Comparación de desempeño de algoritmos para el diagnóstico de sífilis / Performance comparison of algorithms for the diagnosis of syphilis / Comparação de desempenho de algoritmos para o diagnóstico da sífilis

Resumen La sífilis es una de las infecciones de transmisión sexual con mayor incidencia en la Argentina. Para su diagnóstico, el Ministerio de Salud de la Nación avala distintos algoritmos, entre ellos, el algoritmo tradicional y el reverso. En el algoritmo tradicional, la VDRL constituye la prueba de screening y los resultados positivos se confirman con la prueba treponémica de aglutinación de partículas (TPPA). El algoritmo reverso con un test rápido, avalado más recientemente, consiste en la realización de un test rápido treponémico como screening y posterior VDRL en las muestras que resulten positivas. Se realizó una comparación entre ambos algoritmos para evaluar si era factible y conveniente la implementación del algoritmo reverso con un test rápido en el laboratorio del H.I.G.A. Dr. Oscar Alende. El objetivo fue determinar la concordancia entre el algoritmo tradicional, utilizado actualmente en la institución (VDRL seguido por TPPA), y el nuevo algoritmo propuesto (test rápido treponémico Alere Determine Syphilis TP seguido por VDRL-USR). Para ello se realizó un estudio prospectivo de desempeño de métodos cualitativos. Se realizó VDRL-USR, TPPA y test rápido Alere Determine Syphilis TP en muestras de 580 pacientes, de los cuales 558 cumplieron con los criterios de inclusión. Se obtuvieron 51 muestras con resultados positivos y 507 con resultados negativos para el diagnóstico de sífilis por ambos algoritmos, con un porcentaje de concordancia global del 100%, lo cual indica que podría reemplazarse el algoritmo tradicional por el reverso en aquellas situaciones que lo requieran en la población estudiada.

Abstract Syphilis is one of the sexually transmitted infections with the highest incidence in Argentina. For its diagnosis, the Ministry of Health of the Nation endorses different algorithms, among them, the traditional algorithm and the reverse. In the traditional algorithm, VDRL constitutes the screening test and positive results are confirmed with particle agglutination assay TPPA. The reverse algorithm with rapid test, endorsed more recently, consists of performing a rapid treponemal test as screening and subsequent VDRL in the samples that are positive. A comparison was made between both algorithms to evaluate if the implementation of the reverse algorithm with rapid test in Dr. Oscar Alende Hospital would be feasible and convenient. The objective of this work was to determine the concordance between the traditional algorithm, currently used in the institution (VDRL followed by TPPA), and the new algorithm proposed (rapid treponemal test Alere Determine Syphilis TP followed by VDRL-USR). For that purpose, a prospective study of the performance of qualitative methods was carried out. VDRL-USR, TPPA and Alere Determine Syphilis TP Rapid Test were performed on samples from 580 patients, of which 558 met the inclusion criteria. A total of 51 samples with positive results and 507 with negative results for the diagnosis of syphilis were obtained by both algorithms, with an overall concordance percentage of 100%, which indicates that the traditional algorithm could be replaced by the reverse in those situations that require it in the studied population.

Resumo A sífilis é uma das infecções sexualmente transmissíveis com maior incidência na Argentina. Para o seu diagnóstico, o Ministério da Saúde da Nação endossa diversos algoritmos, incluindo o algoritmo tradicional e o reverso. No algoritmo tradicional, o VDRL constitui o teste de triagem e os resultados positivos são confirmados com o teste treponêmico de aglutinação de partículas (TPPA). O algoritmo reverso com teste rápido, endossado mais recentemente, consiste na realização de um teste rápido treponêmico como triagem e posterior VDRL nas amostras positivas. Foi feita uma comparação entre os dois algoritmos para avaliar se a implementação do algoritmo reverso com um teste rápido no laboratório H.I.G.A. Dr. Óscar Alende era viável e conveniente. O objetivo foi determinar a concordância entre o algoritmo tradicional, atualmente utilizado na instituição (VDRL seguido de TPPA), e o novo algoritmo proposto (teste rápido treponêmico Alere Determine Syphilis TP seguido de VDRL-USR). Para tanto, foi realizado um estudo prospectivo de desempenho de métodos qualitativos. O VDRL- -USR, o TPPA e o teste rápido Alere Determine Syphilis TP foram realizados em amostras de 580 pacientes, dos quais 558 preencheram os critérios de inclusão. Foram obtidas 51 amostras com resultados positivos e 507 com resultados negativos para o diagnóstico de sífilis por ambos os algoritmos, com um percentual de concordância global de 100%, o que indica que o algoritmo tradicional poderia ser substituído pelo reverso nas situações que o exigissem na população estudada.

