Neguentropia Algorítmica e a Gestão Digital do Gozo / Algorithmic Negentropy and the Digital Management of Jouissance / La Negentropia Algorítmica y la Gestión Digital del Goce

O algoritmo digital permitiu o manejo de dados dos usuários da web pelos conglomerados informacionais. De forma discreta e personalizada, a nova forma de governamentalidade coleta, organiza, permuta e devolve os dados ao próprio indivíduo na forma de mais informações. Cada vez mais, esbarra na dimensão singular, tocando o campo do gozo via proliferação de objetos a que, na teoria lacaniana dos discursos, assume a dupla função de perda e de incessante tentativa de suplementação de gozo. Com o incremento informacional, o objeto chega ao ápice social e o digital alcança patamar discursivo. Inserindo-se no mesmo nicho do saber, a informação digital se aproveita da divisão subjetiva, deixando pouco espaço para que o sujeito possa lidar com a entropia de seu gozo via desejo. Se a neguentropia é o atributo do saber que limita a dispersão de gozo, na informação tratada e retornada algoritmicamente tal processo sofre uma aceleração, agindo diretamente sobre a economia dos afetos. Com prejuízo para o sujeito, resta uma experiência de gozo cada vez mais direta, crua, menos mediatizada pelo saber e pelo Outro.

The digital algorithm has allowed the management of data from web users by informational conglomerates. In a discreet and personalized way, the new form of governmentality collects, organizes, exchanges and returns data to the individual in the form of more information. More and more, it comes up against the singular dimension, touching the field of jouissance via the proliferation of objects a which, in the Lacanian theory of discourses, assumes the double function of loss and an incessant attempt to supplement jouissance. With the increase in information, the object reaches the social apex and the digital reaches a discursive level. Inserting itself in the same niche of know [savoir], digital information takes advantage of the subjective division, leaving little space for the subject to deal with the entropy of his jouissance via desire. If negentropy is the attribute of savoir that limits the dispersion of jouissance, in the information processed and returned algorithmically this process is accelerated, acting directly on the economy of affections. To the detriment of the subject, what remains is an experience of jouissance that is increasingly direct, raw, less mediated by savoir and the Other.

El algoritmo digital permitió la gestión de datos de los usuarios de la web por parte de conglomerados informativos. De forma discreta y personalizada, la nueva forma de gubernamentalidad recolecta, organiza, intercambia y devuelve datos al individuo en forma de más información. Cada vez más, choca con la dimensión singular, tocando el campo del goce a través de la proliferación de objetos a que, en la teoría lacaniana de los discursos, asume la doble función de pérdida y de intento incesante de complementar el goce. Con el aumento de la información, el objeto alcanza el ápice social y lo digital alcanza un nivel discursivo. Insertándose en el mismo nicho del conocimiento, la información digital aprovecha la división subjetiva, dejando poco espacio para que el sujeto gestione la entropía de su goce vía deseo. Si la negentropía es el atributo del saber que limita la dispersión del goce, en la información procesada y devuelta algorítmicamente, este proceso se acelera, actuando directamente sobre la economía de los afectos. En detrimento del sujeto, lo que queda es una experiencia de goce cada vez más directa, cruda, menos mediatizada por el saber y el Otro.

Síndrome Stevens Jonhson: reporte de caso clínico / Stevens Johnson syndrome: clinical case report

Resumen Introducción: El síndrome Stevens Johnson (SSJ) es una dermatosis potencialmente fatal caracterizada por una extensa necrosis epidérmica y de mucosas que se acompaña de ataque al estado general, y junto con la necrólisis epidérmica tóxica (NET) se consideran reacciones de hipersensibilidad tipo IV, relacionadas con ciertos fármacos en 60% de los casos, siendo uno de los diagnósticos pocos frecuentes, pero con una alta mortalidad hasta del 40%. Caso clínico: El siguiente caso clínico es un masculino de 34 años de edad que inició un cuadro de eritema generalizado inmediatamente tras la administración del medicamento trimetoprima/sulfametoxazol. Se le solicitó un hemograma mostrando leucocitosis, neutrofilia, VSG elevada, PCR elevada, IgE elevada, y tras el interrogatorio clínico se realiza el algoritmo ALDEN dando positivo con 10 puntos asociado al medicamento previamente dicho. Por lo tanto se le inicia tratamiento con metilprednisolona, difenhidramina, inmunoglobulina humana intravenosa y un plan terapéutico cutáneo, dando como resultado una mejoría clínica, evitando complicaciones y secuelas, hasta el día de su egreso. A manera de conclusión, se requiere un manejo multidisciplinario para atender las manifestaciones clínicas del inmunoglobulina humana intravenosa.

Abstract Introduction: Stevens Johnson Syndrome (SJS) is a potentially fatal dermatosis characterized by extensive epidermal and mucosal necrosis accompanied by an attack on the general condition, which together with Toxic Epidermal Necrolysis (TEN) are considered type IV hypersensitivity reactions, related to certain drugs in 60% of cases, being one of the rare diagnoses, but with a high mortality of up to 40%. Case report: The following clinical case is a 34 year old male who started a generalized erythema picture immediately after administration of the medication trimethoprim/sulfamethoxazole, for which a complete blood count was requested showing leukocytosis, neutrophilia, elevated ESR, elevated PCR, elevated IgE, and after the clinical questioning, the ALDEN algorithm was performed, giving positive with 10 points associated with the previously mentioned medication, for which treatment was started with methylprednisolone, diphenhydramine, intravenous human immunoglobulin and a skin therapeutic plan, resulting in clinical improvement, avoiding complications and sequelae, until the day of discharge. In conclusion, a multidisciplinary management is required to attend to the clinical manifestations of the patient, helping him to a quick and effective recovery.

