Establishment and analysis of osteoarthritis diagnosis model based on artificial neural networks / 中国组织工程研究

BACKGROUND:Rapid developments in the field of bioinformatics have provided new methods for the diagnosis of osteoarthritis.Artificial neural networks have powerful data computing and classification capabilities,which have shown better performance in disease diagnosis. OBJECTIVE:To establish a new diagnostic predictive model of osteoarthritis based on artificial neural network and to verify the diagnostic value of the model in osteoarthritis with an external dataset. METHODS:The eligible osteoarthritis-related data sets were downloaded through GEO database search and divided into Train group and Test group.The gene expression matrix of the Train group was analyzed to screen the differentially expressed genes.GO and KEGG enrichment analyses were performed on the differentially expressed genes.Through Lasso regression model,support vector machine model and random forest tree model,the key genes of osteoarthritis were further identified from the differentially expressed genes.The R software"Neuralnet"package was then used to construct the osteoarthritis diagnosis model based on artificial neural network,and the model performance was evaluated by the five-fold cross-validation.Two independent data sets in the Test group were used to verify their diagnostic results. RESULTS AND CONCLUSION:A total of 90 differentially expressed genes related to osteoarthritis were obtained by differential analysis,of which 33 were down-regulated and 57 were up-regulated.GO enrichment analysis showed that the differentially expressed genes were mainly involved in the following biological processes,including leukocyte-mediated immunity,leukocyte migration in bone marrow and chemokine production.KEGG enrichment analysis showed that these genes were mainly enriched in rheumatoid arthritis,interleukin-17 signaling pathway and osteoclast differentiation pathway.Five key genes for the diagnosis of osteoarthritis,HMGB2,GADD45A,SLC19A2,TPPP3 and FOLR2,were identified by three machine learning methods.The artificial neural network model of five key genes in the Train group showed that the accuracy was 96.36%and the area under the curve was 0.997.The five-fold cross validation of the neural network model showed that the average area under the curve was greater than 0.9 and the model was of robustness.Two independent data sets in the Test group showed its area under the curve was 0.814 and 0.788 respectively.Therefore,the establishment of an artificial neural network model for the diagnosis of osteoarthritis has a certain diagnostic value.

Establishment of prognostic model for severe primary graft dysfunction in patients with idiopathic pulmonary fibrosis after lung transplantation / 器官移植

Objective To explore the establishment of a prognostic model based on machine learning algorithm to predict primary graft dysfunction (PGD) in patients with idiopathic pulmonary fibrosis (IPF) after lung transplantation. Methods Clinical data of 226 IPF patients who underwent lung transplantation were retrospectively analyzed. All patients were randomly divided into the training and test sets at a ratio of 7:3. Using regularized logistic regression, random forest, support vector machine and artificial neural network, the prognostic model was established through variable screening, model establishment and model optimization. The performance of this prognostic model was assessed by the area under the receiver operating characteristic curve (AUC), positive predictive value, negative predictive value and accuracy. Results Sixteen key features were selected for model establishment. The AUC of the four prognostic models all exceeded 0.7. DeLong and McNemar tests found no significant difference in the performance among different models (both P>0.05). Conclusions Based on four machine learning algorithms, the prognostic model for grade 3 PGD after lung transplantation is preliminarily established. The overall prediction performance of each model is similar, which may predict the risk of grade 3 PGD in IPF patients after lung transplantation.

Screening of natural drug molecules against Fusarium oxysporum of ginseng root rot based on machine learning / 药学学报

italic>Fusarium oxysporum widely exists in farmland soil and is one of the main pathogenic fungi of root rot, which seriously affects the growth and development of plants and often causes serious losses of cash crops. In order to screen out natural compounds that inhibit the activity of Fusarium oxysporum more economically and efficiently, random forest, support vector machine and artificial neural network based on machine learning algorithms were constructed using the information of known inhibitory compounds in ChEMBL database in this study. And the antibacterial activity of the screened drugs was verified thereafter. The results showed that the prediction accuracy of the three models reached 77.58%, 83.03% and 81.21%, respectively. Based on the inhibition experiment, the best inhibition effect (MIC = 0.312 5 mg·mL-1) of ononin was verified. The virtual screening method proposed in this study provides ideas for the development and creation of new pesticides derived from natural products, and the screened ononin is expected to be a potential lead compound for the development of novel inhibitors of Fusarium oxysporum.

