Diagnosis and Treatment Reasoning of Integrated Traditional Chinese and Western Medicine Against Acute Abdomen Based on Knowledge Graph / 中国实验方剂学杂志

ObjectiveIn view of the standardization of clinical diagnosis and treatment of the acute abdomen and the inheritance of diagnosis and treatment experience of prestigious veteran traditional Chinese medicine（TCM） doctors， a diagnosis and treatment reasoning algorithm based on association rule mining under incomplete evidence（AMIE）+ random walk was proposed to provide information services and technical support for primary doctors by recommending personalized diagnosis and treatment plans based on medical records. MethodThe experience of diagnosis and treatment of acute abdomen of prestigious veteran TCM doctors and the text data of clinical diagnosis and treatment guidelines of integrated TCM and western medicine were collected to complete the task of knowledge extraction and construct acute abdomen knowledge graph based on Neo4j. On the basis of ontology-supported rule-based reasoning， the rule reasoning based on similar syndromes was used to expand the syndrome combinations whose Jaccard similarity was greater than the threshold in the syndrome recommendation results. The semantic path coverage algorithm was used to calculate the semantic similarity between the symptom nodes. The symptom nodes were divided into 10 categories， and the symptom nodes in the same category were extended. The random walk algorithm was used to search the symptom nodes connected with the syndrome， and the connection rules between the syndrome and symptom nodes were extended to realize the knowledge reasoning of AMIE+ random walk. ResultThe acute abdomen knowledge graph included 1 320 nodes and 2 464 relationships. According to the link prediction evaluation index of knowledge reasoning， the reasoning results of the three algorithms in the auxiliary diagnosis and treatment of acute abdomen were compared. The AMIE+ random walk algorithm complemented the knowledge graph by extending the similar syndrome connection rules and the syndrome-symptom connection rules. Compared with the knowledge reasoning algorithm based on ontology rules， the area under the curve （AUC） was 15.18% higher and the accuracy was 30.36% higher， which achieved more accurate and effective knowledge inference. ConclusionThis study used knowledge graph technology to visualize the diagnosis and treatment of acute abdomen with TCM and western medicine， assisting primary clinicians in intuitively viewing the diagnosis and treatment process and data relationship. The proposed diagnosis and treatment reasoning algorithm can realize the personalized diagnosis and treatment plan recommendation at the level of "disease-syndrome-diagnosis-treatment-prescription"， which can assist primary doctors in disease diagnosis and treatment and clinical decision-making， contribute to the knowledge sharing and application of diagnosis and treatment experience and clinical guidelines of prestigious veteran TCM doctors， improve the level of primary clinical diagnosis and treatment， and promote the normalization and standardization of the diagnosis and treatment process of acute abdomen with integrated TCM and western medicine.

Lung nodule segmentation based on fuzzy c-means clustering and improved random walk algorithm / 生物医学工程学杂志

Accurate segmentation of pulmonary nodules is an important basis for doctors to determine lung cancer. Aiming at the problem of incorrect segmentation of pulmonary nodules, especially the problem that it is difficult to separate adhesive pulmonary nodules connected with chest wall or blood vessels, an improved random walk method is proposed to segment difficult pulmonary nodules accurately in this paper. The innovation of this paper is to introduce geodesic distance to redefine the weights in random walk combining the coordinates of the nodes and seed points in the image with the space distance. The improved algorithm is used to achieve the accurate segmentation of pulmonary nodules. The computed tomography (CT) images of 17 patients with different types of pulmonary nodules were selected for segmentation experiments. The experimental results are compared with the traditional random walk method and those of several literatures. Experiments show that the proposed method has good accuracy in the segmentation of pulmonary nodule, and the accuracy can reach more than 88% with segmentation time is less than 4 seconds. The results could be used to assist doctors in the diagnosis of benign and malignant pulmonary nodules and improve clinical efficiency.