Algoritmo para la indicación del estudio por imágenes en pacientes politraumatizados

Introducción: En los últimos años se han producido cambios profundos en el manejo del paciente politraumatizado. A la vez, se han desarrollado nuevos conceptos en relación con las posibles complicaciones, los esquemas de tratamiento y las escalas pronósticas, así como en la identificación de elementos relacionados con su evolución para determinar, de manera precoz, las lesiones que amenazan la vida y precisan de un control quirúrgico inmediato o de intervencionismo radiológico. La tomografía computarizada multicorte y otros estudios imagenológicos permiten la obtención de imágenes de las estructuras corporales por planos, y proporcionan información muy detallada y útil para el diagnóstico; sin embargo, no existe consenso a la hora de indicar uno u otro en el trauma. Objetivo: Elaborar un algoritmo para la indicación eficiente de los estudios imagenológicos en el paciente politraumatizado. Materiales y métodos: Se ejecutó una investigación de desarrollo tecnológico, donde el universo de trabajo estuvo conformado por 43 pacientes con criterio de politrauma -que necesitaron estudios imagenológicos-, ingresados en el Hospital Universitario Clínico Quirúrgico Comandante Faustino Pérez Hernández, en el período comprendido entre marzo de 2020 y marzo de 2021. Resultados: Se elaboró un algoritmo para estandarizar la indicación de estudios imagenológicos en el trauma. Este trabajo considera la seguridad y protección del paciente, y el cuidado de la vida útil del equipo de tomografía axial computarizada. Conclusión: El algoritmo diseñado viabiliza la toma de decisiones respecto al uso de recursos imagenológicos en la atención a los pacientes politraumatizados.

Introduction: In recent years there have been profound changes in the management of poly-traumatized patients. At the same time, new concepts have been developed in relation to possible complications, treatment schemes and prognostic scales, as well as in the identification of elements related with its evolution to early determine the life-threatening lesions and require immediate surgical control or radiological intervention. Multislice computed tomography and other imaging studies allow obtaining images of body structures by planes and provide very detailed and useful information for the diagnosis; nevertheless there is no consensus when it comes to indicating one or the other in trauma. Objective: To develop an algorithm for the efficient indication of imaging study in the poly-traumatized patient. Materials and methods: A technological development research was carried out, where the working universe was made up by 43 patients with polytrauma criteria -who needed imaging studies- admitted to the Clinical Surgical University Hospital Faustino Perez, in the period between March 2020 and March 2021. Results: An algorithm was developed for standardizing the indication of imaging studies in trauma. This work considers the safety and protection of the patient, and the care of the life of the computed axial tomography equipment. Conclusions: The developed algorithm enables decision-making regarding the use of imaging resources in the care of poly-traumatized patients.

Effect of dental distance from implant and MAR algorithm on the detection of vertical root fracture in CBCT images

Three-dimensional cone-beam computed tomography (CBCT) has an important role in the detection of vertical root fractures (VRFs). The effect of artifact generation by high-density objects like dental implants on image quality was well documented. This study aimed to assess the effect of tooth-implant distance and the application of metal artifact reduction (MAR) algorithm on the detection of VRFs on CBCT scans. This study was conducted on 20 endodontically treated single-rooted teeth. VRFs were induced in 10 teeth, while the other 10 remained intact. The implant was inserted in the right second premolar socket area, and two teeth were inserted in right canine and right first premolar sockets area randomly and underwent CBCT with and without the application of MAR algorithm. SPSS 21 was used to analyze the results (alpha=0.05). According to the findings of this study, all four variables of sensitivity, specificity, accuracy, and positive predictive values in diagnosis were higher in cases without MAR software at both close(roots in first premolar sockets) and far distances (roots in canine sockets) from the implant. However, the highest rate of diagnosis accuracy of the first and second radiologists was in the far distance group from the implant without MAR, and the lowest rate of diagnosis accuracy in the first and second radiologists was in the close distance to the implant. Applying MAR algorithm had no positive effect on detection of VRFs on CBCT scans in both close and distant scenarios.

La tomografía computarizada de haz cónico tridimensional (CBCT) tiene un papel importante en la detección de fracturas radiculares verticales (VRF). El efecto de la generación de artefactos por objetos de alta densidad como los implantes dentales en la calidad de la imagen está bien documentado. Este estudio tuvo como objetivo evaluar el efecto de la distancia entre el diente y el implante y la aplicación del algoritmo de reducción de artefactos metálicos (MAR) en la detección de VRF en escaneos CBCT. Este estudio se realizó en 20 dientes uniradiculares tratados endodónticamente. Se indujeron VRF en 10 dientes, mientras que los otros 10 permanecieron intactos. El implante se insertó en el área del alveolo del segundo premolar derecho, y dos dientes se insertaron en el canino derecho y en el área del alvéolo del primer premolar derecho al azar y se sometieron a CBCT con y sin la aplicación del algoritmo MAR. Se utilizó SPSS 21 para analizar los resultados (alfa=0,05). De acuerdo con los hallazgos de este estudio, las cuatro variables de sensibilidad, especificidad, precisión y valores predictivos positivos en el diagnóstico fueron más altas en los casos sin el software MAR tanto en distancias cercanas (raíces en las cavidades de los primeros premolares) como lejanas (raíces en las cavidades de los caninos) del implante. Sin embargo, la tasa más alta de precisión diagnóstica del primer y segundo radiólogo fue en el grupo de mayor distancia al implante sin MAR, y la tasa más baja de precisión diagnóstica en el primer y segundo radiólogo fue en la distancia cercana al implante. La aplicación del algoritmo MAR no tuvo un efecto positivo en la detección de VRF en escaneos CBCT en escenarios cercanos y distantes.

