Objective To explore the role of an artificial intelligence(AI)model based on real-time object detection network in fetal facial ultrasound examination.Methods With the normal fetal facial ultrasound standard plane(FFUSP)at 20-24 weeks of gestation as the research object,a FFUSP recognition model based on real-time object detection network was constructed.The recognition accuracy of the model for FFUSP and the anatomical structures were analyzed,and the clinical value was evaluated by analyzing its performance in identifying FFUSP in 119 cases of fetal ultrasound images.Results The overall precision,recall rate,mAP@.5 and mAP@.5:.95 of the AI model were 97.8%,98.5%,98.1%and 61.0%,respectively.The clinical validation showed that the AI model had a sensitivity,specificity,positive predictive value,negative predictive value and accuracy of 100.0%,98.5%,87.4%,100.0%and 98.7%for facial anatomy recognition,and the results were highly consistent with the classification of fetal ultrasound experts(k=0.925,P<0.001).The recognition accuracy of the model for 3 types of standard planes reached 100%;and the average speed of dynamic video detection was 33.93 frames per second.Conclusion The FFUSP recognition model based on real-time object detection network exhibits excellent performance,and it can be applied to real-time ultrasound diagnosis,teaching and intelligent quality evaluation.

Objective To assess the effect of ultrasonic thyroid artificial intelligence(AI)-assisted diagnostic system(AI-assisted diagnostic system)for diagnosing medullary thyroid carcinoma(MTC)compared with different physicians and taken papillary thyroid carcinoma(PTC)as the controls.Methods Totally 63 MTC,70 PTC and 62 benign thyroid nodules confirmed by pathology were enrolled.AI-assisted diagnostic system was utilized to analyze thyroid nodules and identify the likelihood of malignancy,and the probability value threshold was set at ≥0.40.All thyroid nodules were retrospectively reviewed and categorized by 3 physicians(1 senior physician,1 attending physician and 1 junior physician)according to Chinese thyroid imaging reporting and data system(C-TIRADS).The efficacy of AI-assisted diagnostic system and physicians for diagnosing MTC and PTC were evaluated.Results AI-assisted diagnostic system showed lower sensitivity,specificity,positive predictive value,negative predictive value,accuracy,and area under the curve(AUC)for diagnosing MTC and PTC compared with physicians.Significant differences of AUC were found between senior physician and AI-assisted diagnostic system,as well as between attending physician and AI-assisted diagnostic system for diagnosing MTC and PTC(all P＜0.01),while no significant difference of AUC was between junior physicians and AI-assisted diagnostic system(both P＞0.05).The sensitivity,specificity,positive predictive value,negative predictive value,accuracy and AUC for AI-assisted diagnostic system for diagnosing MTC were all lower than those for diagnosing PTC,but the AUC was not significantly different(P＞0.05).Conclusion Ultrasonic thyroid AI-assisted diagnostic system had relatively high value for diagnosing MTC.

