Disease Diagnosis Model Research Articles

A divide-and-conquer method for sparse risk prediction and evaluation.

Divide-and-conquer (DAC) is a commonly used strategy to overcome the challenges of extraordinarily large data, by first breaking the dataset into series of data blocks, then combining results from individual data blocks to obtain a final estimation. Various DAC algorithms have been proposed to fit a sparse predictive regression model in the $L_1$ regularization setting. However, many existing DAC algorithms remain computationally intensive when sample size and number of candidate predictors are both large. In addition, no existing DAC procedures provide inference for quantifying the accuracy of risk prediction models. In this article, we propose a screening and one-step linearization infused DAC (SOLID) algorithm to fit sparse logistic regression to massive datasets, by integrating the DAC strategy with a screening step and sequences of linearization. This enables us to maximize the likelihood with only selected covariates and perform penalized estimation via a fast approximation to the likelihood. To assess the accuracy of a predictive regression model, we develop a modified cross-validation (MCV) that utilizes the side products of the SOLID, substantially reducing the computational burden. Compared with existing DAC methods, the MCV procedure is the first to make inference on accuracy. Extensive simulation studies suggest that the proposed SOLID and MCV procedures substantially outperform the existing methods with respect to computational speed and achieve similar statistical efficiency as the full sample-based estimator. We also demonstrate that the proposed inference procedure provides valid interval estimators. We apply the proposed SOLID procedure to develop and validate a classification model for disease diagnosis using narrative clinical notes based on electronic medical record data from Partners HealthCare.

Development and validation of two artificial intelligence models for diagnosing benign, pigmented facial skin lesions.

This study used deep learning for diagnosing common, benign hyperpigmentation. In this study, two convolutional neural networks were used to identify six pigmentary diseases, and a disease diagnosis model was established. Because the distribution of lesions in the original training picture is very complex, we cropped the image around the lesions, trained the network on the extracted lesion images, and fused the verification results of the overall picture and the extracted picture to assess the model performance in identifying hyperpigmented dermatitis pictures. Finally, we evaluated the image recognition performance of the two convolutional neural networks and the converged networks in the test set through a comparison of the converged network and the physicians' assessments. The AUC of DenseNet-96 for the overall picture was 0.98, whereas the AUC of ResNet-152 was 0.96; therefore, we concluded that DenseNet-96 performed better than ResNet-152. From the AUC, the converged network has the best performance. The converged network model achieved a comprehensive classification performance comparable to that of the doctors. The diagnostic model for benign, pigmented skin lesions based on convolutional neural networks had a slightly higher overall performance than the skin specialists.

Diagnosing Parkinson Disease Through Facial Expression Recognition: Video Analysis.

BackgroundThe number of patients with neurological diseases is currently increasing annually, which presents tremendous challenges for both patients and doctors. With the advent of advanced information technology, digital medical care is gradually changing the medical ecology. Numerous people are exploring new ways to receive a consultation, track their diseases, and receive rehabilitation training in more convenient and efficient ways. In this paper, we explore the use of facial expression recognition via artificial intelligence to diagnose a typical neurological system disease, Parkinson disease (PD).ObjectiveThis study proposes methods to diagnose PD through facial expression recognition.MethodsWe collected videos of facial expressions of people with PD and matched controls. We used relative coordinates and positional jitter to extract facial expression features (facial expression amplitude and shaking of small facial muscle groups) from the key points returned by Face++. Algorithms from traditional machine learning and advanced deep learning were utilized to diagnose PD.ResultsThe experimental results showed our models can achieve outstanding facial expression recognition ability for PD diagnosis. Applying a long short-term model neural network to the positions of the key features, precision and F1 values of 86% and 75%, respectively, can be reached. Further, utilizing a support vector machine algorithm for the facial expression amplitude features and shaking of the small facial muscle groups, an F1 value of 99% can be achieved.ConclusionsThis study contributes to the digital diagnosis of PD based on facial expression recognition. The disease diagnosis model was validated through our experiment. The results can help doctors understand the real-time dynamics of the disease and even conduct remote diagnosis.