Algoritmo para la selección de colgajos perforantes perimamarios en reconstrucción inmediata poscirugía conservadora / Algorithm to select chest wall perforator flaps in immediate conservative breast surgery reconstruction

RESUMEN Antecedentes: los colgajos perforantes perimamarios son de gran utilidad en la reconstrucción mamaria inmediata en cirugía conservadora. Objetivo: describir los resultados del empleo de un algoritmo sobre colgajos perforantes perimamarios en la reconstrucción mamaria inmediata después de cirugía conservadora por cáncer de mama. Material y métodos: se llevó a cabo un estudio retrospectivo descriptivo. Se revisaron las historias clínicas de las pacientes operadas entre enero de 2020 y diciembre de 2022 por carcinoma de mama con cirugía conservadora y que requirieron reconstrucción con colgajos perimamarios. Las indicaciones incluyeron déficit de volumen, defecto de contorno y asimetría. Se evaluó el pedículo vascular del colgajo mediante Doppler color en todos los casos, lo que permitió seguir un algoritmo para la selección de la mejor opción de colgajo. Resultados: se realizaron 20 colgajos en 19 pacientes. Promedio de edad: 52 años ± 11 (rango 30-76). No existieron complicaciones intraoperatorias. Una paciente requirió reoperación por compresión del pedículo vascular del colgajo por hematoma, con la pérdida parcial, y otro colgajo sufrió epidermólisis superficial. No hubo pérdidas totales de ningún colgajo. Todas recibieron radioterapia posoperatoria y no experimentaron pérdida de volumen ni retracciones. Con un promedio de seguimiento de 15 meses, las pacientes valoraron los resultados a 6 meses como excelente en 7, bueno en 11 y regular en 2. Conclusión: la selección de colgajos perforantes locales para corregir defectos mamarios después de cirugía conservadora, mediante el examen con Doppler color preoperatorio para la identificación del pedículo vascular y un algoritmo específico, permitió obtener resultados estéticos satisfactorios sin requerir elementos aloplásticos ni revisiones posteriores.

ABSTRACT Background: Chest wall perforator flaps are a good option for immediate breast reconstruction after conservative surgery. Objective: The aim of this study was to describe the clinical results of an algorithm for using chest wall perforator flaps for breast reconstruction after breast-conserving surgery for breast cancer. Material and methods: We conducted a descriptive and retrospective study. The information was retrieved from the medical records of the patients diagnosed with breast cancer who underwent breast-conserving surgery and required reconstruction using chest wall perforator flaps between January 2020 and March 2022. The indications included volume deficit, contour defect and asymmetry. The vascular pedicle of the flap was evaluated by color Doppler ultrasound in all cases, which allowed us to follow an algorithm for selecting the best flap option. Results: Twenty flaps were made in 19 patients. Mean age: 52 years ± 11 (range 30-76). There were no intraoperative complications. One patient required reoperation due to a hematoma with compression of the vascular pedicle of the flap with partial flap loss, and another flap presented superficial epidermolysis. There were no cases of complete flap loss. All the patients underwent postoperative radiation therapy without loss of volume or retractions. Mean follow-up was 15 months. At 6 months, patients rated the results as excellent, good, and fair in 7, 11, and 2 cases, respectively. Conclusion: The selection of local perforator flaps to correct breast defects after conservative surgery, using preoperative color Doppler ultrasound to identify the vascular pedicle and a specific algorithm, allowed us to obtain satisfactory aesthetic results without the need for alloplastic elements or subsequent revisions.

Application value of improved Cuda-based volume rendering algorithm in CT vascular imaging three-dimensional reconstruction / 实用放射学杂志

Objective To explore the application value of an improved volume rendering algorithm based on Cuda in CT vascular imaging three-dimensional reconstruction.Methods Five cases of head and neck vascular computed tomography angiography(CTA)examinations and five cases of coronary CTA examinations were selected.The traditional Bounding-Box algorithm and the Cuda-based volume rendering reconstruction method were used for vascular three-dimensional reconstruction.The reconstruction speed and quality of the two algorithms were compared.Results Running the traditional algorithm on an RTX2060 graphics card took 50-60 ms per frame,while running the algorithm described in this study took 25-35 ms per frame,resulting in approximately a 1x speed improvement.On an RTX3060,the algorithm described in this study took 18-23 ms per frame,resulting in approximately a 1x speed improvement.The reconstruction results from all ten cases demonstrated that the algorithm described in this study provided clearer visualization of small blood vessels in the head and neck region and the distal coronary arteries.Conclusion The Cuda-based development framework achieves faster rendering speed and better image quality compared to the traditional Bounding-Box algorithm.

