Case-based reasoning support for liver disease diagnosis

Diversity in Machine Learning: A Systematic Review of Text-Based Diagnostic Applications

OBJECTIVE

 As the storage of clinical data has transitioned into electronic formats, medical informatics has become increasingly relevant in providing diagnostic aid. The purpose of this review is to evaluate machine learning models that use text data for diagnosis and to assess the diversity of the included study populations.

METHODS

 We conducted a systematic literature review on three public databases. Two authors reviewed every abstract for inclusion. Articles were included if they used or developed machine learning algorithms to aid in diagnosis. Articles focusing on imaging informatics were excluded.

RESULTS

 From 2,260 identified papers, we included 78. Of the machine learning models used, neural networks were relied upon most frequently (44.9%). Studies had a median population of 661.5 patients, and diseases and disorders of 10 different body systems were studied. Of the 35.9% (N = 28) of papers that included race data, 57.1% (N = 16) of study populations were majority White, 14.3% were majority Asian, and 7.1% were majority Black. In 75% (N = 21) of papers, White was the largest racial group represented. Of the papers included, 43.6% (N = 34) included the sex ratio of the patient population.

DISCUSSION

 With the power to build robust algorithms supported by massive quantities of clinical data, machine learning is shaping the future of diagnostics. Limitations of the underlying data create potential biases, especially if patient demographics are unknown or not included in the training.

CONCLUSION

 As the movement toward clinical reliance on machine learning accelerates, both recording demographic information and using diverse training sets should be emphasized. Extrapolating algorithms to demographics beyond the original study population leaves large gaps for potential biases.

Using Case-Based Reasoning in a Learning System: A Prototype of a Pedagogical Nurse Tool for Evidence-Based Diabetic Foot Ulcer Care

BACKGROUND

Currently, evidence-based learning systems to increase knowledge and evidence level of wound care are unavailable to wound care nurses in Denmark, which means that they need to learn about diabetic foot ulcers from experience and peer-to-peer training, or by asking experienced colleagues. Interactive evidence-based learning systems built on case-based reasoning (CBR) have the potential to increase wound care nurses' diabetic foot ulcer knowledge and evidence levels.

METHOD

A prototype of a CBR-interactive, evidence-based algorithm-operated learning system calculates a dissimilarity score (DS) that gives a quantitative measure of similarity between a new case and cases stored in a case base in relation to six variables: necrosis, wound size, granulation, fibrin, dry skin, and age. Based on the DS, cases are selected by matching the six variables with the best predictive power and by weighing the impact of each variable according to its contribution to the prediction. The cases are ranked, and the six cases with the lowest DS are visualized in the system.

RESULTS

Conventional education, that is, evidence-based learning material such as books and lectures, may be less motivating and pedagogical than peer-to-peer training, which is, however, often less evidence-based. The CBR interactive learning systems presented in this study may bridge the two approaches. Showing wound care nurses how individual variables affect outcomes may help them achieve greater insights into pathophysiological processes.

CONCLUSION

A prototype of a CBR-interactive, evidence-based learning system that is centered on diabetic foot ulcers and related treatments bridges the gap between traditional evidence-based learning and more motivating and interactive learning approaches.

Artificial intelligence in disease diagnosis: a systematic literature review, synthesizing framework and future research agenda

Artificial intelligence can assist providers in a variety of patient care and intelligent health systems. Artificial intelligence techniques ranging from machine learning to deep learning are prevalent in healthcare for disease diagnosis, drug discovery, and patient risk identification. Numerous medical data sources are required to perfectly diagnose diseases using artificial intelligence techniques, such as ultrasound, magnetic resonance imaging, mammography, genomics, computed tomography scan, etc. Furthermore, artificial intelligence primarily enhanced the infirmary experience and sped up preparing patients to continue their rehabilitation at home. This article covers the comprehensive survey based on artificial intelligence techniques to diagnose numerous diseases such as Alzheimer, cancer, diabetes, chronic heart disease, tuberculosis, stroke and cerebrovascular, hypertension, skin, and liver disease. We conducted an extensive survey including the used medical imaging dataset and their feature extraction and classification process for predictions. Preferred reporting items for systematic reviews and Meta-Analysis guidelines are used to select the articles published up to October 2020 on the Web of Science, Scopus, Google Scholar, PubMed, Excerpta Medical Database, and Psychology Information for early prediction of distinct kinds of diseases using artificial intelligence-based techniques. Based on the study of different articles on disease diagnosis, the results are also compared using various quality parameters such as prediction rate, accuracy, sensitivity, specificity, the area under curve precision, recall, and F1-score.