RETRACTED ARTICLE: An optimal artificial neural network based big data application for heart disease diagnosis and classification model

At present days, world is facing several issues like irregular distribution of medicinal resources, new chronic diseases, and the raising operating cost. The way of combining recent technologies into the medical system will helps to significantly resolve the problems. This study introduces a big health application system based on optimal artificial neural network (OANN) for heart disease diagnosis, which is considered as a deadliest disease in all over the globe. The proposed OANN includes a set of two main processes namely, distance based misclassified instance removal (DBMIR) and teaching and learning based optimization (TLBO) algorithm for ANN, called (TLBO-ANN). The proposed model is developed using a Big Data framework like Apache Spark. The presented OANN model operates on two phases, namely offline prediction and online prediction. During the offline prediction stage, the benchmark heart disease dataset will be used to train a model and performs testing. Similarly, at the online prediction stage, the real time data will be streamed into Apache Spark model and the filtered data will be diagnosed by the use of trained model to obtain the prediction results. The performance of the presented OANN model has been tested using a benchmark heart disease dataset from UCI repository. A comprehensive experimental result analysis clearly verified the better outcome of the OANN model over the compared methods. The proposed method is found to be an effective tool to analyze big data based heart disease prediction model to satisfy the need of increasing number of heart patients.

Optimal Deep Learning based Classification Model for Mitral Valve Diagnosis System

In present days, the domain of mitral valve (MV) diagnosis so common due to the changing lifestyle in day to day life. The increased number of MV disease necessitates the development of automated disease diagnosis model based on segmentation and classification. This paper makes use of deep learning (DL) model to develop a MV classification model to diagnose the severity level. For the accurate classification of ML, this paper applies the DL model called convolution neural network (CNN-MV) model. And, an edge detection based segmentation model is also applied which will helps to further enhance the performance of the classifier. Due to the non-availability of MV dataset, we have collected a MV dataset of our own from a total of 211 instances. A set of three validation parameters namely accuracy, sensitivity and specificity are applied to indicate the effective operation of the CNN-MV model. The obtained simulation outcome pointed out that the presented CNN-MV model functions as an appropriate tool for MV diagnosis.

Based On K-means Disease Diagnosis Research

For the diagnosis of diseases, modern medicine usually searches for diseases in the disease database to find the type of disease that matches them. The diagnosis of diseases is the first step in treatment. Then the classification of diseases is the basis of disease diagnosis. Disease classification plays an extremely important role in the scientific management of medical records and the development of modern medicine, and is a bridge connecting modern medical science. Therefore, the classification of diseases is very necessary. Based on this, this article establishes a K-means model for disease diagnosis, and combines the internationally unified disease type code ICD statistics table to classify the sample data set into infectious and parasitic diseases, tumors, diabetes and circulatory diseases The training is perfect, and finally the diagnosis classification of the disease is realized.

GAN-based synthetic brain PET image generation

In recent days, deep learning technologies have achieved tremendous success in computer vision-related tasks with the help of large-scale annotated dataset. Obtaining such dataset for medical image analysis is very challenging. Working with the limited dataset and small amount of annotated samples makes it difficult to develop a robust automated disease diagnosis model. We propose a novel approach to generate synthetic medical images using generative adversarial networks (GANs). Our proposed model can create brain PET images for three different stages of Alzheimer’s disease—normal control (NC), mild cognitive impairment (MCI), and Alzheimer’s disease (AD).

IDDSAM: An Integrated Disease Diagnosis and Severity Assessment Model for Intensive Care Units

People are admitted to intensive care units (ICUs) because they need complete support for failing organ systems, constant monitoring, routine nursing care, and treatment. A critical or intensive illness is different from conventional or chronic diseases that most people are likely to have previously encountered. Such an illness is often unexpected and without warnings and can suddenly strike the previously fit. High levels of treatment and support are generally required to prevent life-threatening complications for the patents. Two of the most noticeable actions during an ICU stay are disease diagnosis and severity assessment of the patients. Unlike the majority of previous approaches where diagnosis and severity assessment are studied separately, we treat these actions as two tasks in an integrated procedure that clinicians must be able to quickly and accurately conduct such that patients are given the best possible chance for therapeutic success. In this paper, we propose an integrated disease diagnosis and severity assessment model (IDDSAM) to diagnose and assess diseases. Moreover, accompanying the prediction, we also provide an evidence-based explanation. IDDSAM is a multisource multitask model that is based on an attention mechanism and utilizes shareable information from laboratory tests, bedside monitoring, and complications to support patients' severity assessment and in-hospital disease diagnoses. We use 50,430 ICU cases consisting of 46,520 patients from 50 kinds of diseases over nine classifications to evaluate our proposed model. The experimental results demonstrated that our model outperforms the existing state-of-the-art mortality and diagnosis prediction framework by 3.79% on average in terms of accuracy for the mortality prediction tasks and by 14.51% on average for the diagnosis tasks.