Multi-level ranking classification algorithm for nuclear cataract based on AS-OCT image / 中华实验眼科杂志

Objective:To investigate the diagnostic value of an intelligent assisted grading algorithm for nuclear cataract using anterior segment optical coherence tomography (AS-OCT) images.Methods:A diagnostic test study was conducted.AS-OCT image data were collected from 939 cases of 1 608 eyes of nuclear cataract patients at the Shanghai Tenth People's Hospital of Tongji University from November 2020 to September 2021.The data were obtained from the electronic case system and met the requirements for clinical reading clarity.Among them, there were 398 cases of 664 male eyes and 541 cases of 944 female eyes.The ages of the patients ranged from 18 to 94 years, with a mean age of (65.7±18.6) years.The AS-OCT images were labelled manually from one to six levels according to the Lens Opacities Classification System Ⅲ (LOCS Ⅲ grading system) by three experienced clinicians.This study proposed a global-local cataract grading algorithm based on multi-level ranking, which contains five basic binary classification global local network (GL-Net).Each GL-Net aggregates multi-scale information, including the cataract nucleus region and original image, for nuclear cataract grading.Based on ablation test and model comparison test, the model's performance was evaluated using accuracy, precision, sensitivity, F1 and Kappa, and all results were cross-validated by five-fold.This study adhered to the Declaration of Helsinjki and was approrved by Shanghai Tenth People's Hospital of Tongji University (No.21K216).Results:The model achieved the results with an accuracy of 87.81%, precision of 88.88%, sensitivity of 88.33%, F1 of 88.51%, and Kappa of 85.22% on the cataract dataset.The ablation experiments demonstrated that ResNet18 combining local and global features for multi-level ranking classification improved the accuracy, recall, specificity, F1, and Kappa metrics.Compared with ResNet34, VGG16, Ranking-CNN, MRF-Net models, the performance index of this model were improved.Conclusions:The deep learning-based AS-OCT nuclear cataract image multi-level ranking classification algorithm demonstrates high accuracy in grading cataracts.This algorithm may help ophthalmologists in improving the diagnostic accuracy and efficiency of nuclear cataract.

Fast reconstruction algorithm of magnetic particle imaging based on Kaczmarz algorithm / 医疗卫生装备

Objective To propose a Kaczmarz algorithm-based fast reconstruction method of magnetic particle imaging to solve the problems of magnetic particle tomography in prolonged imaging time and computational complexity.Methods Firstly,the convergence speeds of the classical Kaczmarz algorithm and its variant algorithms were analyzed,and the number of iterations and computational time under arbitrary matrices were calculated.Secondly,the abilities of Euclidean distance and cosine distance in differentiating system data were compared,and the cosine distance-based K-means algorithm was employed to enhance the computational capability of block Kaczmarz algorithm,shorten the system matrix reconstruction time,and ultimately fast reconstruction of magnetic particle imaging was realized.The effectiveness of the proposed algorithm was verified through computer simulation.Results The proposed algorithm reduced greatly the reconstruction time and improved the spatial resolution and quality of the reconstructed images.Conclusion The proposed algorithm enables fast reconstruction of magnetic particle imaging and behaves well in reconstruction of data containing noise.[Chinese Medical Equipment Journal,2024,45(1):9-14]

Arrhythmia classification method based on genetic algorithm optimization of C-LSTM model / 中国医学物理学杂志

A GC-LSTM model is proposed based on the characteristics of global optimization of genetic algorithm.The model automatically and iteratively searches the optimal hyper-parameter configuration of the C-LSTM model through the genetic algorithm of a specific genetic strategy,and it is configured using the genetic iteration results and validated on the MIT-BIH arrhythmia database according to the classification criteria of the Association for the Advancement of Medical Instrumentation.The testing shows that the classification accuracy,sensitivity,accuracy and F1 value of GC-LSTM model are 99.37%,95.62%,95.17%and 95.39%,respectively,higher than those of the manually established model,and it is also advantageous over the existing mainstream methods.Experimental results demonstrate that the proposed method can achieve better classification performance while avoiding a large number of experimental parameters.

Intelligent diagnosis of psoriasis vulgaris based on deep learning and improved fuzzy KMeans / 中国医学物理学杂志

In order to address issues such as the decline in diagnostic performance of deep learning models due to imbalanced data distribution in psoriasis vulgaris,a VGG13-based deep convolutional neural network model is proposed by integrating the processing capability of the improved fuzzy KMeans clustering algorithm for highly clustered complex data and the predictive capability of VGG13 deep convolutional neural network model.The model is applied to the diagnosis of psoriasis vulgaris,and the experimental results indicate that compared with VGG13 and resNet18,the proposed approach based on deep learning and improved fuzzy KMeans is more suitable for identifying psoriasis features.