Prediction of concentration immediately dangerous to life or health of benzene and its derivatives based on quantitative structure-activity relationship / 环境与职业医学

Background With the increasing exposure to hazardous chemicals in the workplace and frequency of occupational injuries and occupational safety accidents, the acquisition of occupational exposure limits of hazardous chemicals is imminent. Objective To obtain more unknown immediately dangerous to life or health (IDLH) concentrations of hazardous chemicals in the workplace by exploring the application of quantitative structure-activity relationship (QSAR) prediction method to IDLH concentrations, and to provide a theoretical basis and technical support for the assessment and prevention of occupational injuries. Methods QSAR was used to correlate the IDLH values of 50 benzene and its derivatives with the molecular structures of target compounds. Firstly, affinity propagation algorithm was applied to cluster sample sets. Secondly, Dragon 2.1 software was used to calculate and pre-screen 537 molecular descriptors. Thirdly, the genetic algorithm was used to select six characteristic molecular descriptors as dependent variables and to construct a multiple linear regression model (MLR) and two nonlinear models using support vector machine (SVM) and artificial neural network (ANN) respectively. Finally, model performance was evaluated by internal and external validation and Williams diagram was drawn to determine the scopes of selected models. Results The ANN model results showed that \begin{document}$ {R}_{\mathrm{t}\mathrm{r}\mathrm{a}\mathrm{i}\mathrm{n}}

Identification of Quantized Characterization of Liver Meridian Based on Raman Spectrum of Chinese Medicinal Materials / 世界科学技术-中医药现代化

Objective Based on the comparison and analysis of Raman spectra of liver meridian(including other meridian)and non-liver meridian(other meridian excluding liver meridian)traditional Chinese medicine,the accurate quantitative characterization data of liver meridian was obtained,and the liver meridian identification model was established and analyzed.Methods Taking 120 non-liver meridian(other meridian excluding liver meridian)traditional Chinese medicines(TCMs)as blank control and 120 liver-meridian(including other meridian)TCMs as experimental medicines,Raman spectra of 240 TCMs were obtained after sample pretreatment and Raman spectroscopy detection,and then quantified in units of 1 cm-1.Then combined with Random Forest(Random Forest,RF),Artificial Neural Network(Artificial Neural Network,ANN)and other algorithms,we constructed the identification models of quantized characterization of liver meridian.Results Compared with non-liver meridian(other meridian excluding liver meridian)TCMs,the Raman spectra of the liver meridian TCM were generally lower in the whole detection range,especially in the range of 200-1100 cm-1.The quantized Raman spectrogram data combined with ANN presented the best discrimination results with accuracy,precision>0.871,the receiver operating characteristic curve(ROC)was drawn and the area under ROC curve(AUC)was obtained,with AUC>0.921.Conclusion The Raman spectrogram of TCMs has significant correlation with liver meridian,which can be used as a whole quantized characterization of liver meridian.Combined with ANN,Raman spectrogram can carry out identification analysis efficiently and accurately,which is conducive to solving the bottleneck problem of lacking accurate data on medicinal properties and enriching the scientific connotation of attributing meridians.

Optimization of Escherichia coli shake flask culture medium by artificial neural network / 中国生物制品学杂志

@#Objective To optimize a shake flask culture medium for Escherichia coli(E.coli)with high biomass and viability using artificial neural networks(ANN). Methods Using the proportion of glucose(Glu),yeast extract(YE),yeast peptone(YP),soy peptone(SP)and yeast nitrogen base(YNB)as the mixture component,and the A_(600)(A1)value of cell suspension,wet bacterial weight(G,g/L)of culture and cell viability(A2,A_(460))as the response values,the mixture design was used to screen the mixture components that had a significant effect on the response value. The ANN model was constructed with the test results of mixture design as training and verification data samples. The input variables were mixture components and restricted the upper and lower limits of the mixture components,and the output variables were mixture design response values. The optimized medium formula and reference values were obtained by the constructed ANN. The medium formula was further adjusted by Monte Carlo simulation to obtain the shake flask medium formula of E.coli,which was then verified for 10 times. Results The shake flask culture medium of E.coli was composed of Glu 26 g/L,SP 26 g/L,YNB13 g/L with the total concentration of 65 g/L. The verification results showed that the probability of A1 ≥ 14 was 60%,the probability of G ≥ 77 g/L was 50% and the probability of A2 ≥ 11 was 40%. The mean values of the incubation result data were equivalent to the reference values. Conclusion The shake flask culture medium of E.coli optimized in this study can obtain E.coli with high biomass and bacterial activity.