Validation of qrs-polarity algorithm with special emphasis in parahisian pathways / Validación del algoritmo de la polaridad del qrs con especial énfasis en vías parahisianas

Abstract Background: In 1996 Iturralde et al. published an algorithm based on the QRS polarity to determine the location of the accessory pathways (AP), this algorithm was developed before the massive practice of invasive electrophysiology. Purpose: To validate the QRS-Polarity algorithm in a modern cohort of subjects submitted to radiofrequency catheter ablation (RFCA). Our objective was to determinate its global accuracy and its accuracy for parahisian AP. Methods: We conducted a retrospective analysis of patients with Wolff-Parkinson-White (WPW) syndrome who underwent an electrophysiological study (EPS) and RFCA. We employed the QRS-Polarity algorithm to predict the AP anatomical location and we compared this result with the real anatomic location determined in the EPS. To determine accuracy, the Cohen's kappa coefficient (k) and the Pearson correlation coefficient were used. Results: A total of 364 patients were included (mean age 30 years, 57% male). The global k score was 0.78 and the Pearson's coefficient was 0.90. The accuracy for each zone was also evaluated, the best correlation was for the left lateral AP (k of 0.97). There were 26 patients with a parahisian AP, who showed a great variability in the ECG features. Employing the QRS-Polarity algorithm, 34.6% patients had a correct anatomical location, 42.3% had an adjacent location and only 23% an incorrect location. Conclusion: The QRS-Polarity algorithm has a good global accuracy; its precision is high, especially for left lateral AP. This algorithm is also useful for the parahisian AP.

Resumen Antecedentes: En 1996 Iturralde y colaboradores publicaron un algoritmo basado en la polaridad del QRS para determinar la ubicación de las vías accesorias (VA), este algoritmo fue desarrollado antes de la práctica masiva de la electrofisiología invasiva. Objetivo: Validar el algoritmo de la polaridad del QRS en una cohorte moderna de sujetos sometidos a ablación con catéter por radiofrecuencia (ACRF). Nuestro objetivo fue determinar su precisión global y su precisión para las VA parahisianas. Métodos: Realizamos un análisis retrospectivo de pacientes con síndrome de Wolff-Parkinson-White (WPW) a los que se les realizó estudio electrofisiológico (EEF) y ACRF. Empleamos el algoritmo de la polaridad del QRS para predecir la ubicación anatómica de la VA y comparamos este resultado con la ubicación anatómica real determinada en el EEF. Para determinar la precisión se utilizaron el coeficiente kappa de Cohen (k) y el coeficiente de correlación de Pearson. Resultados: Se incluyeron un total de 364 pacientes (edad media 30 años, 57 % varones). La puntuación k global fue de 0,78 y el coeficiente de Pearson de 0,90. También se evaluó la precisión para cada zona, la mejor correlación fue para las VA laterales izquierdas (k de 0.97). Hubo 26 pacientes con VA parahisianas, que mostraron una gran variabilidad en las características del ECG. Empleando el algoritmo de la polaridad del QRS, el 34,6 % de los pacientes tenía una ubicación anatómica correcta, el 42,3 % tenía una ubicación adyacente y solo el 23 % una ubicación incorrecta. Conclusión: El algoritmo de la polaridad del QRS tiene una buena precisión global; su precisión es alta, especialmente para VA lateral izquierdo. Este algoritmo también es útil para la VA parahisiana.

Automated extraction of information from free text of Spanish oncology pathology reports

Background: Pathology reports are stored as unstructured, ungrammatical, fragmented, and abbreviated free text with linguistic variability among pathologists. For this reason, tumor information extraction requires a significant human effort. Recording data in an efficient and high-quality format is essential in implementing and establishing a hospital-based-cancer registry Objective: This study aimed to describe implementing a natural language processing algorithm for oncology pathology reports. Methods: An algorithm was developed to process oncology pathology reports in Spanish to extract 20 medical descriptors. The approach is based on the successive coincidence of regular expressions. Results: The validation was performed with 140 pathological reports. The topography identification was performed manually by humans and the algorithm in all reports. The human identified morphology in 138 reports and by the algorithm in 137. The average fuzzy matching score was 68.3 for Topography and 89.5 for Morphology. Conclusions: A preliminary algorithm validation against human extraction was performed over a small set of reports with satisfactory results. This shows that a regular-expression approach can accurately and precisely extract multiple specimen attributes from free-text Spanish pathology reports. Additionally, we developed a website to facilitate collaborative validation at a larger scale which may be helpful for future research on the subject.

Introducción: Los reportes de patología están almacenados como texto libre sin estructura, gramática, fragmentados o abreviados, con variabilidad lingüística entre patólogos. Por esta razón, la extracción de información de tumores requiere un esfuerzo humano significativo. Almacenar información en un formato eficiente y de alta calidad es esencial para implementar y establecer un registro hospitalario de cáncer. Objetivo: Este estudio busca describir la implementación de un algoritmo de Procesamiento de Lenguaje Natural para reportes de patología oncológica. Métodos: Desarrollamos un algoritmo para procesar reportes de patología oncológica en Español, con el objetivo de extraer 20 descriptores médicos. El abordaje se basa en la coincidencia sucesiva de expresiones regulares. Resultados: La validación se hizo con 140 reportes de patología. La identificación topográfica se realizó por humanos y por el algoritmo en todos los reportes. La morfología fue identificada por humanos en 138 reportes y por el algoritmo en 137. El valor de coincidencias parciales (fuzzy matches) promedio fue de 68.3 para Topografía y 89.5 para Morfología. Conclusiones: Se hizo una validación preliminar del algoritmo contra extracción humana sobre un pequeño grupo de reportes, con resultados satisfactorios. Esto muestra que múltiples atributos del espécimen pueden ser extraídos de manera precisa de texto libre de reportes de patología en Español, usando un abordaje de expresiones regulares. Adicionalmente, desarrollamos una página web para facilitar la validación colaborativa a gran escala, lo que puede ser beneficioso para futuras investigaciones en el tema.