Design and implementation of a fall detection system for elderly patients / 中国医学装备

Objective:To design a fall detection system for elderly patients to solve the problem of elderly patients failing to detect accidental falls in time and to improve the efficiency of medical care.Methods:Based on real-time stream transmission protocol(RTSP),combined with YOLOv5 and Kalman algorithms,a fall detection system for elderly patients was designed by using Vue and Flask technologies.A visual background system management was established,and a unified management platform was provided for medical staff through comprehensive processing of multiple video streams to realize the autonomous detection and alarm of human fall behavior.30 healthy volunteers who underwent fall testing at Xijing Hospital of Air Force Medical University in 2020 to 2022 were selected and divided into normal walking group,squatting group and falling group according to the simulated behavioural categories,with 10 in each group.The fall detection performance was evaluated using two evaluation indicators:detection accuracy and detection speed to verify and determine whether the fall detection system for elderly patients can meet the requirements of timely and accurate fall detection and alarm.Results:The overall fall detection rate of the normal walking group,the squatting group and the falling group can reach 29 frames per second,and the accuracy rate can reach 95.24%.and the system can respond to the fall alarm in time.Conclusion:The fall detection system for elderly patients can assist medical staff to promptly detect and deal with the occurrence of falls,improve the efficiency of fall detection for elderly patients,and meet the real-time detection and alarm of fall behavior for elderly patients.

Study on the effects of AI reconstruction algorithm based on different tube voltages on CT imaging quality and radiation dose of chest phantom / 中国医学装备

Objective:To investigate the effects of different tube voltages combined with artificial intelligence reconstruction algorithm(CI)on the computed tomography(CT)imaging quality and radiation dose of chest phantom on the basis of the CT scan for an adult male simulated chest phantom(PH-N1).Methods:A 512-slice CT scanner of ultrahigh-end was adopted to conduct scan,and the images were divided into 70 kV group,80 kV group,100 kV group and 120 kV group according to different tube voltage.For 4 groups of CT scan images with different tube voltages,the 10%,30%,50%,70%and 90%CI were adopted to reconstruct 1mm thin layer image.The CT volume dose index(CTDIvol)and the dose-length product(DLP)of the scans of 4 groups were compared.The CT values and standard deviation(SD)values of the aorta,abdominal wall fat and erector spine muscle were measured.Two senior diagnostic physicians with more than 5 years of work experience independently and double-blindly evaluated the image quality by using 5-point scale.A Kappa consistency test was conducted.One-way analysis of variance was adopted to compare the differences of CT values and SD values of the tissues of image targets.The Friedman rank-sum test was adopted to compare the differences of subjective image qualities among different groups.Results:The differences of CTDIvol and DLP among 4 groups with different tube voltages were significant(F=1855.617,3996.118,P<0.05),respectively.Under 70 kV tube voltage,there were no significant differences in CT values of the aorta,abdominal wall fat and erector spine muscle,which were reconstructed by using 10%,30%,50%,70%and 90%CI(P>0.05),while the differences of SD values among them were statistically significant(F=32.267,53.327,14.873,P<0.05),respectively.Under the different tube voltages of 4 groups,which were reconstructed by 90%CI,the CT values of aorta,abdominal wall fat and erector spine muscle gradually decreased with decreasing of tube voltage,the differences were significant(F=139.899,2563.93,219.231,P<0.05),respectively.The consistency of subjective scores between two diagnostic physicians was better for each group of images(Kappa=0.712～0.869).Conclusion:Compared with 80 kV,90 kV and 120 kV images,the reconstructed images with 90%CI algorithm under 70 kV tube voltage can significantly reduce the radiation dose,and the images have a favorable signal-to-noise ratio at the same time.

Application value of the deep learning-based image reconstruction algorithm in combined head and neck CT angiography with low radiation dose / 中华放射医学与防护杂志

Objective:To explore the differences between the deep learning-based image reconstruction (DLIR) and the adaptive statistical iterative reconstruction V (ASiR-V) algorithms in the radiation dose and image quality of head and neck CT angiography (CTA).Methods:The data of 80 patients undergoing head and neck CTA due to vascular diseases in the head and neck were prospectively collected. These patients were randomly divided into groups A and B based on their examination sequence. The CTA images of group A were reconstructed based on ASiR-V 50%, with a tube voltage of 120 kV and a noise index of 11.0. In contrast, those of group B were reconstructed based on ASiR-V 50% (for group B1) and DLIR-H (for group B2), with a tube voltage of 80 kV and a noise index of 9.0. Then, the radiation doses and image quality of both groups were compared using the independent-sample t-test. The radiation doses, and both subjective and objective image quality of the two imaging method were compared through the Kruskal-Wallis test and the Wilcoxon rank-sum test. The independent- or paired-sample t-test was employed to measure inter-group vascular enhanced CT values, as well as signals and noise from regions of interest (ROIs), with signal-to-noise ratios (SNRs) and contrast-to-noise ratios (CNRs) calculated. Results:The effective doses of groups A and B were (0.77±0.08) and (0.45±0.05) mSv, respectively, with a statistically significant difference ( t = 21.96, P < 0.001). The vascular enhanced CT values, SDs, SNRs, and CNRs in the arch of the aorta, the initial and bifurcation parts of the common carotid artery, and the M1 segment of the middle cerebral artery showed statistically significant differences among groups A, B1, and B2 ( F = 67.69, 68.50, 50.52, 74.10, 63.10, 91.22, 69.16, P < 0.001). Additionally, statistically significant differences were observed in the subjective scores of image quality among groups A, B1, and B2 ( Z = 71.06, P < 0.05). Conclusions:The DLIR algorithm can further reduce the radiation dose in head and neck CTA examination while significantly reducing image noise and ensuring image quality, thus demonstrating high clinical application value.