Effect of Tripterygium Glycosides Tablets on immune-induced liver and kidney function in patients with rheumatoid arthritis based on data mining / 中国中药杂志

This paper aims to investigate the effect of oral administration of Tripterygium Glycosides Tablets combined with traditional Chinese medicine on immune inflammatory index in patients with rheumatoid arthritis,in order to explore the compatibility mode of traditional Chinese medicine in the treatment of rheumatoid arthritis. Medical records of hospitalized patients with rheumatology at the First Affiliated Hospital of Anhui University of Traditional Chinese Medicine from June 2012 to December 2017 were collected. The combined administration of Tripterygium Glycosides Tablets and traditional Chinese medicine was adopted for the experimental group,while the simply administration of Tripterygium Glycosides Tablets were adopted for the control group. SPSS 21. 0 was used to analyze the changes of general conditions and immune inflammatory metabolic indexes in the two groups of RA patients. The association rules were analyzed by SPSS Clementine 14. 2 software Apriori module,and the random walk model was evaluated by ORACLE 10 g tool. The results showed that a total of 1 220 patients with rheumatoid arthritis met the requirements of this study,including 322 in the experimental group and 898 in the control group. Before treatment,there was no significant difference in age and duration between the two groups. The difference value of Ig A,Ig G,RF,CCP-AB,hs-CRP and ESR in the two groups of RA patients decreased before and after treatment,and the experimental group was superior to the control group in reduction of Ig A,Ig G,RF,CCP-AB,hs-CRP and ESR.The control group was superior to the experimental group in reduction of Ig M( P<0. 01 or P<0. 05). Compared with before treatment,ALT,AST,ALP,GGT,CREA,BUN,b-MG,MA,TRU and Ig U all increased,with statistically significant differences( P<0. 01).The UA of the two groups of RA patients decreased after treatment,with statistically significant differences( P<0. 01). The experimental group was superior to the control group in reduction of UA,with statistically significant differences( P < 0. 05 or P < 0. 01). The herbs adopted in the prescriptions of 1 220 patients were mainly classified into four categories,namely spleen-sweating herbs,blood-activating and stasis-relieving herbs,phlegm and phlegm-relieving herbs,and heat-clearing and antidote herbs. The results of association rule analysis indicated a significant correlation between the single-flavored Tripterygium Glycosides Tablets,oral Chinese medicine and immune inflammation,and improvement of liver and kidney function indexes. The results of the random walk model analysis indicated that the experimental group's Ig M and hs-CRP were superior to those of the control group in terms of random fluctuation maximum,walking positive growth rate,comprehensive evaluation index increasing rate,comprehensive improvement rate,comprehensive evaluation index recording times,and expected improvement value. The results of this study showed that the single administration of Tripterygium Glycosides Tablets can effectively improve the immune inflammatory metabolic index of patients with rheumatoid arthritis,and the combined administration of Tripterygium Glycosides Tablets and traditional Chinese medicine could alleviate the immune inflammatory index of RA patients and reduce liver and kidney dysfunction compared with simple oral administration. The comprehensive evaluation Ig M and hs-CRP in the group of combined administration of Tripterygium Glycosides Tablets and traditional Chinese medicine were better than those in the group of the Tripterygium Glycosides Tablets. There was a long-term correlation between the comprehensive evaluation index and the intervention measures of the two groups of patients.

Effect of traditional Chinese medicine invigorating spleen unit therapy on inflammatory markers in patients with osteoarthritis based on random walk model / 中国中药杂志