Objective:To investigate the correlation of LymphGen genotyping with the clinicopathologic characteristics, efficacy and prognosis in patients with newly diagnosed diffuse large B-cell lymphoma (DLBCL).Methods:A retrospective case series study was conducted. The clinicopathological data and follow-up information of 132 DLBCL patients diagnosed and treated in the First Affiliated Hospital of Soochow University from January 2016 to January 2022 were collected. LymphGen genotyping was made based on the results of second-generation sequencing. The distributions of the main subtypes in the whole group and the stratification of all clinicopathological features were analyzed. The short-term efficacy of patients with different gene subtypes was compared. Survival analysis of patients with different gene subtypes was performed by using the Kaplan-Meier method.Results:Among the 132 patients, 69 were males and 63 were females. The median age was 60 years, with the age ranging from 13 to 87 years. Hans typing: germinal center B cell (GCB) type was detected in 49 cases, non-GCB type was detected in 81 cases, and the remaining 2 cases were unknown. Ann Arbor staging: 31 cases with stage Ⅰ-Ⅱ, 89 cases with stage Ⅲ-Ⅳ, and 9 primary central nervous system lymphoma (PCNSL) cases without stage, and the remaining 3 cases with unknown stage. Among the 132 patients, 64 cases (48.5%) were genotyped with LymphGen, including 6 cases (4.5%) of MCD subtype, 18 cases (13.6%) of A53 subtype, 17 cases (12.9%) of BN2 subtype, 3 cases (2.3%) of EZB subtype, 5 cases (3.8%) of ST2 subtype, and 15 cases (11.4%) of composite subtype, and 68 cases (51.5%) of the other subtypes; N1 subtype was not detected. The differences in the proportion of MCD subtype [5.0% (3/60) vs. 4.2% (3/71)], A53 subtype [16.7% (10/60) vs. 11.3% (8/71)], BN2 subtype [6.7% (4/60) vs. 18.3% (13/71)], EZB subtype [5.0% (3/60) vs. 0 (0/71)], ST2 subtype [5.0% (3/60) vs. 2.8% (2/71)], composite subtype [18.3% (11/60) vs. 5.6% (4/71)], other types [43.3% (26/60) vs. 57.7% (41/71)] were statistically significant between the patients with lactate dehydrogenase (LDH) < 245 U/L and those with LDH ≥245 U/L ( P = 0.023). There were no statistically significant differences in genotype distribution among subgroups with different age, gender, B symptoms, Hans typing, primary site, involvement site, Ann Arbor stage, international prognostic index score/international extranodal lymphoma study group score (all P > 0.05). After 4-6 courses treatment in PCNSL patients and 6-8 courses of standard first-line treatment in non-PCNSL patients, 17 patients with BN2 subtype [including 9 cases of complete remission (CR) and 4 cases of partial remission (PR)] and 3 patients with EZB subtype (including 2 cases of CR) had the higher proportion of those achieving good treatment outcomes. However, 15 patients with the composite subtype showed the worst outcomes including 5 cases of CR, 4 cases of PR, 1 case of stable disease, 3 cases of disease progression, and 2 death cases. The CR rates of the composite subtype group, non-composite subtype group, and other groups were 33.3% (5/15), 44.9% (22/49), and 66.2% (45/68), respectively; and the difference among these groups was statistically significant ( P = 0.034). The CR rate of composite type patients with BN2 subtype was higher compared to composite subtype patients without BN2 subtype (5/8 vs. 0/7), and the difference was statistically significant ( P = 0.023); 7 patients with A53 subtype combined with other subtypes except BN2 subtype did not achieve CR; 2 cases had PR, 3 cases had disease progression and 2 cases died. The median follow-up time was 26 months (ranging from 1 to 86 months) until the last follow-up in March 2023. There were no statistically significant differences in overall survival and progression-free survival among patients with different gene subtypes (all P > 0.05). Conclusions:The distribution of gene subtypes in DLBCL patients may be correlated with LDH levels. Patients with different gene subtypes show variations in short-term efficacy. The composite type patients with A53 subtype and without BN2 subtype have poor treatment outcomes, but no differences in overall survival and progression-free survival of patients with different gene subtypes are observed.

Objective:To investigate the predictive value of mid-regional proadrenomedullin (MR-proADM) on poor prognosis of low-risk patients with sepsis.Methods:This was a prospective cohort study. Patients with sepsis admitted to the Emergency Intensive Care Unit of China Rehabilitation Research Center from December 2018 to December 2020 were included in this study. The patients were divided into the low-risk group (SOFA≤7) and medium-high-risk group (SOFA>7) according to the sequential organ failure assessment (SOFA) score, and the clinical characteristics of the two groups were compared. Proportional hazards regression model (COX regression model) was used to investigate the risk factors of 28-day mortality in the low-risk and medium-high-risk group. The predictive ability of MR-proADM, C-reactive protein (CRP), lactic acid (Lac), interleukin-6 (IL-6), SOFA score, and acute physiology and chronic health evaluationⅡ (APACHE Ⅱ) score for the prognosis in each group was evaluated by receiver operating characteristic (ROC) curve. The outcomes of patients with different concentration of MR-proADM in the low-risk group were compared.Results:Totally 205 patients with sepsis were included, and the 28-day mortality was 41.0% (84/205). There were significant differences in the number of organ dysfunction, acute kidney injury, use of vasoactive drugs, Lac, IL-6, SOFA score and APACHEⅡ score between the two groups ( P<0.05). Cox regression model showed that age, MR-proADM, mechanical ventilation, IL-6 and APACHEⅡ score were the risk factors of 28-day death in the low-risk group, while MR-proADM, Lac, SOFA score and APACHEⅡ score were the risk factors of 28-day mortality in the medium-high-risk group. In each group, MR-proADM had a good predictive ability for the prognosis of patients with sepsis ( P<0.001). Especially in low-risk patients with sepsis, the predictive ability of MR-proADM was better than other indicators. Kaplan-Meier survival curve suggested that the patients with MR-proADM >2.53 nmol/L had worse prognosis than those with MR-proADM ≤2.53 nmol/L, and the difference was statistically significant ( P<0.001). In the low-risk group, the mortality of patients increased from 7.8% to 58.2% if MR-proADM >2.53 nmol/L. Conclusions:MR-proADM is a risk factor for 28-day mortality in patients with sepsis, and MR-proADM can early identify the poor prognosis of low-risk patients with sepsis.