Application of artificial neural network algorithm in pathological diagnosis and prognosis prediction of digestive tract malignant tumors / 浙江大学学报·医学版

The application of artificial neural network algorithm in pathological diagnosis of gastrointestinal malignant tumors has become a research hotspot. In the previous studies, the algorithm research mainly focused on the model development based on convolutional neural networks, while only a few studies used the combination of convolutional neural networks and recurrent neural networks. The research contents included classical histopathological diagnosis and molecular typing of malignant tumors, and the prediction of patient prognosis by utilizing artificial neural networks. This article reviews the research progress on artificial neural network algorithm in the pathological diagnosis and prognosis prediction of digestive tract malignant tumors.

Outcome prediction for critical care patients with respiratory neoplasms using a multilayer perceptron neural network

ABSTRACT Objective: The variation in mortality rates of intensive care unit oncological patients may imply that clinical characteristics and prognoses are very different between specific subsets of patients with cancer. The specific characteristics of patients with cancer have not been included as risk factors in the established severity-of-illness scoring systems and comorbidity scores, showing limitations in predicting mortality risk. This study aimed to devise a predictive tool for in-hospital mortality for adult patients with a respiratory neoplasm admitted to the intensive care unit, using an artificial neural network. Methods: A total of 1,221 stays in the intensive care unit from the Beth Israel Deaconess Medical Center were studied. The primary endpoint was the all-cause in-hospital mortality prediction. An artificial neural network was developed and compared with six severity-of-illness scores and one comorbidity score. Model building was based on important predictors of lung cancer mortality, such as several laboratory parameters, demographic parameters, organ-supporting treatments, and other clinical information. Discrimination and calibration were assessed. Results: The AUROC for the multilayer perceptron was 0.885, while it was <0.74 for the conventional systems. The AUPRC for the multilayer perceptron was 0.731, whereas it was ≤0.482 for the conventional systems. The superiority of multilayer perceptron was statistically significant for all pairwise AUROC and AUPRC comparisons. The Brier Score was better for the multilayer perceptron (0.109) than for OASIS (0.148), SAPS III (0.163), and SAPS II (0.154). Conclusion: Discrimination was excellent for multilayer perceptron, which may be a valuable tool for assessing critically ill patients with lung cancer.

Aplicación de Redes Neuronales Artificiales para la Clasificación de Actividades de la Vida Diaria en Sujetos con Enfermedad de Párkinson / Classification of Daily Living Activities in subjects with Parkinson's Disease using Artificial Neural Networks

Resumen El presente trabajo es un seguimiento a la propuesta para la contribución con especialistas en la salud para enriquecer los sistemas de seguimiento y apoyo en pacientes con Enfermedad de Párkinson a través de la clasificación de actividades de la vida diaria (AVDs) utilizando Redes Neuronales Artificiales programadas en lenguaje Python. El método propuesto de aprendizaje supervisado permitió la clasificación de 6 AVDs mediante 22 señales procedentes de haber aplicado Análisis de Componentes Principales; conformando la base de datos utilizada para entrenar un Perceptrón Multicapa, logrando un acercamiento a la clasificación con el 93% de medida F1-score. El presente estudio demuestra la versatilidad de las RNA basadas en MLP combinadas con la técnica de PCA, pues incluso en una base de datos desbalanceada como la utilizada permite alcanzar excelentes valores en la medida F1-score. El uso de Inteligencia Artificial y otras herramientas aplicadas en este trabajo pueden eventualmente ayudar a especialistas a desempeñar una evaluación más certera en el monitoreo de la rehabilitación en pacientes con enfermedad de Párkinson mejorando los registros y así evitar subjetividad en la interpretación de los resultados del tratamiento.

