. Comparison of measurement data with skewed distribution between groups was conducted using the Mann-Whitney U test. Comparison of count data between groups was conducted using the chi-square test. Comparison of ordinal data between groups was conducted using the rank sum test. The Kaplan-Meier method was used to calculate survival rate and plot survival curve, and the Log-rank test was used for survival analysis. The Cox proportional hazard regression model was used for univariate and multivariate analyses. Independent influencing factors were included, and data processing, machine learning model construction, and visualization were performed using R packages including random survival forest (RSF), gradient boosting machine (GBM), least absolute shrinkage and selection operator Cox regression (LASSO-Cox), Cox proportional hazards model boosting (CoxBoost), survival support vector machine (survivalsvm), extreme gradient boosting (XGBoost), supervised principal component analysis (SuperPC), and Cox partial least squares regression (plsRcox). Receiver operating characteristic (ROC) curves were drawn, and sensitivity, specificity, and area under the curve (AUC) were calculated. The Delong test was used to assess the differences in AUC among different models in the training set, and the time-dependent ROC was used to compare the predictive performance of different models. Calibration curves were used to evaluate model accuracy, and decision curve analysis (DCA) was used to evaluate overall net benefit. Results:(1) Follow-up of patients and analysis of influencing factors for prognosis. All 406 patients were followed up postoperatively for 28(range, 6-36)months, with 1- and 3-year overall survival rate of 86.5% and 40.9%, respectively. The 285 patients in the training set were followed up postoperatively for 30(range, 6-36)months, with 1- and 3-year overall survival rate of 85.1% and 35.5%, respectively. The 121 patients in the validation set were followed up postoperatively for 25(range, 6-36)months, with 1- and 3-year overall survival rate of 87.0% and 43.2%, respectively. There was no significant difference in postoperative overall survival rate between the training set and the validation set ( χ2=3.20, P>0.05). Results of multivariate analysis showed that left thoracic surgical approach, preopera-tive neutrophil count, vascular invasion, perineural invasion, pathological T2-4 stage, pathological N2-3 stage, and postoperative pneumonia were independent risk factors affecting postoperative survival of 285 patients in the training set ( hazard ratio=1.466, 1.037, 1.482, 1.549, 5.268, 7.727, 22.202, 2.539, 2.686, 1.425, 95% confidence interval as 1.026-2.096, 1.003-1.073, 1.008-2.179, 1.105-2.170, 1.201-23.099, 1.833-32.576, 4.734-104.128, 1.577-4.087, 1.631-4.422, 1.018-1.994, P<0.05). (2) Construction and validation of machine learning prediction models. Independent risk factors affecting postoperative survival were included to construct RSF, GBM, LASSO-Cox, CoxBoost, survivalsvm, XGBoost, SuperPC, and plsRcox machine learning prediction models. Results of Delong test showed that there were significant differences in the AUC of RSF and GBM from the other six models ( P<0.05). Results of time-dependent ROC curve showed that all 8 machine learning predic-tion models had good discriminative ability in the training cohort, among which the RSF machine learning prediction model had the best predictive performance. Results of calibration curve showed that the RSF machine learning prediction model fitted well for predicting postoperative 1-, 2-, and 3-year overall survival in the training cohort, with high consistency with actual results. Results of decision curve analysis showed that within a threshold range of 0-0.80, the RSF machine learning prediction model provided a better overall net benefit. Further analysis showed that in the validation set, the AUC of RSF machine learning prediction model for postoperative 1-, 2-, and 3-year survival prediction were 0.786 (95% confidence interval as 0.609-0.962), 0.774 (95% confidence interval as 0.676-0.873), and 0.750 (95% confidence interval as 0.652-0.848), respectively. Results of calibration curve showed that the RSF machine learning prediction model fitted well for predicting postopera-tive 1-, 2-, and 3-year overall survival in the validation set, with high consistency with actual results. In the training set, the optimal cutoff value of the RSF machine learning prediction model risk score was 11.7. Patients with risk score ≥11.7 were classified as the high-risk group, and those with risk score <11.7 as the low-risk group. The median survival times of the two groups were 18.0 months and >36.0 months, respectively, showing a significant difference between them ( χ2=73.30, P<0.05). In the validation set, the optimal cutoff value of the RSF machine learning prediction model risk score was 11.7. Patients with risk score ≥11.7 were classified as the high-risk group, and those with risk score<11.7 as the low-risk group. The median survival times of the two groups were 17.0 months and>36.0 months for the high-risk and low-risk groups, respectively, showing a significant difference between them ( χ2=35.20, P<0.05). Conclusions:Left thoracic surgical approach, preoperative neutrophil count, vascular invasion, perineural invasion, pathological T2-4 stage, pathological N2-3 stage, and postoperative pneumonia are independent risk factors affecting survival of esophageal cancer patients after radical resection. The RSF machine learning prediction model constructed based on these factors can effectively distinguish the survival prognosis of high-risk and low-risk patients.