Application of Jacobian determinant of reverse deformation field to evaluation of deformation registration algorithm / 中华放射医学与防护杂志

Objective:To effectively quantify and evaluate the quality of different deformation registration algorithms, in order to enhance the possibility of implementing deformation registration in clinical practice.Methods:The Jacobian determinant mean (JDM) is proposed based on the Jacobian determinant (JD) of displacement vector field (DVF), and the Jacobian determinant error (DJDE) is introduced by incorporating the JD of the inverse DVF. The optical flow method (OF-DIR) and fast demons method with elastic regularization (FD-DIR) were tested on nasopharyngeal and lung cancer datasets. Finally, JDM and DJDE with the Jacobian determinant negative percentage (JDNP), inverse consistency error (ICE) and normalized mean square error (NMSE) were used to evaluate the registration algorithms and compare the differences evaluation indicators in different tumor images and different algorithms, and the receiver operating curve (ROC) was analyzed in evaluation.Results:In lung cancer, OF-DIR outperformed FD-DIR in terms of JDM, NMSE, DJDE and ICE, and the difference was statistically significant( z = -2.24, -4.84, t = 4.01, 6.54, P<0.05). In nasopharyngeal carcinoma, DJDE, ICE and NMSE of OF-DIR were superior to FD-DIR, and the difference was statistically significant ( t = 4.46, -7.49, z = -2.22, P<0.05), but there was no significant difference in JDM ( P>0.05). In lung cancer and nasopharyngeal carcinoma, JDNP of OF-DIR was worse than that of FD-DIR, and the difference was statistically significant ( z = -4.29, -4.02, P<0.01). In addition, DJDE is more specific and sensitive on ROC curve (AUC=0.77), and has different performance result for tumor images at different sites. Conclusions:The JDM and DJDE evaluation metrics proposed are effective for deformation registration algorithms. OF-DIR is suitable for both lung cancer and nasopharyngeal carcinoma, while the influence of organ motion on the registration effect should be considered when using FD-DIR.

Evaluation of the accuracy of optical surface imaging system in non-coplanar radiotherapy using orthogonal kV/MV images / 中华放射肿瘤学杂志

Objective:To evaluate the accuracy of the optical surface imaging system (OSI) using stereotactic radiosurgery (SRS) algorithm in single-center non-coplanar treatment of multiple brain metastases.Methods:Data of phantom and 15 patients with multiple brain metastases who underwent single-center non-coplanar radiotherapy in West China Hospital of Sichuan University from February to April 2022 were retrospectively analyzed. kV/MV and OSI imaging were used for imaging of the patients and phantoms under the same non-coplanar couch angle, respectively. The accuracy of OSI imaging of the phantoms and patients was evaluated using kV/MV imaging as reference image. The difference between the OSI and kV/MV systems is defined as accuracy, and the percentage of the absolute difference ≤1.00 mm in the translational direction or ≤0.50° in the rotational direction is defined as the threshold pass rate. Origin software was used to draw radar maps and Bland-Altman plots for statistical analysis.Results:When OSI images were used for the phantom imaging, the average differences in six-dimensional directions of lateral, long, vertical, rotational, roll and pitch were 0.03 mm, -0.09 mm, -0.27 mm, 0.04°, 0.17° and -0.19°, respectively. The maximum values were -2.20 mm, -2.30 mm, -1.20 mm, 0.60°, -1.00°, and -1.00°, respectively. When OSI system was utilized for the imaging of 15 patients, the average differences in six-dimensional directions were 0.44 mm, 0.16 mm, -0.20 mm, -0.11°, 0.10°, and -0.12°, respectively. The maximum values were -1.80 mm, 2.00 mm, 0.90 mm, -0.90°, -0.70°, and 0.80°, respectively. The translational errors mainly occurred in the lateral and long directions. The qualified rates of the threshold values of the phantoms and patients were 77% and 75% in the lateral direction, 82% and 89% in the long direction, respectively. In addition, 57% and 56% of patients met the threshold conditions of ±1.00 mm and ±0.50° in the six-dimensional directions, respectively.Conclusions:The OSI system using new SRS algorithm cannot meet the high accuracy requirements of single-center non-coplanar radiotherapy for multiple brain metastasis, especially in the lateral and long directions. It is not recommended for non-coplanar image guidance.