Abstract This paper is a proposal to contribute with health specialists to enrich the follow-up and support systems in patients with Parkinson's by identifying and classifying Daily Living Activities (DLAs) using Artificial Neural Networks programmed in Python language. The proposed method of supervised learning allowed the classification of 6 DLAs through 22 signals obtained from the application of Principal Component Analysis, creating a database used to train a Multilayer Perceptron. This model achieved an approximation of classification with 93% of the F1-score. The present study demonstrates the versatility of ANNs based on MLP combined with the PCA technique since, even in an unbalanced database such as the one used, it allows excellent values to be achieved in the F1-score measure. The use of Artificial Intelligence and other tools applied in this work may eventually help specialists to perform a more accurate assessment in the monitoring of rehabilitation for patients with Parkinson's disease by improving records and thus avoiding subjectivity in the interpretation of treatment results.

Progress on application of artificial intelligence technology in orthodontic diagnosis and treatment / 口腔疾病防治

@#In recent years, artificial intelligence technology has developed rapidly and has been gradually applied to the fields of clinical image data processing, auxiliary diagnosis and prognosis evaluation. Research has shown that it can simplify doctors’ clinical tasks, quickly provide analysis and processing results, and has high accuracy. In terms of orthodontic diagnosis and treatment, artificial intelligence can assist in the rapid fixation of two-dimensional and three-dimensional cephalometric measurements. In addition, it is also widely used in the efficient processing and analysis of three-dimensional dental molds data, and shows considerable advantages in determining deciding whether orthodontic treatment needs tooth extraction, thus assisting in judging the stage of growth and development, orthodontic prognosis and aesthetic evaluation. Although the application of artificial intelligence technology is limited by the quantity and quality of training data, combining it with orthodontic clinical diagnosis and treatment can provide faster and more effective analysis and diagnosis and support more accurate diagnosis and treatment decisions. This paper reviews the current application of artificial intelligence technology in orthodontic diagnosis and treatment in the hope that orthodontists can rationally treat and use artificial intelligence technology in the clinic, and make artificial intelligence better serve orthodontic clinical diagnosis and treatment, so as to promote the further development of intelligent orthodontic diagnosis and treatment processes.

Establishing prediction model of community-acquired pneumonia complicated with acute respiratory distress syndrome based on artificial neural network / 中华危重病急救医学

Objective:To investigate the independent risk factors of community-acquired pneumonia (CAP) complicated with acute respiratory distress syndrome (ARDS), and the accuracy and prevention value of ARDS prediction based on artificial neural network model in CAP patients.Methods:A case-control study was conducted. Clinical data of 414 patients with CAP who met the inclusion criteria and were admitted to the comprehensive intensive care unit and respiratory department of Changzhou Second People's Hospital Affiliated to Nanjing Medical University from February 2020 to February 2021 were analyzed. They were divided into two groups according to whether they had complicated with ARDS. The clinical data of the two groups were collected within 24 hours after admission, the influencing factors of ARDS were screened out by univariate analysis, and the artificial neural network model was constructed. Through the artificial neural network model, the importance of input layer independent variables (that was, the influence factors obtained from univariate analysis) on the output layer dependent variables (whether ARDS occurred) was drawn. The artificial neural network modeling data pairs were randomly divided into training group ( n = 290) and verification group ( n = 124) in a ratio of 7∶3. The overall prediction accuracy of the training group and the verification group was calculated respectively. At the same time, the receiver operator characteristic curve (ROC curve) was drawn, and the area under the ROC curve (AUC) was calculated. Results:All 414 patients were enrolled in the analysis, including 82 patients with ARDS and 332 patients without ARDS. Univariate analysis showed that gender, age, heart rate (HR), maximum systolic blood pressure (MSBP), maximum respiratory rate (MRR), source of admission, C-reactive protein (CRP), procalcitonin (PCT), erythrocyte sedimentation rate (ESR), neutrophil count (NEUT), eosinophil count (EOS), fibrinogen equivalent unit (FEU), activated partial thromboplastin time (APTT), total bilirubin (TBil), albumin (ALB), lactate dehydrogenase (LDH), serum creatinine (SCr), hemoglobin (Hb) and blood glucose (GLU) were significantly different between the two groups, which might be the risk factors of CAP patients complicated with ARDS. Taking the above 19 risk factors as the input layer and whether ARDS occurred as the output layer, the artificial neural network model was constructed. Among the input layer independent variables, the top five indicators with the largest influence weight on the neural network model were LDH (100.0%), PCT (74.4%), FEU (61.5%), MRR (56.9%), and APTT (51.6%), indicating that that these five indicators had a greater impact on the occurrence of ARDS in patients with CAP. The overall prediction accuracy of the artificial neural network model in the training group was 94.1% (273/290), and that of the verification group was 89.5% (111/124). The AUC predicted by the aforementioned artificial neural network model for ARDS in CAP patients was 0.977 (95% confidence interval was 0.956-1.000).Conclusion:The prediction model of ARDS in CAP patients based on artificial neural network model has good prediction ability, which can be used to calculate the accuracy of ARDS in CAP patients, and specific preventive measures can be given.