Correlación fisiopatológica, diagnóstica y terapéutica en el derrame pleural paraneumónico / Pathophysiological, diagnostic and therapeutic correlation in parapneumonic pleural effusion

Introducción: La inflamación de la pleura desencadenada por bacterias y mediada por citocinas, aumenta la permeabilidad vascular y produce vasodilatación, lo cual genera desequilibrio entre la producción de líquido pleural y su capacidad de reabsorción por eficientes mecanismos fisiológicos. La condición anterior conduce al desarrollo de derrame pleural paraneumónico. Objetivo: Exponer la importancia de la correlación fisiopatológica y diagnóstica con los pilares fundamentales de actuación terapéutica en el derrame pleural paraneumónico. Métodos: Revisión en PubMed y Google Scholar de artículos publicados hasta abril de 2021 que abordaran el derrame pleural paraneumónico, su fisiopatología, elementos diagnósticos, tanto clínicos como resultados del estudio del líquido pleural, pruebas de imágenes, y estrategias terapéuticas. Análisis y síntesis de la información: El progreso de una infección pulmonar y la producción de una invasión de gérmenes al espacio pleural favorece la activación de mecanismos que conllevan al acúmulo de fluido, depósito de fibrina y formación de septos. Este proceso patológico se traduce en manifestaciones clínicas, cambios en los valores citoquímicos y resultados microbiológicos en el líquido pleural, que acompañados de signos radiológicos y ecográficos en el tórax, guían la aplicación oportuna de los pilares de tratamiento del derrame pleural paraneumónico. Conclusiones: Ante un derrame pleural paraneumónico, con tabiques o partículas en suspensión en la ecografía de tórax, hallazgo de fibrina, líquido turbio o pus en el proceder de colocación del drenaje de tórax, resulta necesario iniciar fibrinólisis intrapleural. Cuando el tratamiento con fibrinolíticos intrapleurales falla, la cirugía video-toracoscópica es el procedimiento quirúrgico de elección(AU)

Introduction: The inflammation of the pleura triggered by bacteria and mediated by cytokines, increases vascular permeability and produces vasodilation, which generates imbalance between the production of pleural fluid and its resorption capacity by efficient physiological mechanisms. The above condition leads to the development of parapneumonic pleural effusion. Objective: To expose the importance of the pathophysiological and diagnostic correlation with the fundamental pillars of therapeutic action in parapneumonic pleural effusion. Methods: Review in PubMed and Google Scholar of articles published until April 2021 that addressed parapneumonic pleural effusion, its pathophysiology, diagnostic elements, both clinical and results of the pleural fluid study, imaging tests, and therapeutic strategies. Analysis and synthesis of information: The progress of a lung infection and the production of an invasion of germs into the pleural space favors the activation of mechanisms that lead to the accumulation of fluid, fibrin deposition and formation of septa. This pathological process results in clinical manifestations, changes in cytochemical values and microbiological results in the pleural fluid, which accompanied by radiological and ultrasound signs in the chest, guide the timely application of the pillars of treatment of parapneumonic pleural effusion. Conclusions: In the event of a parapneumonic pleural effusion, with septums or particles in suspension on chest ultrasound, finding fibrin, turbid fluid or pus in the procedure of placement of the chest drain, it is necessary to initiate intrapleural fibrinolytic. When treatment with intrapleural fibrinolytics fails, video-thoracoscopic surgery is the surgical procedure of choice(AU)

Challenges faced by the HIV testing system in low- and middle-income countries

Introduction: Determining the HIV status of some individuals remains challenging due to multidimensional factors such as flaws in diagnostic systems, technological challenges, and viral diversity. This report pinpoints challenges faced by the HIV testing system in Cameroon. Case presentation: A 53-year-old male received a positive HIV result by a rapid testing algorithm in July 2016. Not convinced of his HIV status, he requested additional tests. In February 2017, he received a positive result using ImmunoComb® II HIV 1 & 2 BiSpot and Roche cobas electrochemiluminescence assays. A sample sent to France in April 2017 was positive on the Bio-Rad GenScreen™ HIV 1/2, but serotyping was indeterminate, and viral load was < 20 copies/mL. The Roche electrochemiluminescence immunoassay and INNO-LIA HIV I/II Score were negative for samples collected in 2018. A sample collected in July 2019 and tested with VIDAS® HIV Duo Ultra enzyme-linked fluorescent assay and Geenius™ HIV 1/2 Confirmatory Assay was positive, but negative with Western blot; CD4 count was 1380 cells/mm3 and HIV proviral DNA tested in France was 'target-not-detected'. Some rapid tests were still positive in 2020 and 2021. Serotyping remained indeterminate, and viral load was 'target-not-detected'. There were no self-reported exposure to HIV risk factors, and his wife was HIV-seronegative.Management and outcome: Given that the patient remained asymptomatic with no evidence of viral replication, no antiretroviral therapy was initiated. Conclusion: This case highlights the struggles faced by some individuals in confirming their HIV status and the need to update existing technologies and develop an algorithm for managing exceptional cases.