To evaluate the effect of traditional Chinese medicine(TCM) invigorating spleen unit therapy on inflammatory markers of osteoarthritis(OA) patients by random walk model. The patient information was collected by the data processing system of medical records of the First Affiliated Hospital of Anhui University of Traditional Chinese Medicine. In-patient information of the department of rheumatology of the hospital between June 2012 and December 2016 was collected and summarized. Based on the use of traditional Chinese medicine decoction and hospital-prepared compound Qiyi Capsules(Xinfeng Capsules),the patients were divided into the unit therapy group and the simple endotherapy group. The random walk model was used to evaluate the effect of traditional Chinese medicine invigorating spleen unit therapy on TCM spleen therapy unit(ESR) and high sensitive C reactive protein(hs-CRP). A total of 3 517 cases of OA patients met the study requirements. The simple endotherapy group had 1 771 cases(50. 36%),while the unit therapy group had 1 746 cases(49. 64%). The baseline data analysis showed that the general information of the cases,the TCM oral intake frequency and the core prescription information had no statistically significant difference,with comparability. The unit therapy group showed the maximum ESR stochastic volatility at 924,walking step number of 1 771,forward walking growth rate at 0. 264 5,ratio at3. 78,random fluctuation power law at 0. 306 5± 0. 076 8,positive increase rate of comprehensive evaluation index at 0. 264 5,and comprehensive evaluation index record number of 1 771; whereas the simple endotherapy group showed the maximum ESR random fluctuation value at 478,walking step number of 1 399,forward walking growth rate at 0. 152 4,ratio at 6. 56,random fluctuation power law at 0. 347 4±0. 101 7,positive increase rate of comprehensive evaluation index at 0. 152 4,and comprehensive evaluation index record number of 1 399. The unit therapy group showed the maximum hs-CRP random fluctuation value at 391,walking step number of1 081,forward walking growth rate at 0. 178 1,ratio at 5. 62,random fluctuation power law at 0. 343 6±0. 094 7,positive increase rate of comprehensive evaluation index at 0. 178 1,and comprehensive evaluation index record number of 1 081; while the simple endotherapy groups showed the maximum hs-CRP random fluctuation value at 210,walking step number of 797,forward walking growth rate at0. 113 2,ratio at 8. 83,random fluctuation power law at 0. 382 6±0. 109,positive increase rate of comprehensive evaluation index at0. 113 2,and comprehensive evaluation index record number of 797. According to our department of rheumatism,there was a longrange correlation between the two groups in the comprehensive evaluation index and the intervention measures. TCM spleen strengthening unit therapy has a better effect in alleviating the inflammatory index of OA than traditional Chinese medicine.

Evaluation of effect of Hibiscus paste external application combined with traditional Chinese medicine on inflammatory indices of patients with active rheumatoid arthritis based on random walk model / 中国免疫学杂志

Objective:To evaluate the effect of Hibiscus paste external application combined with traditional Chinese medicine on the inflammatory markers in patients with active rheumatoid arthritis (RA). Methods: The patient information was collected by the data processing system of hospitalized medical records in the First Affiliated Hospital of Anhui University of traditional Chinese medicine. The medical records of patients with rheumatoid arthritis in the Department of Rheumatology from May 2012 to December 2016 were collected. Patients were divided into experimental group and control group according to whether Furong ointment was applied. The random walk model was used to evaluate the influence of Furong ointment combined with traditional Chinese medicine on inflammatory index,erythrocyte sedimentation rate ( ESR) and high sensitivity C reactive protein ( Hs-CRP) in patients with active rheumatoid arthritis. Results: A total of 4 832 patients with rheumatoid arthritis were in accordance with the requirements of the study, including 2 579 in the experimental group and 2 253 in the control group. Baseline data analysis showed that there was no significant difference in general condition, frequency of oral Chinese medicine and core prescriptions between two groups ( P＞0. 05 ) . In the experimental group,the maximum ESR of inflammation index was 968,the walking rate was 3 756,the positive growth rate of walking was 0. 257 7,the ratio was 3. 88,the random fluctuation power law value was 0. 364 2±0. 124 6,the comprehensive evaluation index in-creased by 0. 479 9,and the comprehensive evaluation index was 2 017 times. In the control group,the maximum ESR of inflammation index was 398,the number of walking steps was 2 251,the positive growth rate of walking was 0. 176 8,the ratio was 5. 66,the random fluctuation power law value was 0. 173 5±0. 128 8,the comprehensive evaluation index increased by 0. 357,and the comprehensive evaluation index was 1 115 times. In the experimental group,the maximum Hs-CRP of inflammation index was 1 523,the walking rate was 5 149,the positive growth rate of walking was 0. 295 8,the ratio was 3. 38,the random fluctuation power law value was 0. 389 5± 0. 108 1,the comprehensive evaluation index increased by 0. 537 4,and the comprehensive evaluation index was 2 834 times. In the control group,the maximum Hs-CRP of inflammation index was 809,the number of walking steps was 3 463,the positive growth rate of walking was 0. 233 6,the ratio was 4. 28,the random fluctuation power law value was 0. 362 9±0. 073 8,the comprehensive evaluation index increased by 0. 448 2,and the comprehensive evaluation index was 1 805 times. Conclusion: Our hospital rheumatology on the treatment of rheumatoid arthritis from the spleen, oral Chinese medicine prescription to Jianpihuashi drugs, Huoxue Tongluo drugs, Qufengchushi drugs,drug detoxification,two groups of patients with comprehensive evaluation index and acceptable interventions are long-range correlation,a better effect than that of inflammatory markers associated with traditional Chinese medicine in patients with Furong ointment the simple use of Chinese herbs.