Objective:To explore differences in the efficacy and safety of ruxolitinib in patients with myelofibrosis by age and to identify prognostic factors by analyzing clinical features and characteristics of chromosomes and gene mutations.Methods:This study retrospectively analyzed 188 patients with myelofibrosis who received ruxolitinib in the Department of Hematology, Qilu Hospital, Shandong University from January 1, 2017, to July 1, 2024. According to age at diagnosis, the patients were divided into the middle-aged group (≤55 years), young elderly group (56-65 years), and elderly group (>65 years). Clinical features, the characteristics of chromosomes and gene mutations, and the efficacy and safety of ruxolitinib treatment were compared across the three age groups. Independent factors influencing overall survival were identified through Cox proportional risk regression analysis.Results:Before treatment, the elderly group had more underlying comorbidities, a heavier symptom burden, higher leukocyte count, higher proportion and frequency of JAK2 mutations, and lower proportion of CALR mutations. The incidence of nondriver gene mutations was significantly higher in the young elderly group. After ruxolitinib treatment, the degree of reduction in spleen size did not differ significantly among the three groups. The length of the palpable spleen below the left costal margin reduced by more than 50% from baseline in 50.9% (27/53) of the patients in the middle-aged group, 43.5% (27/62) in the young elderly group, and 45.5% (20/44) in the elderly group ( P=0.720). No significant difference was observed among the three groups in the degree of reduction in Myeloproliferative Neoplasm Symptom Assessment Form (10-item version) score ( P=0.153), with a reduction in total symptom score by more than 50% achieved by 54.0% (27/50), 60.3% (41/68), and 66.7% (34/51) of the patients from the three groups, respectively ( P=0.429). The most common hematological adverse events were anemia and thrombocytopenia, while the most common nonhematological adverse events were electrolyte disturbance, elevated transaminase activity, and pulmonary infection. Multivariate analysis indicated that in ruxolitinib-treated patients with myelofibrosis, poor overall survival was independently predicted by increased age, reduced hemoglobin, percentage of bone marrow blasts ≥ 1%, absence of JAK2 mutations, chromosomal abnormalities, ≥2 high-molecular-risk mutations, and TP53 mutations. Conclusions:Patients with myelofibrosis stratified by age exhibited heterogeneous clinical features and gene mutation profiles but similar efficacy of ruxolitinib treatment and occurrence of adverse events.

Objective To investigate the clinicopathological factors associated with pathological complete response(pCR)of axillary metastatic lymph nodes in breast cancer patients after neoadjuvant chemotherapy(NAC),and to analyze the postoperative survival.Methods A total of 116 patients with breast cancer with axillary lymph node metastasis were collected from Jiaxing Hospital of TCM,Jiaxing Maternity and Child Health Care Hospital and The First Hospital of Jiaxing.Univariate analysis was used to analyze the relationship between clinicopathological factors and the pCR of axillary lymph node metastasis in breast cancer after NAC.Binary Logistic regression was used to analyze the independent predictors of the pCR of axillary lymph node metastasis in breast cancer after NAC.Kaplan-Meier survival curve was used to analyze the disease-free survival rate and overall survival rate of patients with and non-pCR of axillary metastatic lymph nodes.Results Among 116 patients,52 cases of axillary metastatic lymph nodes achieved pCR after NAC,accounting for 44.83%.Univariate analysis showed that age,vascular invasion,pCR of primary breast tumor,the difference of Ki67 before and after NAC,NAC regimen,and the efficacy of NAC were statistically significant between breast cancer patients with pCR and those non-pCR(P<0.05).Binary Logistic regression analysis showed that age,vascular invasion and pCR of primary breast tumor were independent predictors of pCR of axillary metastatic lymph nodes(P<0.05).The 5-year disease-free survival rate(80.40%vs.54.60%)and overall survival rate(90.4%vs.70.10%)of patients with pCR and non-pCR of axillary metastatic lymph nodes were compared.Conclusion Some breast cancer patients with axillary lymph node metastasis can reach pCR in lymph nodes after NAC.Analyzing the correlation between clinical pathological factors and pCR of axillary metastatic lymph nodes after NAC,it was found that pCR of axillary metastatic lymph nodes after NAC is related to age≤50 years old,no vascular infiltration,and primary breast tumor pCR.At the same time,it was found that patients with axillary metastatic lymph node pCR had a better prognosis than those with non-pCR.

Objective To explore the mechanisms of Buyang Huanwu Decoction(BYHWD)in reducing oxidative stress levels to protect the blood-brain barrier(BBB)in cerebral ischemia/reperfusion injury(CIRI)rats.Methods A middle cerebral artery occlusion/reperfusion(MCAO/R)model in rats was established via wire embolization method.PeriCam PSI laser speckle flow imaging was applied to detect whether the model was successfully established.Neurological deficits in the rats were evaluated by Zea Longa score,and histopathological changes in the rat brain were observed by HE staining.The degree of brain edema was detected by the dry and wet weight method.BBB permeability was detected by Evans blue staining,and ultrastructural changes to the BBB were observed by transmission electron microscopy.The levels of ROS,MDA and SOD activities,which are related to oxidative stress,were detected using kits.The expression levels of matrix metalloproteinase-9(MMP-9)were detected by immunohistochemical staining and Western blot.The expression levels of Occludin,ZO-1,and Claudin-5 tight junction proteins were determined via immunofluorescence and Western blot.Results BYHWD reduced neurological deficit scores,alleviated brain histopathological damage,alleviated BBB structural disruption,prolonged the appearance of dense regions in the tight junction structure,attenuated edema of the brain on the ischemic side,and reduced BBB permeability in MCAO/R rats.BYHWD decreased the levels of ROS and MDA,increased the activity of SOD,decreased the expression levels of MMP-9,and increased the expression levels of Occludin,Claudin-5 and ZO-1.Conclusions BYHWD can increase BBB tight junction protein expression levels,reduce the permeability of the BBB,protect the ultrastructure of the BBB,and reduce brain edema,and its mechanisms may be related to its antioxidant activity and inhibition of MMP-9 activation.