Using machine learning algorithm to predict the risk of post-traumatic stress disorder among firefighters in Changsha / 中南大学学报(医学版)

OBJECTIVES@#Firefighters are prone to suffer from psychological trauma and post-traumatic stress disorder (PTSD) in the workplace, and have a poor prognosis after PTSD. Reliable models for predicting PTSD allow for effective identification and intervention for patients with early PTSD. By collecting the psychological traits, psychological states and work situations of firefighters, this study aims to develop a machine learning algorithm with the aim of effectively and accurately identifying the onset of PTSD in firefighters, as well as detecting some important predictors of PTSD onset.@*METHODS@#This study conducted a cross-sectional survey through convenient sampling of firefighters from 20 fire brigades in Changsha, which were evenly distributed across 6 districts and Changsha County, with a total of 628 firefighters. We used the synthetic minority oversampling technique (SMOTE) to process data sets and used grid search to finish the parameter tuning. The predictive capability of several commonly used machine learning models was compared by 5-fold cross-validation and using the area under the receiver operating characteristic curve (ROC-AUC), accuracy, precision, recall, and F1 score.@*RESULTS@#The random forest model achieved good performance in predicting PTSD with an average AUC score at 0.790. The mean accuracy of the model was 90.1%, with an F1 score of 0.945. The three most important predictors were perseverance, forced thinking, and reflective deep thinking, with weights of 0.165, 0.158, and 0.152, respectively. The next most important predictors were employment time, psychological power, and optimism.@*CONCLUSIONS@#PTSD onset prediction model for Changsha firefighters constructed by random forest has strong predictive ability, and both psychological characteristics and work situation can be used as predictors of PTSD onset risk for firefighters. In the next step of the study, validation using other large datasets is needed to ensure that the predictive models can be used in clinical setting.

Research on multi-Atlas segmentation based on feature clustering / 中华放射肿瘤学杂志

Objective:To study the improvement of normal tissue region of interest (ROI) segmentation based on clustering-based multi-Atlas segmentation method, thereby achieving better delineation of organs at risk.Methods:CT images of 100 patients with cervical cancer who had completed treatment in Zhejiang Cancer Hospital during 2019-2020 were selected as the Atlas database. According to the volume characteristic parameters of the organs at risk (bladder, rectum and outer contour), the Atlas database was divided into several subsets by k-means clustering algorithm. The image to be segmented was matched to the corresponding Atlas library for multi-Atlas segmentation. The dice similarity coefficient (DSC) was used to evaluate the segmentation results.Results:Using 30 patients as the test set, the sub-Atlas generated by different clustering methods were compared for the improvement of image segmentation results. Compared with general multi-Atlas segmentation methods, clustering-based multi-Atlas segmentation method significantly improve the segmentation accuracy for the bladder (DSC=0.83±0.09 vs. 0.69±0.15, P<0.001) and the rectum (0.7±0.07 vs. 0.56±0.16, P<0.001), but no statistical significance was observed for left and right femoral head (0.92±0.04, 0.91±0.02) and bone marrow (0.91±0.06). The average segmentation time of clustering-based multi-Atlas segmentation method was shorter than that of the general multi-Atlas segmentation method (2.7 min vs. 6.3 min). Conclusion:The clustering-based multi-Atlas segmentation method can not only reduce the number of Atlas images registered with the image to be segmented, but also can be expected to improve the segmentation effect and obtain higher accuracy.

Evaluation of technical performance of stereotactic radiosurgery algorithm in optical surface imaging system in non-coplanar radiotherapy / 中华放射肿瘤学杂志

Objective:To evaluate the accuracy and stability of stereotactic radiosurgery (SRS) algorithm in optical surface imaging (OSI) system in non-coplanar radiotherapy.Methods:Three OSI imaging systems were used to measure the phantom repeatedly at different couch rotation angles to analyze the accuracy and stability of OSI system. Seven patients with multiple brain metastases who underwent single-center non-coplanar radiotherapy were randomly selected, and the accuracy and stability of OSI for patient imaging were analyzed. Stability is defined as the difference between the two OSI measurements when the couch is turned from 0° to a non 0° angle, and then back to 0°, using the 0° cone beam CT (CBCT) as the "gold standard". Accuracy is defined as the difference between OSI and CBCT (at 0° couch angle) measurement data. The measurement data with normal distribution were described as Mean ± SD. The data with non-normal distribution were expressed as M (Q). The difference of the former data was compared by one-way ANOVA, and the difference of the latter data was assessed by Kruskal-Wallis H nonparametric test. Results:For non-coplanarity, the translation accuracy of the phantom and the patient was ≤ 1.30 mm and ≤ 1.00 mm, and the rotation accuracy was ≤ 0.50° and ≤ 0.60°, respectively. The translation errors mainly occurred in the left-right and head-foot directions. In terms of stability, the maximum standard deviation of phantom coplanar translation and rotation was 0.06 mm and 0.06°. The maximum standard deviation of patient translation and rotation was 0.17 mm and 0.19°.Conclusions:Although the new SRS algorithm improves the non-coplanar accuracy, it still cannot meet the precise requirements of non-coplanar single isocenter radiotherapy for multiple brain metastases, especially in the left-right and head-foot directions. When the couch rotation angle is large, OSI is not recommended for image-guided radiotherapy. However, its high stability can be used to monitor the intrafractional motion of patients.