Predicción de la dinámica temporal de egresos hospitalarios por obesidad en niños y jóvenes en Estados Unidos / Prediction of the temporal dynamic of hospital discharges for obesity in children and youth in the united states

The prevalence of overweight in children worldwide is rising in developing countries. Diseases associated with childhood overweight as asthma, sleep apnea and diabetes mellitus, the latter being the most common among children and adolescents, imply another problem: the high cost to health, which has been analyzed by the National Center for Health Statistics in USA. The objective of this research was study mathematically the dynamics of the percentage of hospital discharges for overweight and obese patients between 6-17 years of age in the United States in order to predict the percentage of hospital discharges for obesity in the year 1999 in the context of probabilistic random walk, specifically from a total space of probability for analyzing the probabilistic behavior of increases and decreases, from the years between 1983 and 1998, in the United States. The predicted range for 1999 was 1,17%, which was then compared with data from the National Center for Health, which reported a 1,15%, achievinga 98,01% prediction. It was established a physical and mathematical order underlying the dynamics of hospital discharges rate for obesity in children, making predictions on its trajectory.

La prevalencia de sobrepeso en niños a nivel mundial tiende al incremento especialmente en países en vía de desarrollo. Enfermedades asociadas al sobrepeso infantil como asma, apnea del sueño y diabetes mellitus, siendo esta última la más frecuente en niños y adolescentes, implican otra problemática como es el alto costo en salud, el cual ha sido analizado por el Centro Nacional de Estadísticas de la Salud en los Estados Unidos. El objetivo de esta investigación fue estudiar matemáticamente la dinámica del porcentaje de altas hospitalarias por sobrepeso y obesidad de pacientes de 6 a 17 años de edad en los Estados Unidos con el fin de predecir el porcentaje de altas hospitalarias por obesidad en Estados Unidos para el año 1999, en el contexto de la caminata al azar probabilista, específicamente a partir de un espacio total de probabilidades que permite analizar el comportamiento probabilista de aumentos y disminuciones, a partir de los años comprendidos entre 1983 y 1998, en Estados Unidos. El rango predicho para el año 1999 fue de 1,17%, valor que fue posteriormente comparado con los datos del NCHS, que reportó un 1,15%, logrando una predicción del 98,01%. Se estableció un orden físico y matemático subyacente a la dinámica del porcentaje de altas hospitalarias por obesidad en niños, logrando realizar predicciones en su trayectoria.

Comparison of clustering methods in light of paper similarity network topology / 中华医学图书情报杂志

A paper similarity network was constructed in light of semantic similarity algorithm using the complex network processing package , igraph in R language , and analyzed by random walk-trap algorithm , label propagation algorithm, BGII algorithm, and Girvan-Newman algorithm, respectively.The accuracy and stability of these 4 al-gorithms were compared according to the golden standards and the D function for network community classification evaluation index, which showed that the accuracy and stability of random walk-trap algorithm were better than those of the other 3 algorithms and preconditioning of complex network was an important influencing factor for clustering .