Diagnosis Method of Thyroid Disease Combining Knowledge Graph and Deep Learning

The scale of medical data is growing rapidly, and these data come from different data sources. The amount of data is huge, the production speed is fast, and the format is different. Case data is very important because it contains a lot of medical knowledge about diseases, drugs, treatments, etc. It can provide important support for the development of smart medicine. Knowledge graph is a graph-based data structure, which can well represent the relationship between these medical data in reality and form a semantic network. This research uses knowledge graph technology to connect trivial and scattered knowledge in various medical information systems to assist in disease diagnosis. This research takes thyroid disease as an example, constructs a medical knowledge graph and applies it to intelligent medical diagnosis. First, extract the relationships between biomedical entities to construct a biomedical knowledge graph. Then, the entities and relationships in the knowledge graph are transformed into low-dimensional continuous vectors through the knowledge graph embedding method. Finally, the known pathological disease relationship data is used to train the disease diagnosis model of the bidirectional long short-term memory network (BSTLM). Experiments show that the thyroid disease diagnosis method that combines knowledge graphs and deep learning has a better diagnostic effect. This shows that smart medical care based on the knowledge graph will provide a solution path for alleviating the shortage of domestic high-quality medical resources.

Chronic Kidney Disease Diagnosis Model Based on Case Based Reasoning

Provision of health care services is still a major challenge for developing countries. To mention some of the challenges: Lack of highly qualified medical human resources, financial as well as the ability of manage and transform scare resources to meet healthcare needs. In particular, In Ethiopia health care management related to the kidney disorder suffers from the following challenges: lack of highly qualified medical human resources, financial as well as the ability to manage and transform scarce resources to meet healthcare needs.On the one hand, Artificial Intelligence (AI) helps the medical sciences. Hence, in this paper we proposed a framework for CBR system to facilitate and support the diagnosis of chronic kidney diseases with domain expert’s advice. Interview and techniques have been employed on this study to acquire the necessary information required to develop intended CBR system. Finally, we evaluate the performance of the developed framework using recall and precision.

An intelligent data-driven model for disease diagnosis based on machine learning theory

In the era of data, major decisions are determined by massive data, especially in the healthcare industry. In this paper, an intelligent data-driven model is proposed based on machine learning theory, specifically, support vector machine (SVM) and random forest (RF). The model is then applied to a case of disease diagnosis, cough variant asthma (CVA). The data of 137 samples with 12 attributes is collected for experiments. The results show that the proposed model achieves better prediction performance than single SVM and single RF. Besides, in order to identify the key medical indicators to enhance diagnosis accuracy and efficiency, the most important factors affecting CVA are generated by the proposed model, including FENO, EOS%, MMEF75/25, FEV1/FVC, PEF, etc. Meanwhile, it is demonstrated that the proposed model could be a user-friendly tool to improve the performance of disease diagnosis.

The Italian INTERCEPTOR Project: From the Early Identification of Patients Eligible for Prescription of Antidementia Drugs to a Nationwide Organizational Model for Early Alzheimer's Disease Diagnosis.

Alzheimer's disease is the most common age-related neurodegenerative disorder and its burden on patients, families, and society grows significantly with lifespan. Early modifications of risk-enhancing lifestyles and treatment initiation expand personal autonomy and reduce management costs. Many clinical trials with potentially disease-modifying drugs are devoted to mild cognitive impairment (MCI) prodromal-to-Alzheimer's disease. The identification of biomarkers for early diagnosis may thus be crucial for early intervention and identification of high-risk subjects, the most appropriate target of new drugs as soon as they will be discovered. INTERCEPTOR is a strategic project by the Italian Ministry of Health and the Italian Medicines Agency (AIFA), aiming to validate the best combination (highly accurate, non-invasive, available on the whole national territory and financially sustainable) of biomarkers and organizational model for early diagnosis. 500 MCI subjects will be enrolled at baseline and followed-up for 3 years for at least 400 of them in order to define a "hub & spoke" nationwide model with recruiting (spokes) centers for MCI identification and expert (hubs) centers for risk diagnosis.