Simulation calculation of relative biological effectiveness based on DNA double strand break clusters / 中华放射医学与防护杂志

Objective:To obtain the relative biological effectiveness (RBE) of DNA double strand breaks (DSB) clusters by tracing the mechanism of radiated DNA damage, and explore the relationship among the biological effectiveness of DNA damage, chromosomal aberrations and germ cell death.Methods:Taking low-energy electrons, protons, and α particles as the research objects, this study simulated the process that cell nuclei were exposed to particle radiation using a radiation-related physicochemical model. On the ground of the DSB density-based spatial clustering of applications with noise (DBSCAN) algorithm, the DSB cluster classification method was improved to weaken the connection between the DSBs and the random distribution assumptions of energy depositions during the simulation. In this manner, the DSB clusters can be much closer to a non-random distribution. Furthermore, this study obtained the yields of DSB clusters and proposed a method to calculate the RBE values of DSB clusters.Results:The calculated RBE value (12.29) of DSB clusters of 2 MeV α particles was similar to the experimental RBE values of chromosomal fragments (15.3±5.9) and cell survival (14.7±5.1).Conclusions:After high-LET ionizing radiation, unlike the single DSB, the RBE of DSB clusters was similar to that of chromosomal aberration and cell survival.

Influencing factors of survival and prognosis of patients with bladder urothelial carcinoma after surgical treatment and recommendation of an artificial intelligence algorithm / 现代泌尿外科杂志

【Objective】 To explore the factors influencing the survival and prognosis of patients with bladder urothelial carcinoma (BUC) after surgical treatment, and to establish an artificial intelligence algorithm to predict the effects of different surgical regimens. 【Methods】 BUC patients treated with surgery during Jan.2007 and Jan.2019 in The Second Hospital of Dalian Medical University and Nanfang Hospital of Southern Medical University were enrolled. The complete clinical and follow-up data were collected. Deep neural network (DNN) was used to establish an artificial intelligence algorithm model. A prediction model of survival and prognosis was established, and the influencing factors of survival were explored and ranked by the artificial intelligence algorithm. 【Results】 A total of 832 patients were involved, including 438 (52.64%) treated in The Second Hospital of Dalian Medical University, and 394 (47.36%) treated in Nanfang Hospital of Southern Medical University. Of all cases, 579 (69.6%) were non-muscle invasive bladder cancer, and 253 (30.4%) were muscle invasive bladder cancer. Transurethral resection of bladder tumor was conducted in 539 (64.8%) cases, partial cystectomy in 66 (7.9%) cases, and total cystectomy in 227 (27.3%) cases. The data of patients treated in Second Hospital of Dalian Medical University were used for DNN modeling, and the data of patients treated in Nanfang Hospital of Southern Medical University were used for external verification after modeling. Finally, it was concluded that the factors affecting survival and prognosis were T stage, pathological grade, hypertension or cardiovascular and cerebrovascular disease, hemoglobin, blood calcium, smoking, albumin, lymphocytes, age, ratio of albumin/globulin, operation method, N stage, and creatinine clearance rate in descending order. The model could be used for preoperative prediction. 【Conclusion】 Through DNN modeling and external verification, the influencing factors of postoperative survival can be predicted for patients with bladder cancer, and the surgical effects can also be predicted before operation. The model can provide artificial intelligence algorithm support for the selection of surgical methods and postoperative follow-up plans.

Applicability of feature selection combined with Boosting algorithm in severity prediction of non-fatal occupational injuries in miners / 环境与职业医学

Background Identification and analysis of influencing factors of occupational injury is an important research content of feature selection. In recent years, with the rise of machine learning algorithms, feature selection combined with Boosting algorithm provides a new analysis idea to construct occupational injury prediction models. Objective To evaluate applicability of Boosting algorithm-based model in predicting severity of miners' non-fatal occupational injuries, and provide a basis for rationally predicting the severity level of miners' non-fatal occupational injuries. Methods The publicly available data of the US Mine Safety and Health Administration (MSHA) from 2001 to 2021 on metal miners' non-fatal occupational injuries were used, and the outcome variables were lost working days < 105 d (minor injury) and ≥ 105 d (serious injury). Four different feature sets were screened out by four feature selection methods including least absolute shrinkage and selection operator (Lasso) regression, stepwise regression, single factor + Lasso regression, and single factor + stepwise regression. Logistic regression, gradient boosting decision tree (GBDT), and extreme gradient boosting (XGBoost) were selected to construct prediction models by training with the four feature sets. A total of 12 prediction models of severity of miners' non-fatal occupational injuries were built and their area under the curve (AUC), sensitivity, specificity, and Youden index were calculated for model evaluation. Results According to the results of four feature selection methods, age, time of accident occurrence, total length of service, cause of injury, activities that triggered injury occurrence, body part of injury, nature of injury, and outcome of injury were identified as influencing factors of non-fatal occupational injury severity in miners. Feature set 4 was the optimal set screened out by single factor+stepwise regression and the GBDT model presented the best predictive performance in predicting the severity of non-fatal occupational injuries. The associated specificity, sensitivity, and Youden index were 0.7530, 0.9490, and 0.7020, respectively. The AUC values of logistic regression, GBDT, and XGBoost models trained by feature set 4 were 0.8526 (95%CI: 0.8387, 0.8750), 0.8640 (95%CI: 0.8474, 0.8806), and 0.8603 (95%CI: 0.8439, 0.8773), respectively, higher than the AUC values trained by feature set 2 [0.8487 (95%CI: 0.8203, 0.8669), 0.8110 (95%CI: 0.8012, 0.8344), and 0.8439 (95%CI: 0.8245, 0.8561), respectively] . The AUC values of GBDT and XGBoost models trained by feature set 4 were higher than that of logistic regression model. Conclusion The performance of the prediction models constructed by predictors screened out by two feature selection methods is better than those by single feature selection methods. At the same time, under the condition of optimal feature set, the performance of model prediction based on Boosting is better than that of traditional logistic regression model.