Caminata al aza predictiva de la dinámica de oesidad: predicciones de obesidaad y sobrepeso en la población infantil de Colombia y de variación peso/talla y peso/edad en México / Predictive ranomm walk of obesity dynamic and redictions of obesity and overwweight in children from Colombia and weight/height and weight/age variation in Mexico / Caminhada prvisõões preditivos dinâmicas aleatórias de obesiade e sobrepesoo e obesidade em crianças na Colômbia e variação de peso / estatura e peso / idade noMééxico

La obesidad y el sobrepeso constituyen problemas de salud pública tanto a nivel mundial como en América Latina. La teoría de la probabilidad y la caminata al azar probabilista han sido base para el desarrollo de predicciones de la dinámica de diferentes epidemias. En este trabajo se estudió el crecimiento de la obesidad en cuatro países con base en la caminata al azar, para confirmar la capacidad de la metodología para describir y predecir esta dinámica específica, y se desarrollaron simulaciones de variables asociadas al estudio de sobrepeso y obesidad en Colombia y México, proyectando una predicción al 2015. Se estudiaron tasas de obesidad de Estados Unidos, Finlandia, Australia e Inglaterra desde 1982 a 1996, en analogía con una caminata al azar probabilista, evaluando su capacidad predictiva para el año 1997. Posteriormente se desarrollaron simulaciones de la dinámica de sobrepeso y obesidad en Colombia con base en reportes reales de los años 2005 y 2010 de acuerdo con el índice de masa corporal (IMC), así como simulaciones de la dinámica de peso/talla y peso/edad en la población mexicana de menores de 0 a 5 años, dividida en cuatro regiones, con base en los reportes de 1999 y 2006, proyectándolas hasta el 2015, con base en la caminata al azar. El análisis de la dinámica de crecimiento de la obesidad con base en la caminata al azar, permite predecir cuando los índices van a permanecer estables o cuando van a subir en Estados Unidos, Finlandia, Australia e Inglaterra, logrando predicciones con un porcentaje de efectividad igual o superior al 97,85% para 1997. Las simulaciones obtenidas para México y Colombia predicen un comportamiento probable hasta el 2015, encontrando que en 2015 en Colombia las prevalencias de obesidad para niños de 0 a 9 años oscilarán entre 4,2 y 11,2, y de sobrepeso para niños entre 10 y 17 años entre 12,9 y 19,4. También se encontraron valores predictivos entre 0,1 y 7,7 para el 2015 en México en niños de 0 a 5 años, respecto a la variable de peso/talla, mientras que respecto a peso/ edad se encontraron entre 0,2 y 11,89. Se evidenció que la metodología utilizada es útil para el estudio de diferentes variables asociadas a la dinámica de obesidad y sobrepeso y sirve como base para el desarrollo de predicciones de utilidad en la toma de decisiones de salud pública.

Obesity and overweight are public health problems both globally and in Latin America. The theory of probability and probabilistic random walk have been the basis for developing predictions of the dynamics of different epidemics. In this work, the growth of obesity in four countries is studied based on the random walk, to confirm the ability of the methodology to describe and predict this specific dynamics. Besides, simulations were developed to study variables associated with overweight and obesity in Colombia and Mexico, projecting a possible prediction to 2015. We studied obesity rates in the United States, Finland, Australia and England from 1982 to 1996 in analogy with a probabilistic random walk, assessing its predictive ability for 1997.Subsequently, dynamics simulations of overweight and obesity in Colombia were developed based on actual reports of 2005 and 2010, as well as simulations of the dynamics of weight/age and weight/ height in the Mexican population younger than 0-5 years, divided into four regions, based on the reports of 1999 and 2006. All the simulations were projected to 2015, based on the random walk. The analysis of the dynamics of the obesity rates based on random walk predicts if rates will remain stable or if they will go up in the United States, Finland, Australia and England, making predictions with an effectiveness rate equal to or higher than 97.85% in 1997. The simulations obtained for Mexico and Colombia predict a probable behavior until 2015 both with a regular growth and with the random walk. It was found that in 2015 in Colombia the prevalence of obesity for children aged 0 to 9 years will range between 4.2 and 11.2, and overweight in children between 10 and 17 years will range between 12.9 and 19.4. Predictive values between 0.1 and 7.7 were also found in Mexico for 2015 in children aged 0-5 years relating to the variable weight/height, while regarding weight/age values ranging between 0.2 and 11.89 were found. It was evident that the methodology is useful for the study of different variables associated with overweight and obesity dynamics and serve as a basis for developing predictions useful in making public health decisions.