Acute myocarditis(AM)may rapidly progress to fulminant myocarditis(FM),but lacks special clinical presentation.Multimodal echocardiography combined conventional transthoracic echocardiography,two-dimensional and three-dimensional speckle tracking imaging,myocardial contrast echocardiography and so on is helpful to detecting AM in early stage and assessing the severity,being of great value for clinical decision-making and prognostic evaluation.The research progresses of multimodal echocardiography in AM were reviewed in this article.

Speckle tracking echocardiography(STE)can be used to quantitatively evaluate cardiac function,detect abnormalities of the global and local cardiac wall motion,also help to understand the subtle changes of myocardial function,having high value for early diagnosis of cardiac remodeling after myocardial infarction(MI)and predicting risk and development of heart failure.The research progresses of STE for evaluating cardiac remodeling and heart failure after MI were reviewed in this article.

Speckle tracking echocardiography(STE)can be used to quantitatively evaluate cardiac function,detect abnormalities of the global and local cardiac wall motion,also help to understand the subtle changes of myocardial function,having high value for early diagnosis of cardiac remodeling after myocardial infarction(MI)and predicting risk and development of heart failure.The research progresses of STE for evaluating cardiac remodeling and heart failure after MI were reviewed in this article.

Objective:To observe the clinical characteristics of patients with familial vitreous amyloidosis (FVA) and the efficacy of vitrectomy (PPV) and the occurrence of complications.Methods:A retrospective clinical study. From June 2009 to March 2020, 32 eyes of 18 patients from 3 FVA families who were diagnosed and treated by PPV at Department of Ophthalmology of Jiaxing TCM Hospital were included in the study. Among them, there were 12 males with 22 eyes and 6 females with 10 eyes. The average age of onset was 42.28±3.25 years; the average duration of disease was 3.75±3.93 years. All the affected eyes underwent best corrected visual acuity (BCVA) and B-mode ultrasound examination. A logarithmic visual acuity chart was used in the BCVA examination, which was converted to the logarithmic minimum angle of resolution (logMAR) visual acuity when recorded. The average logMAR BCVA of the affected eye was 1.72±0.53; the intraocular pressure was less than 21 mm Hg (1 mm Hg=0.133 kPa). The vitreous body of the affected eye was obviously cloudy. All the affected eyes underwent standard three-channel PPV through the flat part of the ciliary body, and vitreous specimens were collected for pathological examination during the operation. Peripheral venous blood of probands from 3 families was collected, and the whole exome gene sequencing was performed. The follow-up time after surgery was ≥6 months. The patient's clinical characteristics, fundus lesions in PPV, changes in BCVA after surgery, and complications was observed. One-way analysis of variance or t test was performed for measurement data comparison; χ2 test was performed for count data comparison. Results:The vitreous body of the affected eye showed gray-white dense and thick flocculent changes, and the posterior capsule attached to the lens showed "foot disc-like" turbidity; later the lens was mainly cystic opacity. Pathological examination of the vitreous body showed positive staining of Congo red; under a polarized light microscope, it showed apple green dots and sheet-like birefringence. The genetic test results showed that there was a c.307G>C (p.Gly103Arg) missense mutation in the TTR gene of the proband in Family 2. Peripheral retinal hemorrhages in 4 eyes (12.5%, 4/32), retinal tears in 5 eyes (15.6%, 5/32), retinal degeneration in 4 eyes (12.5%, 4/32), retinal detachment were found in PPV 3 eyes (9.4%, 3/32). The vitreous body was filled with C 3F 8 and silicone oil respectively for 2, 1 eye. Six months after the operation, the logMAR BCVA of the affected eye was 0.39±0.32, which was significantly higher than that before the operation, and the difference was statistically significant ( t=15.131, P=0.000). After the operation, high intraocular pressure occurred in 2 eyes (6.3%, 2/32), secondary glaucoma in 1 eye (3.1%, 1/32), retinal detachment in 2 eyes (6.3%, 2/32), neovascular glaucoma (NVG) in 2 eyes (6.3%, 2/32), cataract in 10 eyes (31.3%, 10/32). Conclusion:The vitreous body of FVA eyes are gray-white dense, thick and flocculent, attached to the posterior lens capsule, showing "foot disc-like" turbidity; PPV treatment can effectively improve the BCVA of the FVA eyes; secondary glaucoma, secondary retinal detachment, NVG can occur after surgery.