Prediction of CW chord after cataract surgery from IOL Master 700 measurement data based on SVR algorithm and BP neural network / 国际眼科杂志(Guoji Yanke Zazhi)

AIM: To observe the changes in the Chang-Warning chord(CW chord)before and after cataract surgery using the IOL Master 700 and predict the CW chord using an artificial intelligence prediction model and preoperative measurement data.METHODS: The analysis was conducted on the preoperative and postoperative IOL Master 700 measurements of 304 cataract patients. This included astigmatism vector value, average keratometry, axial length, anterior chamber depth, lens thickness, corneal central thickness, white-to-white, the position of the Purkinje reflex I image relative to the corneal center and pupil center, and the CW chord. A prediction model based on the SVR algorithm and the BP neural network algorithm was established to predict the postoperative CW chord using the preoperative CW chord and ocular biological parameters.RESULTS: The X component of the CW chord showed a slight shift in the temporal direction in both the left and right eyes after cataract surgery, while the Y component changed little. The SVR model, using the preoperative CW chord and other preoperative biometric parameters as input data, was able to predict the X and Y components of the CW chord more accurately than the BP neural network.CONCLUSION: The CW chord can be directly measured with a coaxial fixation light using various biometers, corneal topographers, or tomographers. The use of the SVR algorithm can accurately predict the postoperative CW chord before cataract surgery.

Optimization of the pressurized processing technology of Strychnos nux-vomica boiled with mung beans based on genetic algorithm / 中国药房

OBJECTIVE To optimize the pressurized processing technology of Strychnos nux-vomica boiled with mung beans. METHODS The least squares method was used to establish a one-dimensional model for the effects of four factors， namely， processing time， processing pressure， mung bean dosage and water added， on the contents of strychnine and toxiferine， and the multivariate model hypothesis was proposed by analyzing the function of one-dimensional model. Based on the orthogonal experiment， the genetic algorithm was used to solve the undetermined coefficients in the model. A bi-objective optimization model based on strychnine and toxiferine content was constructed according to the actual conditions， and the optimal technology was obtained by solving the model function and validated. RESULTS The optimal processing technology was boiling S. nux-vomica with mung beans at 2.393 MPa saturated steam pressure for 5.5 h， and then draining； rinsing to remove mung beans， scraping off the bark of S. nux-vomica and cutting into slice of 0.6 mm； using 180 g of mung beans and 15 L of water per 500 g of S. nux- vomica. CONCLUSIONS The optimized pressurized processing technology is stable and feasible， and can provide a reference for the optimization of processing technology of S. nux-vomica boiled with mung beans.

Analysis of the application risks and legal strategies of intelligent medical algorithms / 中华医院管理杂志

Artificial intelligence algorithms play an important role in the medical field with their unique technological advantages and operational logic. However, due to the " black box" nature and security flaws of artificial intelligence algorithms, there were problems in the application of intelligent medical algorithms, such as the alienation of medical personnel′s subject status, the alienation of right to informed consent for diagnosis and treatment, the alienation of health fairness, and the alienation of health information security. At the same time, there were some practical difficulties in the process of regulating risks, such as the difficulty in determining the responsibility of the legal person, the incompleteness of the causal chain, the lag of the scene regulation of laws and regulations, and the increasing difficulty in protecting health information. In order to prevent the alienation of power in medical intelligent algorithms and promote the healthy development of intelligent medicine, the author suggested to adhere to the embedding of tool attributes in the underlying logic of medical algorithms, enhance the interpretability of medical algorithms, improve relevant laws and regulations, and strengthen the risk supervision mechanism of intelligent medical algorithms.

Feasibility study on rapid identification of methicillin-resistant Staphylococcus aureus by different algorithms of MALDI-TOF mass spectrometry / 中华检验医学杂志