Leveraging electronic health record data to inform hospital resource management : A systematic data mining approach

Early identification of resource needs is instrumental in promoting efficient hospital resource management. Hospital information systems, and electronic health records (EHR) in particular, collect valuable demographic and clinical patient data from the moment patients are admitted, which can help predict expected resource needs in early stages of patient episodes. To this end, this article proposes a data mining methodology to systematically obtain predictions for relevant managerial variables by leveraging structured EHR data. Specifically, these managerial variables are: i) Diagnosis categories, ii) procedure codes, iii) diagnosis-related groups (DRGs), iv) outlier episodes and v) length of stay (LOS). The proposed methodology approaches the problem in four stages: Feature set construction, feature selection, prediction model development, and model performance evaluation. We tested this approach with an EHR dataset of 5,089 inpatient episodes and compared different classification and regression models (for categorical and continuous variables, respectively), performed temporal analysis of model performance, analyzed the impact of training set homogeneity on performance and assessed the contribution of different EHR data elements for model predictive power. Overall, our results indicate that inpatient EHR data can effectively be leveraged to inform resource management on multiple perspectives. Logistic regression (combined with minimal redundancy maximum relevance feature selection) and bagged decision trees yielded best results for predicting categorical and numerical managerial variables, respectively. Furthermore, our temporal analysis indicated that, while DRG classes are more difficult to predict, several diagnosis categories, procedure codes and LOS amongst shorter-stay patients can be predicted with higher confidence in early stages of patient stay. Lastly, value of information analysis indicated that diagnoses, medication and structured assessment forms were the most valuable EHR data elements in predicting managerial variables of interest through a data mining approach.

Comparison of Diagnosis Accuracy between a Backpropagation Artificial Neural Network Model and Linear Regression in Digestive Disease Patients: an Empirical Research

Introduction

A Noninvasive diagnosis model for digestive diseases is the vital issue for the current clinical research. Our systematic review is aimed at demonstrating diagnosis accuracy between the BP-ANN algorithm and linear regression in digestive disease patients, including their activation function and data structure.

Methods

We reported the systematic review according to the PRISMA guidelines. We searched related articles from seven electronic scholarly databases for comparison of the diagnosis accuracy focusing on BP-ANN and linear regression. The characteristics, patient number, input/output marker, diagnosis accuracy, and results/conclusions related to comparison were extracted independently based on inclusion criteria.

Results

Nine articles met all the criteria and were enrolled in our review. Of those enrolled articles, the publishing year ranged from 1991 to 2017. The sample size ranged from 42 to 3222 digestive disease patients, and all of the patients showed comparable biomarkers between the BP-ANN algorithm and linear regression. According to our study, 8 literature demonstrated that the BP-ANN model is superior to linear regression in predicting the disease outcome based on AUROC results. One literature reported linear regression to be superior to BP-ANN for the early diagnosis of colorectal cancer.

Conclusion

The BP-ANN algorithm and linear regression both had high capacity in fitting the diagnostic model and BP-ANN displayed more prediction accuracy for the noninvasive diagnosis model of digestive diseases. We compared the activation functions and data structure between BP-ANN and linear regression for fitting the diagnosis model, and the data suggested that BP-ANN was a comprehensive recommendation algorithm.

Combining visual analytics and case-based reasoning for rupture risk assessment of intracranial aneurysms

Purpose

Medical case-based reasoning solves problems by applying experience gained from the outcome of previous treatments of the same kind. Particularly for complex treatment decisions, for example, incidentally found intracranial aneurysms (IAs), it can support the medical expert. IAs bear the risk of rupture and may lead to subarachnoidal hemorrhages. Treatment needs to be considered carefully, since it may entail unnecessary complications for IAs with low rupture risk. With a rupture risk prediction based on previous cases, the treatment decision can be supported.