Study on The Toxicity of Strychnos nux-vomica L. in vivo in Rats：Application of Bagging Algorithm and 16S rRNA Gene Sequencing Technology in Toxicology Research / 生物化学与生物物理进展

ObjectiveThe traditional Chinese medicine Strychnos nux-vomica L. (SN) has the clinical effect of reducing swelling and relieving pain; however, SN is toxic due to its alkaloid components. Little is known about the endogenous metabolic changes induced by SN toxicity in rats and their potential effects on the metabolic dysregulation of intestinal microbiota. Therefore, toxicological investigation of SN is of great significance to its safety assessment. In this study, the toxic mechanisms of SN were explored using a combination of metabonomics and 16S rRNA gene sequencing. MethodsThe toxic dose, intensity, and target organ of SN were determined in rats using acute, cumulative, and subacute toxicity tests. UHPLC-MS was used to analyze the serum, liver, and renal samples of rats after intragastric SN administration. The decision tree and K Nearest Neighbor (KNN) model were established based on the bootstrap aggregation (bagging) algorithm to classify the omics data. After samples were extracted from rat feces, the high-throughput sequencing platform was used to analyze the 16S rRNA V3-V4 region of bacteria. ResultsThe bagging algorithm improved the accuracy of sample classification. Twelve biomarkers were identified, where their metabolic dysregulation may be responsible for SN toxicity in vivo. Several types of bacteria such as Bacteroidetes, Anaerostipes, Oscillospira and Bilophila, were demonstrated to be closely related to physiological indices of renal and liver function, indicating that SN-induced liver and kidney damage may be related to the disturbance of these intestinal bacteria. ConclusionThe toxicity mechanism of SN was revealed in vivo, which provides a scientific basis for the safe and rational clinical use of SN.

Diagnosis and management of diabetes insipidus complicated with upper urinary tract dilatation: a single-center experience / 现代泌尿外科杂志

【Objective】 To investigate the urinary tract characteristics of diabetes insipidus (DI) complicated with upper urinary tract dilatation (UUTD), and to summarize the treatment experience. 【Methods】 The clinical data of 28 DI patients treated in China Rehabilitation Research Center were retrospectively analyzed with UUTD and all urinary tract dysfunction (AUTD) systems to evaluate the urinary tract characteristics. The relevant laboratory results, video-urodynamic recordings (VUDS), UUTD, neurophysiologic tests, treatment regimens and follow-up data were summarized. 【Results】 There were 21 DI cases (75.0%) and 7 cases of DI with neurogenic bladder (NB). Polyuria, polydipsia, urine specific gravity, urine osmotic pressure and water deprivation vasopressin test had diagnostic value for DI. In addition, detailed history, neurological examination, VUDS and neurophysiologic tests had significant diagnostic value for DI with NB. Enterocystoplasty was recommended for 2 DI with NB patients with poor bladder capacity, compliance and renal impairment. For the remaining 26 patients, individualized medication combined with bladder neck incision and appropriate bladder management, including intermittent catheterization, catheter indwelling and regular voiding, achieved satisfactory results. High serum creatinine decreased from (269.8±105.7)μmol/L to (164.4±90.2)μmol/L in 13 patients with abnormal renal function. Forty-eight dilated ureters showed significant improvement in the UUTD grade, and the median grade decreased from 3 to 2. 【Conclusion】 Bladder distension, trabeculation and decreased or absent sensations were common features for DI patients with UUTD. Individualized therapy by medication combined with appropriate bladder management can improve the dilatation and renal function.

Utilization of artificial intelligence in breast pathology: An overview

@#In the last decade, artificial intelligence (AI) has been increasingly used in various fields of medicine. Recently, the advent of whole slide images (WSI) or digitized slides has paved the way for AI-based anatomic pathology. This paper set out to review the potential integration of AI algorithms in the workflow, and the utilization of AI in the practice of breast pathology.