Establishment of artificial neural network model for predicting lymph node metastasis in patients with stage Ⅱ-Ⅲ gastric cancer / 中华胃肠外科杂志

Objective: To establish a neural network model for predicting lymph node metastasis in patients with stage II-III gastric cancer. Methods: Case inclusion criteria: (1) gastric adenocarcinoma diagnosed by pathology as stage II-III (the 8th edition of AJCC staging); (2) no distant metastasis of liver, lung and abdominal cavity in preoperative chest film, abdominal ultrasound and upper abdominal CT; (3) undergoing R0 resection. Case exclusion criteria: (1) receiving preoperative neoadjuvant chemotherapy or radiotherapy; (2) incomplete clinical data; (3) gastric stump cancer.Clinicopathological data of 1231 patients with stage II-III gastric cancer who underwent radical surgery at the Fujian Medical University Union Hospital from January 2010 to August 2014 were retrospectively analyzed. A total of 1035 patients with lymph node metastasis were confirmed after operation, and 196 patients had no lymph node metastasis. According to the postoperative pathologic staging. 416 patients (33.8%) were stage Ⅱ and 815 patients (66.2%) were stage III. Patients were randomly divided into training group (861/1231, 69.9%) and validation group (370/1231, 30.1%) to establish an artificial neural network model (N+-ANN) for the prediction of lymph node metastasis. Firstly, the Logistic univariate analysis method was used to retrospectively analyze the case samples of the training group, screen the variables affecting lymph node metastasis, determine the variable items of the input point of the artificial neural network, and then the multi-layer perceptron (MLP) to train N+-ANN. The input layer of N+-ANN was composed of the variables screened by Logistic univariate analysis. Artificial intelligence analyzed the status of lymph node metastasis according to the input data and compared it with the real value. The accuracy of the model was evaluated by drawing the receiver operating characteristic (ROC) curve and obtaining the area under the curve (AUC). The ability of N+-ANN was evaluated by sensitivity, specificity, positive predictive values, negative predictive values, and AUC values. Results: There were no significant differences in baseline data between the training group and validation group (all P>0.05). Univariate analysis of the training group showed that preoperative platelet to lymphocyte ratio (PLR), preoperative systemic immune inflammation index (SII), tumor size, clinical N (cN) stage were closely related to postoperative lymph node metastasis. The N+-ANN was constructed based on the above variables as the input layer variables. In the training group, the accuracy of N+-ANN for predicting postoperative lymph node metastasis was 88.4% (761/861), the sensitivity was 98.9% (717/725), the specificity was 32.4% (44/136), the positive predictive value was 88.6% (717/809), the negative predictive value was 84.6% (44/52), and the AUC value was 0.748 (95%CI: 0.717-0.776). In the validation group, N+-ANN had a prediction accuracy of 88.4% (327/370) with a sensitivity of 99.7% (309/310), specificity of 30.0% (18/60), positive predictive value of 88.0% (309/351), negative predictive value of 94.7% (18/19), and an AUC of 0.717 (95%CI:0.668-0.763). According to the individualized lymph node metastasis probability output by N+-ANN, the cut-off values of 0-50%, >50%-75%, >75%-90% and >90%-100% were applied and patients were divided into N0 group, N1 group, N2 group and N3 group. The overall prediction accuracy of N+-ANN for pN staging in the training group and the validation group was 53.7% and 54.1% respectively, while the overall prediction accuracy of cN staging for pN staging in the training group and the validation group was 30.1% and 33.2% respectively, indicating that N+-ANN had a better prediction than cN stage. Conclusions: The N+-ANN constructed in this study can accurately predict postoperative lymph node metastasis in patients with stage Ⅱ-Ⅲ gastric cancer. The N+-ANN based on individualized lymph node metastasis probability has better accurate prediction for pN staging as compared to cN staging.