Objective:To investigate the clinical value of nutritional indexes including body mass index (BMI), albumin (ALB), nutrition risk screening 2002 (NRS 2002) and the nutrition risk in critically ill score (NUTRIC) in 28-day prognosis of patients with sepsis related acute kidney injury (AKI).Methods:A prospective cohort study was conducted. Patients with sepsis treated in the emergency intensive care unit (EICU) of China Rehabilitation Research Center from December 1, 2018 to December 1, 2020 were observed for 7 days. Patients with sepsis related AKI were enrolled in this study. The gender, age, BMI, basic diseases, shock, number of affected organs, length of hospital stay, ALB, mechanical ventilation (MV) and vasoactive drug use, sequential organ failure score (SOFA), rapid sequential organ failure score (qSOFA) and acute physiology and chronic health evaluationⅡ(APACHEⅡ) were recorded. The NRS 2002 score and NUTRIC score were calculated. Cox regression model was used to analyze the risk factors of 28-day mortality in patients with sepsis related AKI. The receiver operator characteristic curves (ROC curves) were drawn and the areas under the ROC curves (AUC) were calculated, and the value of BMI, ALB, NRS 2002 score and NUTRIC score was analyzed to predict 28-day mortality in patients with sepsis related AKI. Kaplan Meier survival curves were used to analyze the effects of NRS 2002 score and NUTRIC score stratification on the 28 day prognosis of patients with sepsis related AKI.Results:A total of 140 patients with sepsis related AKI were enrolled, including 73 survival patients and 67 died patients within 28 days. The 28-day mortality was 47.9% (67/140). BMI in the survival group was significantly higher than that in the death group [kg/m 2: 22.0 (19.5, 25.6) vs. 20.7 (17.3, 23.9), P < 0.05], and NRS 2002 score and NUTRIC score were significantly lower than those in the death group [NRS 2002 score: 5 (4, 6) vs. 7 (6, 7), NUTRIC score: 6 (5, 7) vs. 7 (6, 9), both P < 0.05]. The ALB of the survival group was slightly higher than that of the death group, but the difference was not statistically significant. Cox regression analysis showed that NRS 2002 score and NUTRIC score were independent risk factors for 28-day death in patients with sepsis related AKI. ROC curve analysis showed that NUTRIC score had the strongest predictive ability for 28-day death [AUC = 0.785, 95% confidence interval (95% CI) was 0.708-0.850], followed by NRS 2002 score (AUC = 0.728, 95% CI was 0.647-0.800), but there was no significant difference between them. Compared with NRS 2002 score, the predictive ability of BMI and ALB was poor. Kaplan-Meier curve analysis showed that the prognosis of patients with NRS 2002 score≥5 was significantly worse than that of patients with NRS 2002 score < 5 (28-day cumulative survival rate: 42.1% vs. 75.6%, Log-Rank test: 2 = 11.884, P = 0.001), and the prognosis of patients with NUTRIC score≥6 was significantly worse than that of patients with NUTRIC score < 6 (28-day cumulative survival rate: 40.4% vs. 86.1%, Log-Rank test: 2 = 19.026, P = 0.000). Conclusions:Patients with sepsis related AKI have high nutritional risk. Both NRS 2002 score and NUTRIC score have good predictive value for the prognosis of patients with sepsis related AKI, while BMI and ALB have low predictive value. Due to the complex calculation of NUTRIC score, NRS 2002 score may be more suitable for emergency department.