Early prediction of severe acute pancreatitis based on improved machine learning models / 陆军军医大学学报

Objective To establish an early prediction model for the diagnosis of severe acute pancreatitis based on the improved machine learning models,and to analyze its clinical value.Methods A case-control study was conducted on 352 patients with acute pancreatitis admitted to the Gastroenterology and Hepatobiliary Surgery Departments of the Army Medical Center of PLA and Emergency and Critical Care Medicine Department of No.945 Hospital of Joint Logistics Support Force of PLA from January 2014 to August 2023.According to the severity of the disease,the patients were divided into the severe group(n=88)and the non-severe group(n=264).The RUSBoost model and improved Archimead optimization algorithm was used to analyze 39 routine laboratory biochemical indicators within 48 h after admission to construct an early diagnosis and prediction model for severe acute pancreatitis.The task of feature screening and hyperparameter optimization was completed simultaneously.The ReliefF algorithm feature importance rank and multivariate logistic analysis were used to analyze the value of the selected features.Results In the training set,the area under curve(AUC)of the improved machine learning model was 0.922.In the testing set,the AUC of the improved machine learning model reached 0.888.The 4 key features of predicting severe acute pancreatitis based on the improved Archimedes optimization algorithm were C-reactive protein,blood chlorine,blood magnesium and fibrinogen level,which were consistent with the results of ReliefF algorithm feature importance ranking and multivariate logistic analysis.Conclusion The application of improved machine learning model analyzing the laboratory examination results can help to early predict the occurrence of severe acute pancreatitis.

Analysis on the medication characteristics and compatibility law of ancient prescriptions in the treatment of pediatric epilepsy based on visual network analysis / 国际中医中药杂志

Objective:To analyze the medication characteristics of ancient prescriptions for pediatric epilepsy (PE) through data mining; To summarize the compatibility law; To provide a reference for the treatment selection of Chinese materia medica and the development of patent drugs related to PE in clinic.Methods:Those with definite composition, dosage and efficacy for the treatment of PE was screened from the data of TCM prescription designed by Institute of Traditional Chinese Medicine Information, China Academy of Traditional Chinese Medicine. Excel 2013 was used to analyze the frequency of Chinese materia medica and its flavor and meridian tropism in the included prescriptions. The arules package in R 3.6.3 was used for association analysis based on Apriori algorithm. The sankey package and ggraph package of R 3.6.3 were used to draw the network diagram of the property, taste, meridian tropism and association rules of high-frequency Chinese medicine, so as to realize data visualization.Results:A total of 360 ancient prescriptions for the treatment of PE were included, and the dosage form was mainly pills. Most of the prescriptions were composed of 1 to 10 kinds of Chinese materia medica, with a total of 192 (53.33%, 192/360) prescriptions. 152 kinds of Chinese materia medica were included. The most commonly used types of Chinese materia medica were Glycyrrhizae Radix et Rhizoma, Moschus, Saposhnikoviae Radix, Gastrodiae Rhizoma, and Aconiti Lateralis Radix Praeparata. The properties of high-frequency Chinese materia medica (frequency≥30) were characterized by warm and mild, and the tastes were mainly pungent, bitter and sweet, and the meridians were mainly spleen and liver meridians. Through Apriori association analysis, the commonly used combination drugs were Bovis Calculus-Moschus, Ginseng Radix et Rhizoma-Poria and Saposheikovize Radix-Glycyrrhizae Radix et Rhizoma. Similarly, the commonly used triple drugs included Gastrodiae Rhizoma-Aconiti Lateralis Radix Praeparata-Bombyx Batryticatus, Poria-Glycyrrhizae Radix et Rhizoma-Ginseng Radix et Rhizoma, and Moschus-Bovis Calculus-Realgar.Conclusions:The ancient prescriptions for the treatment of PE is mainly composed of wind-calming, resuscitation and tonifying drug. The core prescription ideas of the ancient prescriptions are as follows: dispelling phlegm and dispelling wind, warming the meridian and dispelling yang, resuscitating and relieving spasms, clearing heat and reducing depression, and tonifying qi and blood.

Optimization of ethanol extraction process for Yihuang powder by orthogonal experiment combined with AHP and GA-BP neural network / 中国药房

OBJECTIVE To optimize ethanol extraction process of Yihuang powder. METHODS An orthogonal experiment was designed by reflux extraction with ethanol volume fraction， liquid-to-material ratio， and extraction time as investigation factors. The parameters used were the contents of hesperidin， nobiletin， tangeretin， gallic acid， chebulagic acid， chebulinic acid， liquiritin， glycyrrhizin， eugenol， and the paste-forming rate. The analytic hierarchy process （AHP） was used to calculate the comprehensive score. The optimal ethanol extraction process parameters of Yihuang powder were determined by verifying the results predicted by orthogonal experiment and genetic algorithm （GA）-back propagation neural network （BP neural network）. RESULTS The optimal ethanol extraction process parameters， as optimized by orthogonal experiment， were as follows: ethanol volume fraction of 60%， liquid-solid ratio of 14∶1 （mL/g)， extraction time of 90 min， and extraction for 2 times. The comprehensive score obtained by verification was 79.19. Meanwhile， the optimal ethanol extraction process parameters， optimized by GA-BP neural network， were ethanol volume fraction of 65%， liquid-solid ratio of 14∶1 （mL/g )， extraction time of 60 min， and extraction for 2 times. The comprehensive score obtained by verification was 85.30， higher than the results obtained from orthogonal experiment. CONCLUSIONS The optimization method of orthogonal experiment combined with GA-BP neural network is superior to the traditional orthogonal experiment optimization method. The optimized ethanol extraction process of Yihuang powder is stable and reliable.