Methods

We present an interactive visual exploration tool for the case-based reasoning of IAs. In presence of a new aneurysm of interest, our application provides visual analytics techniques to identify the most similar cases with respect to morphology. The clinical expert can obtain the treatment, including the treatment outcome, for these cases and transfer it to the aneurysm of interest. Our application comprises a heatmap visualization, an adapted scatterplot matrix and fully or partially directed graphs with a circle- or force-directed layout to guide the interactive selection process. To fit the demands of clinical applications, we further integrated an interactive identification of outlier cases as well as an interactive attribute selection for the similarity calculation. A questionnaire evaluation with six trained physicians was used.

Result

Our application allows for case-based reasoning of IAs based on a reference data set. Three classifiers summarize the rupture state of the most similar cases. Medical experts positively evaluated the application.

Conclusion

Our case-based reasoning application combined with visual analytic techniques allows for representation of similar IAs to support the clinician. The graphical representation was rated very useful and provides visual information of the similarity of the k most similar cases.

A database for using machine learning and data mining techniques for coronary artery disease diagnosis

We present the coronary artery disease (CAD) database, a comprehensive resource, comprising 126 papers and 68 datasets relevant to CAD diagnosis, extracted from the scientific literature from 1992 and 2018. These data were collected to help advance research on CAD-related machine learning and data mining algorithms, and hopefully to ultimately advance clinical diagnosis and early treatment. To aid users, we have also built a web application that presents the database through various reports.

An intelligent case-based knowledge management system for quality improvement in nursing homes

Purpose

This paper aims to maintain the high service quality of the long-term care service providers by establishing a knowledge-based system so as to enhance the service quality of nursing homes and the performance of its nursing staff continually.

Design/methodology/approach

An intelligent case-based knowledge management system (ICKMS) is developed with the integration of two artificial intelligence techniques, i.e. fuzzy logic and case-based reasoning (CBR). In the system, fuzzy logic is adopted to assess the performance through the analysis of the long-term care services provided, nurse performance and elderly satisfaction, whereas CBR is used to formulate a customized re-training program for quality improvement. A case study is conducted to validate the feasibility of the proposed system.

Findings

The empirical findings indicate that the ICKMS helps in identification of those nursing staff who cannot meet the essential service standard. Through the customized re-training program, the performance of the nursing staff can be greatly enhanced, whereas the medical errors and complaints can be considerably reduced. Furthermore, the proposed methodology provides a cost-saving approach in the administrative work.

Practical implications

The findings and results of the study facilitate decision-making using the ICKMS for the long-term service providers to improve their performance and service quality by providing a customized re-training program to the nursing staff.

Originality/value

This study contributes to establishing a knowledge-based system for the long-term service providers for maintaining the high service quality in the health-care industry.

A New Intelligent Medical Decision Support System Based on Enhanced Hierarchical Clustering and Random Decision Forest for the Classification of Alcoholic Liver Damage, Primary Hepatoma, Liver Cirrhosis, and Cholelithiasis

Diagnosis of liver disease principally depends on physician's subjective knowledge. Automatic prediction of the disease is a critical real-world medical problem. This work presents an EHC-ERF-based intelligence-integrated model purposive to predict different types of liver disease including alcoholic liver damage, primary hepatoma, liver cirrhosis, and cholelithiasis. These diseases cause many clinical complications, and their accurate assessment is the only way for providing efficient treatment facilities to patients. EHC is deployed to divide the data into a hierarchy structure that is more informative for the disease predictions carried out by ERF. The occurrence of ERF error rate was dependent on correlation and strength of each individual tree where correlation is directly proportional to forest error rate and strength is inversely proportional to the forest rate. In total, two individual and three integrated classification models are developed to achieve enhanced predictions for the liver disease types. Analysis of results showed that the proposed framework achieved better outcomes in terms of accuracy, true positive rate, precision, F-measure, kappa statistic, mean absolute error, and root mean squared error. Furthermore, it achieved the highest accuracy rates when compared with the state-of-the-art techniques. Results also indicated that the weighted distance function employed in EHC has improved the efficiency of proposed system and has shown the capability to be used by physicians for diagnostic advice.