Objective:To explore the feasibility of rapid identification of methicillin-resistant Staphylococcus aureus using different algorithms of the matrix-assisted laser desorption/ionization time of flight (MALDI-TOF) mass spectrometer. Methods:Totally 314 clinical isolates of Staphylococcus aureus were selected from the bacterial bank at Beijing Tongren Hospital from January 2017 to June 2019. The samples were identified by MALDI-TOF MS, and screened by cefoxitin disk method (inhibition ring diameter ￡21 mm) and PCR mecA gene. The strains were divided into a methicillin-resistant Staphylococcus aureus (MRSA) group (130 strains) and a methicillin-susceptible Staphylococcus aureus (MSSA) group (184 strains). Then, after collecting the spectrograms of these samples using formic acid extraction, the MRSA group and MSSA group were divided into three subgroups each, namely MRSA-1 (43 strains), MRSA-2 (42 strains), MRSA-3 (45 strains) and MSSA-1 (60 strains), MSSA-2 (61 strains) and MSSA-3 (63 strains). The groups were studied using genetic algorithm (GA), fast classification algorithm (QC) and supervised neural network algorithm (SNN) in the ClinProTools software on the Bruker MALDI-TOF mass spectrometer, and the convolutional neural network algorithm (CNN) in the Ex-SmartSpec software on the Zhongyuan Hui-Ji mass spectrometer. These studies were repeated for 3 rounds. The first round with MRSA-1 and MRSA-2, MSSA-1 and MSSA-2 being model groups, MRSA-3 and MSSA-3 being validation groups. The validation groups were rotated for each round. The areas under the receiver operating characteristic (ROC) curve expansions of the four algorithms were used to confirm each program′s performance. Then, 38 MRSA strains and 40 MSSA clinical strains were selected from the bacterial bank of the Laboratory of Beijing Tongren Hospital from July 2019 to December 2019, and were put through the formic acid extraction method to collect their spectra. These samples were tested independently with their convolutional neural network models. Results:After three rounds of modeling and verification, the areas under the ROC curves of the three Bruker ClinProTools programs were as follows: for genetic algorithm, the areas were 0.89, 0.74, and 0.64 respectively; for fast classification algorithm, the areas were 0.77, 0.95, and 0.94 respectively; and for supervised neural network algorithm, the areas were 0.90, 0.98, and 0.98 respectively. The areas under the ROC curves of the convolutional neural network algorithm with Zhongyuan Huiji mass spectrometer′s Ex-SmartSpec software were 0.95, 0.99, and 0.99 respectively. The independent test results of convolutional neural network algorithm showed that these results have an accuracy, specificity, sensitivity and AUC of 88.82% (810/912), 81.15% (779/960), 84.88% (1 589/1 872) and 0.92 respectively.Conclusions:The supervised neural network algorithm of Bruker′s ClinProTools and the convolutional neural network algorithm of Zhongyuan Hui-Ji mass spectrometer′s EX-Smartspec is clinically acceptable for rapid identification of MRSA performance indicators. Using convolutional neural network algorithm and MALDI-TOF mass spectrometry, MRSA strains can be identified quickly, providing timely advice for clinical medications.

Value of serum interleukin-6 and tumor necrosis factor-α in early diagnosis of severe acute pancreatitis / 临床肝胆病杂志

Objective To investigate the value of serum cytokines in the early diagnosis of severe acute pancreatitis (SAP), and to improve the accuracy of the diagnosis of SAP by establishing a mathematical model with composite indices based on LASSO algorithm. Methods A total of 130 patients with acute pancreatitis (AP) who attended Changshu First People's Hospital from January 2019 to June 2022 were enrolled, among whom there were 73 SAP patients and 57 non-SAP patients.Peripheral serum samples were collected from all patients, and Luminex xMAP liquid chip technique was used to measure 13 serum cytokines.Meanwhile, Acute Physiology and Chronic Health Evaluation Ⅱ(APACHE Ⅱ), Bedside Index for Severity in Acute Pancreatitis (BISAP), and Computed Tomography Severity Index (CTSI) scores were determined for all patients.The Kolmogorov-Smirnov method was used for normality test; the independent-samples t test was used for comparison of normally distributed continuous data between two groups, and the Mann-Whitney U test was used for comparison of non-normally distributed continuous data between two groups; the chi-square test was used for comparison of categorical data between two groups.Furthermore, the binary logistic regression analysis was used to evaluate the effect of cytokines on SAP, and the linear regression analysis was used to investigate the correlation between cytokines and SAP severity.The partial correlation analysis was used to evaluate the correlation between cytokines and SAP severity score after adjustment for covariates[age, sex, body mass index (BMI), and history of hypertension and diabetes].The LASSO algorithm was used to establish a mathematical model with composite indices; the receiver operating characteristic (ROC) curve was used to assess the performance of serum cytokines in the clinical diagnosis of SAP, and the area under the ROC curve (AUC) was calculated. Results Compared with the SAP group, the non-SAP group had significantly lower APACHE Ⅱ, BISAP, CTSI, and modified Marshall scores (all P < 0.001).Compared with the non-SAP group, the SAP group had significantly higher levels of interferon-γ(IFN-γ), interleukin-6(IL-6), interleukin-8, and tumor necrosis factor-α(TNF-α) and a significantly lower level of interleukin-12(all P < 0.05).The logistic regression analysis showed that IFN-γ(odds ratio[ OR ]=1.190, 95% confidence interval[ CI ]: 1.036-1.367, P =0.014), IL-6 ( OR =1.148, 95% CI : 1.070-1.231, P < 0.001), and TNF-α ( OR =1.100, 95% CI : 1.048-1.155, P < 0.001) were independent influencing factors for SAP.The partial correlation analysis showed that after adjustment for sex, age, BMI, and history of chronic diseases (diabetes and hypertension), the levels of IL-6 and TNF-α were positively correlated with APACHE Ⅱ score in SAP patients (IL-6: r =0.503, P < 0.001;TNF-α: r =0.557, P < 0.001).The linear regression analysis showed that the levels of IL-6 and TNF-α were associated with APACHE Ⅱ score in SAP patients (IL-6: β =0.049, P =0.044;TNF-α: β =0.054, P =0.046), and there was an interaction between IL-6 and TNF-α, which affected APACHE Ⅱ score.The ROC curve analysis showed that the risk score based on IL-6 and TNF-α using LASSO algorithm had the largest AUC of 0.925 in distinguishing SAP from non-SAP, while IL-6 or TNF-α alone had an AUC of 0.885 and 0.878, respectively.The partial correlation analysis showed that after adjustment for sex, age, BMI, and history of chronic diseases (diabetes and hypertension), the risk score was positively correlated with APACHE Ⅱ score in SAP patients ( r =0.565, P < 0.001). Conclusion The serum levels of IL-6 and TNF-α can reflect the severity of AP.The risk score combining serum IL-6 and TNF-α can significantly improve the accuracy of the early diagnosis of SAP, which has an important clinical value in the clinical diagnosis and treatment of SAP.