A obesidade e o sobrepeso constituem problemas de saúde pública tanto a nível mundial quanto na América Latina. A teoria da probabilidade e a caminhada ao acaso probabilista têm sido base para o desenvolvimento de predições da dinâmica de diferentes epidemias. Em este trabalho se estudou o crescimento da obesidade em quatro países com base na caminhada ao acaso para confirmar a capacidade da metodologia para descrever e predizer esta dinâmica específica, e se desenvolveram simulações de variáveis associadas ao estudo de sobrepeso e obesidade na Colômbia e no México, projetando uma predição a 2015. Estudaram-se taxas de obesidade dos Estados Unidos, da Finlândia, da Austrália e da Inglaterra desde 1982 até 1996 em analogia com uma caminhada ao acaso probabilista, avaliando sua capacidade preditiva para o ano 1997. Posteriormente se desenvolveram simulações da dinâmica de sobrepeso e obesidade na Colômbia com base em reportes reais dos anos 2005 e 2010 de acordo ao índice de massa corporal (IMC), assim como simulações da dinâmica de peso/tamanho e peso/idade na população mexicana de menores de 0 a 5 anos, dividida em quatro regiões, com base nos reportes de 1999 e 2006, projetando-as até 2015, com base na caminhada ao acaso. Análise da dinâmica de crescimento da obesidade com base na caminhada ao acaso permite predizer quando os índices vão permanecer estáveis ou quando vão subir Nos Estados Unidos, na Finlândia, na Austrália e na Inglaterra, logrando predições com uma percentagem de efetividade igual ou superior ao 97,85% para 1997. As simulações obtidas para o México e a Colômbia predizem um comportamento provávelaté 2015, encontrando que em 2015 na Colômbia as prevalências de obesidade para crianças de 0 a 9 anos oscilarão entre 4,2 e 11,2, e de sobrepeso para crianças entre 10 e 17 anos entre 12,9 e 19,4. Também se encontraram valores preditivos entre 0,1 e 7,7 para 2015 no México em crianças de 0 a 5 anos, respeito à variável de peso/tamanho, por enquanto com respeito a peso/ idade se encontraram entre 0,2 e 11,89. Evidenciou-se que a metodologia utilizada é útil para o estudo de diferentes variáveis associadas à dinâmica de obesidade e sobrepeso e serve como base para o desenvolvimento de predições de utilidade na toma de decisões de saúde pública.

Previsibilidade e eficiência no mercado agrícola / Predictability and efficiency in agricultural market

O presente trabalho possui como objetivo testar a hipótese de caminho aleatório no mercado da Soja, Algodão, Café e Milho, através da utilização de testes de quociente de variância. São utilizados dados referentes às cotações diárias dos indicadores de preço da ESALQ/CEPEA, correspondentes ao período de 13/03/2006 a 20/10/2010. Os resultados obtidos permitem concluir que todas as commodities rejeitam a hipótese de caminho aleatório, e por consequência a eficiência de mercado, gerando oportunidade de arbitragem.

This research aims to test the random walk hypothesis in Soybean, Cotton, Coffee and Corn markets by using the variance ratio tests. The data used refers to the daily quotations of price indicators, ESALQ/CEPEA for the period from 13/03/2006 to 20/10/2010.Results allowed to conclude that all commodities reject the random walk hypothesis, and hence the efficiency of market, generating arbitrage opportunity.