Application of artificial neural network in evaluation of IVF embryo / 中华检验医学杂志

Artificial neural network (ANN) is a network framework that drives artificial intelligence (AI). Classical convolutional neural networks (CNN) are mainly used for cell count and image recognition at fixed time in embryo evaluation. Fully connected deep neural networks (DNN), with increased accuracy of image recognition, are suitable for the units equipped with high configuration hardware and need comprehensive prediction according to the integrated clinical information. Residual networks improve the accuracy by increasing layers and solving the gradient disappearance problem through jump connection to realize dynamic embryo assessment. Bayesian networks (BN) and multi-layer perceptron (MLP) are two machine learning methods. The former is especially used for comprehensive prediction combined with complex clinical information in case of lack of conditions. The latter has gradient disappearance and explosion problem, and is easy to lose some spatial features of images, so it is used for small sample volumes. ANN has advantages in the prediction of implantation rate and aneuploidy and reducing invasive detection in quality assessment of embryos, which is an important research direction of human-assisted reproductive technology (ART).

Research advance and challenges of the application of machine learning in laboratory medicine / 中华检验医学杂志

The application of machine learning has become an important direction for the development of intelligent laboratory medicine. Recently, the rapid development of open-source software and publicly available data sources made the application of machine learning highly accessible. It reduced the requirement for developers to have necessary matter knowledge and also facilitated a surge in interest and publications. However, the practicality and reproducibility of machine learning models still remain unclear. In the face of these challenges, some countermeasures were proposed, including strict control of data quality, improvemrnt of model applicability, establishment of model selction and validation strategies, enhancement of model interpretability and reproducibility. Machine learning helps to break through the bottleneck of clinical translation of laboratory big data and improve the quality of diagnostic services in the laboratory medicine.

Application of artificial neural network model in bioequivalence study of candesartan cilexetil tablets / 中国临床药理学与治疗学

AIM: To evaluate the bioequivalence of two candesartan cilexetil tablet formulations in healthy Chinese subjects after administration of a single dose, and an artificial neural network model was established to predict the candesartan plasma concentration, and provide a basis for clinical rational use of drugs. METHODS: Thirty-two healthy Chinese subjects were enrolled for oral administration of a single 8 mg dose of candesartan cilexetil tablet (test or reference product) under fasting or fed conditions to conduct a bioequivalence study. The bioequivalence results were used to build a back-propagation artificial neural network model by MATLAB software, and the model was internally and externally verified to predict the plasma concentration. RESULTS: Under both fasting and fed conditions, the C

Changes of cognitive domain function and risk factors of cognitive dysfunction in patients with mild acute cerebral infarction / 中风与神经疾病杂志

@#Objective　To investigate the changes of cognitive domain function and risk factors of cognitive dysfunction (CI) in patients with mild acute cerebral infarction.Methods　A total of 195 patients with mild acute cerebral infarction in our hospital were selected as the infarction group,and 50 healthy subjects were selected as the control group.The cognitive domains scores of different infarct sites were compared between the two groups.According to the Montreal Cognitive Assessment Scale (MoCA) score,the infarction group was divided into CI group (150 cases) and non-CI group (45 cases),and the general data of the two groups were compared.Multifactorial analysis of risk factors affecting CI in patients with mild acute cerebral infarction.The Receiver Operating Characteristic (ROC) and calibration curve were used to evaluate the discrimination and accuracy of the artificial neural network model.Results　Compared with the control group,the cognitive function of infarct group decreased (P<0.05).CI rate of mild acute cerebral infarction was 76.92% (150/195).Multivariate Logistic analysis showed that female,diabetes mellitus,hypertension and HSS-SP≤55 were independent risk factors for CI in patients with mild acute cerebral infarction,while high education level was a protective factor (P<0.05).ROC curve and calibration curve show that the model has good discrimination and accuracy.Conclusion　Clinical attention should be paid to menopausal women,patients HBS-SP score and other risk factors to prevent and slow down the occurrence of CI.