Objective:To investigate the prognostic factors associated with unresectable (stage Ⅲa-Ⅳ, according to the 7th edition of the AJCC cancer staging manual) lung squamous cell carcinoma.Methods:We retrospectively analyzed 350 patients with inoperable locally advanced, recurrent or metastatic lung squamous cell carcinoma who were admitted to the First Affiliated Hospital of Chinese Medical University from January 2005 to June 2018. The clinical pathological data, treatment and survival follow-up information of the patients were collected. Kaplan-Meier survival was used to compare the overall survival rate of different risk groups. Univariate analysis and multivariate Cox regression analysis were used to determine the independent prognostic factors.Results:A total of 350 patients were enrolled. The median overall survival (OS) of these patients was 16.7 months. Univariate analysis showed the stage, Eastern Cooperative Oncology Group(ECOG), first-line chemotherapy evaluation (RECIST version 1.1), radiation therapy, number of systemic chemotherapy lines, carcinoembryonic antigen (CEA), cancer antigen 125 (CA125), C reactive protein (CRP), lactate dehydrogenase (LDH), whether liver, brain, boneor metastasis were associated with the OS of patients with advanced lung squamous cell carcinoma (all P<0.05). Multivariate analysis showed that ECOG score ( HR=1.855, 95% CI: 1.063-3.239, P=0.030), whether underwent lung resection ( HR=0.476, 95% CI: 0.302-0.751, P=0.001), first-line chemotherapy evaluation [stable disease (SD): HR=0.293, 95% CI: 0.159-0.540, P<0.001; complete response (CR)+ partial response (PR): HR=0.223, 95% CI: 0.120-0.413, P<0.001], CRP ( HR=1.715, 95% CI: 1.080-2.723, P=0.042), LDH ( HR=1.116, 95% CI: 0.780-1.596, P=0.002) and CEA ( HR=1.855, 95% CI: 1.361-2.528, P<0.001) before chemotherapy, liver metastasis ( HR=2.453, 95% CI: 1.461-4.120, P=0.001) are independent prognostic factors for patients with unresectable lung squamous cell carcinoma. Conclusion:The ECOG score, surgical treatment history, first-line chemotherapy, LDH, CEA and CRP before chemotherapy, liver metastasis are independent prognostic factors for patients with advanced lung squamous cell carcinoma.

Objective:To investigate the prognostic factors associated with unresectable (stage Ⅲa-Ⅳ, according to the 7th edition of the AJCC cancer staging manual) lung squamous cell carcinoma.Methods:We retrospectively analyzed 350 patients with inoperable locally advanced, recurrent or metastatic lung squamous cell carcinoma who were admitted to the First Affiliated Hospital of Chinese Medical University from January 2005 to June 2018. The clinical pathological data, treatment and survival follow-up information of the patients were collected. Kaplan-Meier survival was used to compare the overall survival rate of different risk groups. Univariate analysis and multivariate Cox regression analysis were used to determine the independent prognostic factors.Results:A total of 350 patients were enrolled. The median overall survival (OS) of these patients was 16.7 months. Univariate analysis showed the stage, Eastern Cooperative Oncology Group(ECOG), first-line chemotherapy evaluation (RECIST version 1.1), radiation therapy, number of systemic chemotherapy lines, carcinoembryonic antigen (CEA), cancer antigen 125 (CA125), C reactive protein (CRP), lactate dehydrogenase (LDH), whether liver, brain, boneor metastasis were associated with the OS of patients with advanced lung squamous cell carcinoma (all P<0.05). Multivariate analysis showed that ECOG score ( HR=1.855, 95% CI: 1.063-3.239, P=0.030), whether underwent lung resection ( HR=0.476, 95% CI: 0.302-0.751, P=0.001), first-line chemotherapy evaluation [stable disease (SD): HR=0.293, 95% CI: 0.159-0.540, P<0.001; complete response (CR)+ partial response (PR): HR=0.223, 95% CI: 0.120-0.413, P<0.001], CRP ( HR=1.715, 95% CI: 1.080-2.723, P=0.042), LDH ( HR=1.116, 95% CI: 0.780-1.596, P=0.002) and CEA ( HR=1.855, 95% CI: 1.361-2.528, P<0.001) before chemotherapy, liver metastasis ( HR=2.453, 95% CI: 1.461-4.120, P=0.001) are independent prognostic factors for patients with unresectable lung squamous cell carcinoma. Conclusion:The ECOG score, surgical treatment history, first-line chemotherapy, LDH, CEA and CRP before chemotherapy, liver metastasis are independent prognostic factors for patients with advanced lung squamous cell carcinoma.