Small sample-based disease diagnosis model acquisition in medical human-centered computing

With the development of wireless communications and networks, HCC (human-centred computing) has attracted considerable attention in recent years throughout the medical field. HCC can provide an effective integration of various medical auxiliary diagnosis models using machine learning algorithms. In medical HCC, deep learning has demonstrated its powerful ability in the field of computer vision. However, image processing based on deep learning usually requires a large amount of labeled data, which requires significant resources since it needs to be completed by doctors, and it is difficult to collect a large amount of data for some rare diseases. Therefore, how to use the deep learning method to obtain an effective auxiliary diagnosis model based on a small sample or zero sample data set has become an important issue in the study of medical auxiliary diagnosis. We proposes an auxiliary diagnosis model acquisition method based on a variational auto-encoder and zero sample augmentation technology, and the incremental update training program based on wireless communications and networks is designed to obtain the auxiliary diagnosis model to solve the difficulty of collecting a large amount of valid data. The experimental results show that the model obtained by the above method based on a small sample or zero sample data set can effectively diagnose the types of skin diseases, which helps doctors make better judgments.

Artificial Intelligence based Android App for Medical Consultation

This paper proposes an Artificial Intelligence (AI) based mobile health application model for E-consultation and disease diagnosis. An android application, named ‘consult-AI, predicting diseases based on symptoms and associated health issues is designed and developed in this work. The proposed system consists of the user interface and web services, symptoms-disease database, disease-drugs database, disease prediction engine, and prescription engine. The user interface is implemented using android/java programming, and the disease diagnosis part is designed with the help of symptoms-disease database, AI-assisted prediction engines, and web services. The prescription engine works with the disease-drugs database and outputs from the disease prediction engine to deliver the e-prescription recommendation to doctors according to the severity of the condition. The patients can quickly identify the disease by just inputting their issues, and the software generates awareness on the state through which he/she may be passing at that time. The system suggests some first aid activities to save their lives and facilitates a remote consultation with a specialist available in the session. The proposed system proves very helpful in urgent cases where the patient needs immediate attention before reaching the hospital or in instances where there are no doctors available in the area.

A medical monitoring scheme and health‐medical service composition model in cloud‐based IoT platform

AbstractAdvanced technologies such as internet of things (IoT) and clouds have significantly influenced on modern medical monitoring systems. Analytical statistics derived from massive patients' medical data via different data analysis methods, contribute in remote medical monitoring, early diagnosis of diseases, predicting clinical events, and recommending vital health/medical instructions. According to existence of the same health/medical services in functional aspect, finding appropriate composite health/medical services by the patients has been remained as a major concern in modern medical systems. Regarding this challenge, in this paper, a medical monitoring scheme for cloud‐based IoT platform is proposed, in which the patients' medical conditions are derived through predicting diseases by mining her physiological data collected from IoT devices and other medical records. A disease diagnosis model is used to analyze the patients' medical data for the aim of offering a composite health/medical prescription. After confirming the outcomes by medical team, it is sent to the patient. Then, the patient indicates her nonfunctional requirements such as location, cost and time to find the most appropriate composite health/medical service based on her preferences. Experimental results reveal that the proposed scheme is successful in achieving effective diseases diagnosis for offering composite health/medical prescriptions.

Age Is Important for the Early-Stage Detection of Breast Cancer on Both Transcriptomic and Methylomic Biomarkers.

Patients at different ages have different rates of cell development and metabolisms. As a result, age should be an essential part of how a disease diagnosis model is trained and optimized. Unfortunately, most of the existing studies have not taken age into account. This study demonstrated that disease diagnosis models could be improved by merely applying individual models for patients of different age groups. Both transcriptomes and methylomes of the TCGA breast cancer dataset (TCGA-BRCA) were utilized for the analysis procedure of feature selection and classification. Our experimental data strongly suggested that disease diagnosis modeling should integrate patient age into the whole experimental design.

Glaucoma diagnosis based on both hidden features and domain knowledge through deep learning models

Glaucoma is one of the leading causes of blindness in the world and there is no cure for it yet. But it is very meaningful to detect it early as earlier detection makes it possible to stop further loss of visions. Although deep learning models have proved their advantages in natural image analysis, they usually rely on large datasets to learn to extract hidden features, thus limiting its application in medical areas where data is hard to get. Consequently, it is meaningful and challenging to design a deep learning model for disease diagnosis with relatively fewer data. In this paper, we study how to use deep learning model to combine domain knowledge with retinal fundus images for automatic glaucoma diagnosis. The domain knowledge includes measures important for glaucoma diagnosis and important region of the image which contains much information. To make full use of this domain knowledge and extract hidden features from image simultaneously, we design a multi-branch neural network (MB-NN) model with methods to automatically extract important areas of images and obtain domain knowledge features. We evaluate the effectiveness of the proposed model on real datasets and achieve an accuracy of 0.9151, sensitivity of 0.9233, and specificity of 0.9090, which is better than the state-of-the-art models.