Cómo clasificar llanto del recién nacido mediante una red neuronal supervisada / How to classify newborn cry through a supervised neural network

El llanto es una vía de comunicación del recién nacido con el medio circundante. Investigaciones acerca del llanto infantil han correlacionado características acústicas de éste con patologías, demostrándose que el llanto puede reflejar la integridad neurofisiológica del niño y dar una medida de su interacción con el ambiente y su desarrollo cognitivo y social. Esta contribución muestra cómo clasificar el llanto de neonatos con hipoxia y de un grupo de control, en normal o patológico, a través de una red neuronal artificial supervisada. Para implementar la red neuronal se aprovechan las posibilidades de la plataforma MATLAB®. El diseño y estructuración de la red considera algoritmo de aprendizaje o entrenamiento, iteraciones, pruebas e intervalos de clasificación, obteniéndose arquitectura y topología, y funcionalidades de la red neuronal que en la generalización proporciona la mejor clasificación. En el trabajo se aplica el método de selección de casos, el método acústico para extraer parámetros cuantitativos de la señal de llanto en tiempo, intensidad y frecuencia, así como métodos vinculados con el diseño, implementación y validación, con pruebas diagnósticas, de la red neuronal artificial obtenida para cumplir el objetivo del trabajo que es la generación de clases (clasificación del llanto). Con precisión del resultado de clasificación del 90 por ciento se está en condición de concebir una solución informática (agregando interfaz para interactuar con base de datos) para ayudar complementariamente al diagnóstico médico no invasivo usando el llanto del neonato provocado ante dolor(AU)

Cry from newborn (0-28 days) is a way of communication for the interaction with surrounding world. Infant cry researches provide information that correlate among cries acoustic features with pathologies. It has been demonstrated that the infant cry is able to reflect child neurophysiology integrity and give meaning from newborn interaction with environment, also cognitive and social development from child. This contribution shows how to classify the cry of neonates with hypoxia and of a control group, into normal or pathological, through a supervised artificial neural network. Network implementation makes use of MATLAB® platform possibilities. Design and structuring of network take into consideration aspects as training algorithm, iterations, tests and classification intervals. All these referred aspects give as result an architectural, topology and functionalities from neural network able to classify cry in generalization stage offering good outcome. Different methods are applied in this paper as selection of cases, acoustic methods in order to obtain quantitative parameters from cry signals (in time, intensity and frequency domain). Methods related with design, implementation and validation (diagnostic test) of an artificial neural network able to carry out the goal of this paper (classification of cry) are used. With accuracy results in cry classification about 90 percent, authors get ready conditions for an informatic solution (with addition of interface for data base interaction) for help as a non-invasive complement to medical diagnosis using cry from neonate induced by pain(AU)

Wavelet packet transform and multilayer perceptron to identify voices with a mild degree of vocal deviation / Transformada Wavelet packet y Perceptrón Multicapa para identificación de voces con grado leve de desvío vocal