Objective:To analyze Traditional Chinese Medicine(TCM) prescriptions in COVID-19 patients in Shanghai area.Methods:Two hundred and forty patients were enrolled in the study, including 19 mild cases, 199 moderate cases, 16 severe case and 6 critical cases. The COVID-19 formula in Shanghai area was extracted and input in TCM Inheritance platform. Data association method such as software association rules,improved mutual information method,complex system entropy clustering,unsupervised entropy hierarchical clustering were used to analyze the frequency,herb flavor and meridian, combination rule and core combination of different types of Chinese herbs in the treatment of COVID-19 in Shanghai area.Results:According to the frequency analysis of 240 prescriptions of Chinese medicine,194 herbs were found. The COVID-19 formula herbs were all "cold", the frequency of use in mild, moderate, severe and critical cases was [46.02%(104/226), 46.31%(1 230/2 656), 37.06%(146/394), 39.24%(31/79)]. The flavor was mainly "bitter" and the frequency of use in 4 types of disease were [36.53%(122/332), 37.33%(1 445/3 857), 35.96%(205/564), 33.62%(39/113)]. Scutellaria was the most frequently used TCM of "bitter and cold". The drugs used were mainly lung,stomach and spleen meridians. By comparing the formulas between mild and moderate cases,herb combinations with the highest frequency were all "scutellaria glycyrrhiza" and "tangerine glycyrrhiza". The formulas for 19 mild cases were collected,and 197 drug combinations were counted, and 125 Chinese medicine association rules,including 13 Chinese herbs. The formulas were extracted in 199 moderate cases of COVID-19, a total of 92 drug combinations and 38 Chinese medicine association rules were collected,including 19 Chinese herbs. In 16 severe cases, a total of 62 drug combination models and 46 Chinese medicine association rules were collected,including 17 Chinese herbs. For the 6 critical cases,80 Chinese medicine prescriptions were combined,and 10 Chinese medicine association rules, including 12 Chinese herbs.Conclusions:The herbal prescriptions of COVID-19 in Shanghai are characterized by clearing away heat and resolving dampness. By analyzing prescription rules with complex system entropy clustering, association compatibility ideas of different types of traditional Chinese medicine are found to be different among four types of COVID-19 cases. Analyzing the connection rules in formulas, by using the theory of TCM and pharmacology of traditional Chinese medical formula in different COVID-19 patients may be helpful for general practitioners.

Objective:To explore the accuracy of array comparative genomic hybridization(aCGH) in the unexpected detection of Duchenne muscular dystrophy ( DMD) gene duplication/deletion in prenatal diagnosis. Methods:A retrospective analysis was performed on 31 cases with DMD gene duplication/deletion detected by aCGH among 5 025 prenatal diagnosis samples without family history of DMD in Henan Provincial People's Hospital from July 2018 to December 2019. The multiplex ligation-dependent probe amplification (MLPA) method was used to verify the above results. The American College of Medical Genetics and Genomics (ACMG) guideline was referred for pathogenicity analysis of the detected duplicates/deletions. Descriptive analysis was adopted in analysis. Results:The total unexpected DMD gene duplication/deletion rate was 0.62% (31/5 025), among which 25 cases were with microduplication/microdeletion ≤ 200 kb and six were >200 kb; there were 24 cases of deletion, seven cases of duplication; exon or intron duplication/deletion were accounted for 19 and 12 cases, respectively. According to the five classification standards of ACMG guideline, there were 17 cases with pathogenic variants and 14 cases with uncertain pathogenicity/likely benign variants. Of the 19 with exon mutations, 17 cases were DMD intragenic variants, and two cases involved variants in and outside DMD gene, which were verified by MLPA whose results were all positive. Conclusions:The duplication/deletion of exon region of DMD gene detected by aCGH technique is accurate and reliable, which plays an important role in the diagnosis of DMD. For these cases involved both internal and external regions of DMD gene, aCGH can identify the upstream and downstream breaking points of DMD gene, thus providing the basis for ACMG grading.

An expert consensus about the clinical diagnosis and treatment of dry eye was documented in 2013 by a corneal expert group of Chinese Ophthalmological Society.However, due to the rapid development of diagnostic and therapeutic devices of dry eye, researoh on dry eye has made significont progress in China since then.Consequently, the existing expert consensus cannot meet the needs of clinical practice.It is therefore urgent to develop a series of standardized diagnosis and treatment protocols, and publish a new consensus of experts and an operating guideline.At the same time, basic, clinical, and translational research on dry eye should be promoted to provide better services to the patients with dry eyes.On January 12, 2019 many experts in the field of dry eye in China held a panel discussion of dry eye study in Guangzhou to analyze the current development status and trends in the field of dry eye in China and abroad.In that meeting, opinions and recommendations were put forward based on a new understanding of the definition of dry eye, new concepts of dysfunctional dry eye, advances its diagnosis and classification, refinement and standardization of dry eye treatment, and the future development of dry eye research.