Application of Machine Learning Algorithms to a Well Defined Clinical Problem: Liver Disease

Liver diseases represent a major health burden worldwide. Machine learning (ML) algorithms have been extensively used to diagnose liver disease. This study accordingly aims to employ various individual and integrated ML algorithms on distinct liver disease datasets for evaluating the diagnostic performances, to integrate dimensionality reduction method with the ML algorithms for analyzing variation in results, to find the best classification model and to analyze the merits and demerits of these algorithms. KNN and PCA-KNN emerged to be the top individual and integrated models. The study also concluded that one specific algorithm can't show best results for all types of datasets and integrated models not always perform better than the individuals. It is observed that no algorithm is perfect and performance of an algorithm totally depends on the dataset type and structure, its number of observations, its dimensions and the decision boundary.

A case-based reasoning system based on weighted heterogeneous value distance metric for breast cancer diagnosis

OBJECTIVE

We present the implementation and application of a case-based reasoning (CBR) system for breast cancer related diagnoses. By retrieving similar cases in a breast cancer decision support system, oncologists can obtain powerful information or knowledge, complementing their own experiential knowledge, in their medical decision making.

METHODS

We observed two problems in applying standard CBR to this context: the abundance of different types of attributes and the difficulty in eliciting appropriate attribute weights from human experts. We therefore used a distance measure named weighted heterogeneous value distance metric, which can better deal with both continuous and discrete attributes simultaneously than the standard Euclidean distance, and a genetic algorithm for learning the attribute weights involved in this distance measure automatically. We evaluated our CBR system in two case studies, related to benign/malignant tumor prediction and secondary cancer prediction, respectively.

RESULT

Weighted heterogeneous value distance metric with genetic algorithm for weight learning outperformed several alternative attribute matching methods and several classification methods by at least 3.4%, reaching 0.938, 0.883, 0.933, and 0.984 in the first case study, and 0.927, 0.842, 0.939, and 0.989 in the second case study, in terms of accuracy, sensitivity×specificity, F measure, and area under the receiver operating characteristic curve, respectively.

CONCLUSION

The evaluation result indicates the potential of CBR in the breast cancer diagnosis domain.

Role of Soft Computing Approaches in HealthCare Domain: A Mini Review

In the present era, soft computing approaches play a vital role in solving the different kinds of problems and provide promising solutions. Due to popularity of soft computing approaches, these approaches have also been applied in healthcare data for effectively diagnosing the diseases and obtaining better results in comparison to traditional approaches. Soft computing approaches have the ability to adapt itself according to problem domain. Another aspect is a good balance between exploration and exploitation processes. These aspects make soft computing approaches more powerful, reliable and efficient. The above mentioned characteristics make the soft computing approaches more suitable and competent for health care data. The first objective of this review paper is to identify the various soft computing approaches which are used for diagnosing and predicting the diseases. Second objective is to identify various diseases for which these approaches are applied. Third objective is to categories the soft computing approaches for clinical support system. In literature, it is found that large number of soft computing approaches have been applied for effectively diagnosing and predicting the diseases from healthcare data. Some of these are particle swarm optimization, genetic algorithm, artificial neural network, support vector machine etc. A detailed discussion on these approaches are presented in literature section. This work summarizes various soft computing approaches used in healthcare domain in last one decade. These approaches are categorized in five different categories based on the methodology, these are classification model based system, expert system, fuzzy and neuro fuzzy system, rule based system and case based system. Lot of techniques are discussed in above mentioned categories and all discussed techniques are summarized in the form of tables also. This work also focuses on accuracy rate of soft computing technique and tabular information is provided for each category including author details, technique, disease and utility/accuracy.

Designing and Implementation of Fuzzy Case-based Reasoning System on Android Platform Using Electronic Discharge Summary of Patients with Chronic Kidney Diseases

Introduction:

Case-based reasoning (CBR) systems are one of the effective methods to find the nearest solution to the current problems. These systems are used in various spheres as well as industry, business, and economy. The medical field is not an exception in this regard, and these systems are nowadays used in the various aspects of diagnosis and treatment.