A machine learning model for improving healthcare services on cloud computing environment

Recently, cloud computing gained an important role in healthcare services (HCS) due to its ability to improve the HCS performance. However, the optimal selection of virtual machines (VMs) to process a medical request represents a big challenge. Optimal selection of VMs performs a significant enhancement of the performance through reducing the execution time of medical requests (tasks) coming from stakeholders (patients, doctors, etc.) and maximizing utilization of cloud resources. For that, this paper proposes a new model for HCS based on cloud environment using Parallel Particle Swarm Optimization (PPSO) to optimize the VMs selection. In addition, a new model for chronic kidney disease (CKD) diagnosis and prediction is proposed to measure the performance of our VMs model. The prediction model of CKD is implemented using two consecutive techniques, which are linear regression (LR) and neural network (NN). LR is used to determine critical factors that influence on CKD. NN is used to predict of CKD. The results show that, the proposed model outperforms the state-of-the art models in total execution time the rate of 50%. In addition, the system efficiency regarding real-time data retrieval is greatly improved by 5.2%. In addition, the accuracy of hybrid intelligent model in predicting of CKD is 97.8%. The proposed model is superior to most of the referred models in the related works by 64%.

A FAST CORRELATION FILTER BASED GRADIENT BOOSTING CLASSIFIER FOR DISEASE DIAGNOSIS

Disease diagnosis is the process to find the disease with specified details of a person's symptoms. Diagnosing the Disease is time consuming due to the need to analyze relevant microorganisms. Due to large growth in world’s population, Classification model receives a great deal in any domain of research and also a consistent tool for medical disease diagnosis. The domain of classification approach is used in the disease diagnosis, disease prediction, bio informatics and so on. However, an effective disease diagnosis model and the accuracy with the disease prediction were compromised. In order to obtain higher classification accuracy for heart and stroke disease diagnosis, a Fast Correlation Filter based Gradient Boosting Classifier (FCF GBC) technique is introduced. The main objective of the FCF-GBC technique is effectively performs disease diagnosis with two processing steps. Initially, Fast Correlation Filtering (FCF) algorithm is used to select the most relevant attributes (i.e. features) for disease diagnosis and filter out the irrelevant attributes in dataset. FCF uses symmetrical uncertainty to calculate the dependences of attributes and discovers the relevant attributes. After that, A Gradient Boosting Classifier is used for classifying and predicting the heart and stroke disease from the extracted attributes. Experimental evaluation is carried out using Statlog heart disease dataset and International Stroke Trial Database on the factors such as classification accuracy, classification time, error rate and true positive rate with respect to number of patients.

Daehr

Electronic health records (EHR) provide a rich source of temporal data that present a unique opportunity to characterize disease patterns and risk of imminent disease. While many data-mining tools have been adopted for EHR-based disease early detection, linear discriminant analysis (LDA) is one of the most commonly used statistical methods. However, it is difficult to train an accurate LDA model for early disease diagnosis when too few patients are known to have the target disease. Furthermore, EHR data are heterogeneous with significant noise. In such cases, the covariance matrices used in LDA are usually singular and estimated with a large variance. This article presents Daehr , an extension of the LDA framework using electronic health record data to address these issues. Beyond existing LDA analyzers, we propose Daehr to (1) eliminate the data noise caused by the manual encoding of EHR data and (2) lower the variance of parameter (covariance matrices) estimation for LDA models when only a few patients’ EHR are available for training. To achieve these two goals, we designed an iterative algorithm to improve the covariance matrix estimation with embedded data-noise/parameter-variance reduction for LDA. We evaluated Daehr extensively using the College Health Surveillance Network, a large, real-world EHR dataset. Specifically, our experiments compared the performance of LDA to three baselines (i.e., LDA and its derivatives) in identifying college students at high risk for mental health disorders from 23 U.S. universities. Experimental results demonstrate Daehr significantly outperforms the three baselines by achieving 1.4%--19.4% higher accuracy and a 7.5%--43.5% higher F1-score.