Application of Bayesian probabilistic linkage model in birth and death data linking / 上海预防医学

ObjectiveTo elucidate the principles and methods of the Bayesian probabilistic linkage model， and to demonstrate the effect of applying the model in linking birth and death data. MethodsThrough the Shanghai birth and death registration system， data of 199 025 infants born in 2017 and 1 512 infants who died in 2017 and 2018 were collected. After cleaning the data， the data were divided into monthly blocks and fully linked. The Jaro-Winkler algorithm and Euclidean distance were employed to measure the similarity of fields for matching. A Bayesian probabilistic linkage model was constructed and the linking effect was evaluated using a confusion matrix. ResultsUsing the Bayesian probabilistic linkage model， the birth and death data of infants were effectively linked， revealing that 36.71% of infants who died in Shanghai were born outside the city， and the probability of infant death was 2.6‰. The confusion matrix of the test set showed a recall rate of 0.86， precision of 0.76， and an F-score of 0.81. ConclusionThe practical application of Bayesian probabilistic linkage demonstrates a good model performance， enabling the establishment of birth-death cohorts that more accurately reflect the true levels of infant mortality. Utilizing this technique to integrate data from different departments can effectively improve research efficiency in the field of public health.

Molecular identification of new Trypanosoma evansi type non-A/B isolates from buffaloes and cattle in Indonesia / Identificação molecular de novos isolados de Trypanosoma evansi tipo não A/B em búfalos e gado na Indonésia

Abstract Trypanosoma evansi is reportedly divided into two genotypes: types A and B. The type B is uncommon and reportedly limited to Africa: Kenya Sudan, and Ethiopia. In contrast, type A has been widely reported in Africa, South America, and Asia. However, Trypanosoma evansi type non-A/B has never been reported. Therefore, this study aims to determine the species and genotype of the Trypanozoon subgenus using a robust identification algorithm. Forty-three trypanosoma isolates from Indonesia were identified as Trypanosoma evansi using a molecular identification algorithm. Further identification showed that 39 isolates were type A and 4 isolates were possibly non-A/B types. The PML, AMN-SB1, and STENT3 isolates were likely non-A/B type Trypanosoma evansi isolated from buffalo, while the PDE isolates were isolated from cattle. Cladistic analysis revealed that Indonesian Trypanosoma evansi was divided into seven clusters based on the gRNA-kDNA minicircle gene. Clusters 6 and 7 are each divided into two sub-clusters. The areas with the highest genetic diversity are the provinces of Banten, Central Java (included Yogyakarta), and East Nusa Tenggara. The Central Java (including Yogyakarta) and East Nusa Tenggara provinces, each have four sub-clusters, while Banten has three.

Resumo Trypanosoma evansi é reportado como dividido em dois genótipos: tipos A e B. O tipo B é incomum e reportado como limitado à África: Quênia, Sudão e Etiópia. Em contraste, o tipo A tem sido amplamente relatado na África, América do Sul e Ásia. No entanto, Trypanosoma evansi tipo não-A/B nunca foi relatado. Portanto, este estudo tem como objetivo determinar a espécie e o genótipo do subgênero Trypanozoon, utilizando-se um algoritmo robusto de identificação. Quarenta e três isolados de tripanosoma da Indonésia foram identificados como Trypanosoma evansi, usando-se um algoritmo de identificação molecular. A identificação adicional mostrou que 39 isolados eram do tipo A e 4 isolados eram, possivelmente, do tipo não A/B. Os isolados PML, AMN-SB1 e STENT3 foram, provavelmente, Trypanosoma evansi do tipo não A/B isolado de búfalos, enquanto os isolados de PDE foram isolados de bovinos. A análise cladística revelou que o Trypanosoma evansi indonésio foi dividido em sete grupos baseados no gene do minicírculo gRNA-kDNA. Os clusters 6 e 7 foram divididos cada um em dois subclusters. As áreas com maior diversidade genética são as províncias de Banten, Java Central (incluindo Yogyakarta) e East Nusa Tenggara. As de Java Central (incluindo Yogyakarta) e East Nusa Tenggara têm, cada uma, quatro subgrupos, enquanto Banten tem três.