Methodology:

In this study, the effective parameters were first extracted from the structured discharge summary prepared for patients with chronic kidney diseases based on data mining method. Then, through holding a meeting with experts in nephrology and using data mining methods, the weights of the parameters were extracted. Finally, fuzzy system has been employed in order to compare the similarities of current case and previous cases, and the system was implemented on the Android platform.

Discussion:

The data on electronic discharge records of patients with chronic kidney diseases were entered into the system. The measure of similarity was assessed using the algorithm provided in the system, and then compared with other known methods in CBR systems.

Conclusion:

Developing Clinical fuzzy CBR system used in Knowledge management framework for registering specific therapeutic methods, Knowledge sharing environment for experts in a specific domain and Powerful tools at the point of care.

A retrieval strategy for case-based reasoning using similarity and association knowledge

Retrieval is a key phase in case-based reasoning (CBR), since it lays the foundation for the overall effectiveness of CBR systems. Its aim is to retrieve useful cases that can be used to solve the target problem. To perform the retrieval process, CBR systems typically exploit similarity knowledge and is called similarity-based retrieval (SBR). However, SBR tends to rely strongly on similarity knowledge, ignoring other forms of knowledge that can be further leveraged to improve the retrieval performance. This paper argues and motivates that association analysis of stored cases can significantly strengthen SBR. We propose a novel retrieval strategy USIMSCAR that substantially outperforms SBR by leveraging association knowledge, encoded via a certain form of association rules, in conjunction with similarity knowledge. We also propose a novel approach for extracting association knowledge from a given case base using various association rule mining techniques. We evaluate the significance of USIMSCAR in three application domains-medical diagnosis, IT service management, and product recommendation.

Improving case-based reasoning systems by combining k-nearest neighbour algorithm with logistic regression in the prediction of patients' registration on the renal transplant waiting list

Introduction

Case-based reasoning (CBR) is an emerging decision making paradigm in medical research where new cases are solved relying on previously solved similar cases. Usually, a database of solved cases is provided, and every case is described through a set of attributes (inputs) and a label (output). Extracting useful information from this database can help the CBR system providing more reliable results on the yet to be solved cases.

Objective

We suggest a general framework where a CBR system, viz. K-Nearest Neighbour (K-NN) algorithm, is combined with various information obtained from a Logistic Regression (LR) model, in order to improve prediction of access to the transplant waiting list.

Methods

LR is applied, on the case database, to assign weights to the attributes as well as the solved cases. Thus, five possible decision making systems based on K-NN and/or LR were identified: a standalone K-NN, a standalone LR and three soft K-NN algorithms that rely on the weights based on the results of the LR. The evaluation was performed under two conditions, either using predictive factors known to be related to registration, or using a combination of factors related and not related to registration.

Results and Conclusion

The results show that our suggested approach, where the K-NN algorithm relies on both weighted attributes and cases, can efficiently deal with non relevant attributes, whereas the four other approaches suffer from this kind of noisy setups. The robustness of this approach suggests interesting perspectives for medical problem solving tools using CBR methodology.

Early prediction of the highest workload in incremental cardiopulmonary tests

Incremental tests are widely used in cardiopulmonary exercise testing, both in the clinical domain and in sport sciences. The highest workload (denoted W peak ) reached in the test is key information for assessing the individual body response to the test and for analyzing possible cardiac failures and planning rehabilitation, and training sessions. Being physically very demanding, incremental tests can significantly increase the body stress on monitored individuals and may cause cardiopulmonary overload. This article presents a new approach to cardiopulmonary testing that addresses these drawbacks. During the test, our approach analyzes the individual body response to the exercise and predicts the W peak value that will be reached in the test and an evaluation of its accuracy. When the accuracy of the prediction becomes satisfactory, the test can be prematurely stopped, thus avoiding its entire execution. To predict W peak , we introduce a new index, the CardioPulmonary Efficiency Index (CPE), summarizing the cardiopulmonary response of the individual to the test. Our approach analyzes the CPE trend during the test, together with the characteristics of the individual, and predicts W peak . A K-nearest-neighbor-based classifier and an ANN-based classier are exploited for the prediction. The experimental evaluation showed that the W peak value can be predicted with a limited error from the first steps of the test.