Introduction. Laryngeal disorders are characterized by a change in the vibratory pattern of the vocal folds. This disorder may have an organic origin described by anatomical fold modification, or a functional origin caused by vocal abuse or misuse. The most common diagnostic methods are performed by invasive imaging features that cause patient discomfort. In addition, mild voice deviations do not stop the in-dividual from using their voices, which makes it difficult to identify the problem and increases the possibility of complications. Aim. For those reasons, the goal of the present paper was to develop a noninvasive alternative for the identification of voices with a mild degree of vocal deviation ap-plying the Wavelet Packet Transform (WPT) and Multilayer Perceptron (MLP), an Artificial Neural Network (ANN). Methods. A dataset of 74 audio files were used. Shannon energy and entropy mea-sures were extracted using the Daubechies 2 and Symlet 2 families and then the processing step was performed with the MLP ANN. Results. The Symlet 2 family was more efficient in its generalization, obtaining 99.75% and 99.56% accuracy by using Shannon energy and entropy measures, re-spectively. The Daubechies 2 family, however, obtained lower accuracy rates: 91.17% and 70.01%, respectively. Conclusion. The combination of WPT and MLP presented high accuracy for the identification of voices with a mild degree of vocal deviation

ntroducción. Los trastornos laríngeos se caracterizan por un cambio en el patrón vibratorio de los pliegues vocales. Este trastorno puede tener un origen orgánico, descrito como la modificación anatómica de los pliegues vocales, o de origen fun-cional, provocado por abuso o mal uso de la voz. Los métodos de diagnóstico más comunes se realizan mediante procedimientos invasivos que causan malestar al pa-ciente. Además, los desvíos vocales de grado leve no impiden que el individuo utilice la voz, lo que dificulta la identificación del problema y aumenta la posibilidad de complicaciones futuras.Objetivo. Por esas razones, el objetivo de esta investigación es desarrollar una he-rramienta alternativa, no invasiva para la identificación de voces con grado leve de desvío vocal aplicando Transformada Wavelet Packet (WPT) y la red neuronal artifi-cial del tipo Perceptrón Mutlicapa (PMC). Métodos. Fue utilizado un banco de datos con 78 voces. Fueron extraídas las me-didas de energía y entropía de Shannon usando las familias Daubechies 2 y Symlet 2 para después aplicar la red neuronal PMC. Resultados. La familia Symlet 2 fue más eficiente en su generalización, obteniendo un 99.75% y un 99.56% de precisión mediante el uso de medidas de energía y en-tropía de Shannon, respectivamente. La familia Daubechies 2, sin embargo, obtuvo menores índices de precisión: 91.17% y 70.01%, respectivamente. Conclusión. La combinación de WPT y PMC presentó alta precisión para la iden-tificación de voces con grado leve de desvío vocal

An anesthesia depth computing method study based on wavelet transform and artificial neural network / 生物医学工程学杂志

General anesthesia is an essential part of surgery to ensure the safety of patients. Electroencephalogram (EEG) has been widely used in anesthesia depth monitoring for abundant information and the ability of reflecting the brain activity. The paper proposes a method which combines wavelet transform and artificial neural network (ANN) to assess the depth of anesthesia. Discrete wavelet transform was used to decompose the EEG signal, and the approximation coefficients and detail coefficients were used to calculate the 9 characteristic parameters. Kruskal-Wallis statistical test was made to these characteristic parameters, and the test showed that the parameters were statistically significant for the differences of the four levels of anesthesia: awake, light anesthesia, moderate anesthesia and deep anesthesia (

Application of Data Mining Technology in Risk Prediction Model for Lung Cancer / 肿瘤防治研究

Objective To establish a lung cancer risk prediction model using data mining technology and compare the performance of decision tree C5.0 and artificial neural networks in the application of risk prediction model, and to explore the value of data mining techniques in lung cancer risk prediction. Methods We collected the data of 180 patients with lung cancer and 240 patients with benign lung lesion which contained 17 variables of risk factors and clinical symptoms. Decision tree C5.0 and artificial neural networks models were established to compare the prediction performance. Results There were 420 valid samples collected in total and proportioned with the ratio of 7:3 for the training set and testing set. The accuracy, sensitivity, specificity, Youden index, positive predictive value, negative predictive value and AUC of artificial neural networks model were 65.3%, 61.7%, 73.3%, 0.350, 54.9%, 73.1% and 0.675 (95%CI: 0.628-0.720) in testing set; those of decision tree C5.0 model were 61.0%, 47.8%, 80.4%, 0.282, 35.3%, 80.6% and 0.641 (95%CI: 0.593-0.687) in testing set. Conclusion The artificial neural networks model is superior to the decision tree C5.0 model at overall performance and it has potential application value in the risk prediction of lung cancer.