Decision trees based on automatic learning and their use in cardiology

Real-Time and Offline Evaluation of Myoelectric Pattern Recognition for the Decoding of Hand Movements

Pattern recognition algorithms have been widely used to map surface electromyographic signals to target movements as a source for prosthetic control. However, most investigations have been conducted offline by performing the analysis on pre-recorded datasets. While real-time data analysis (i.e., classification when new data becomes available, with limits on latency under 200-300 milliseconds) plays an important role in the control of prosthetics, less knowledge has been gained with respect to real-time performance. Recent literature has underscored the differences between offline classification accuracy, the most common performance metric, and the usability of upper limb prostheses. Therefore, a comparative offline and real-time performance analysis between common algorithms had yet to be performed. In this study, we investigated the offline and real-time performance of nine different classification algorithms, decoding ten individual hand and wrist movements. Surface myoelectric signals were recorded from fifteen able-bodied subjects while performing the ten movements. The offline decoding demonstrated that linear discriminant analysis (LDA) and maximum likelihood estimation (MLE) significantly (p < 0.05) outperformed other classifiers, with an average classification accuracy of above 97%. On the other hand, the real-time investigation revealed that, in addition to the LDA and MLE, multilayer perceptron also outperformed the other algorithms and achieved a classification accuracy and completion rate of above 68% and 69%, respectively.

Supporting Real World Decision Making in Coronary Diseases Using Machine Learning

Cardiovascular diseases are one of the leading global causes of death. Following the positive experiences with machine learning in medicine we performed a study in which we assessed how machine learning can support decision making regarding coronary artery diseases. While a plethora of studies reported high accuracy rates of machine learning algorithms (MLA) in medical applications, the majority of the studies used the cleansed medical data bases without the presence of the “real world noise.” Contrary, the aim of our study was to perform machine learning on the routinely collected Anonymous Cardiovascular Database (ACD), extracted directly from a hospital information system of the University Medical Centre Maribor). Many studies used tens of different machine learning approaches with substantially varying results regarding accuracy (ACU), hence they were not usable as a base to validate the results of our study. Thus, we decided, that our study will be performed in the 2 phases. During the first phase we trained the different MLAs on a comparable University of California Irvine UCI Heart Disease Dataset. The aim of this phase was first to define the “standard” ACU values and second to reduce the set of all MLAs to the most appropriate candidates to be used on the ACD, during the second phase. Seven MLAs were selected and the standard ACUs for the 2-class diagnosis were 0.85. Surprisingly, the same MLAs achieved the ACUs around 0.96 on the ACD. A general comparison of both databases revealed that different machine learning algorithms performance differ significantly. The accuracy on the ACD reached the highest levels using decision trees and neural networks while Liner regression and AdaBoost performed best in UCI database. This might indicate that decision trees based algorithms and neural networks are better in coping with real world not “noise free” clinical data and could successfully support decision making concerned with coronary diseasesmachine learning.

A model for acute kidney injury in severe burn patients

INTRODUCTION

In patients with severe burns, morbidity and mortality are high. One factor related to poor prognosis is acute kidney injury. According to the AKIN criteria, acute kidney injury has 3 stages based on urine output, serum creatinine level, and renal replacement therapy. In this study, we aimed to create a decision tree for estimating risk of acute kidney injury in patients with severe burn injuries.

METHODS

We retrospectively evaluated 437 adult patients with ≥20% total burn surface area injury who were treated at the Baskent University Ankara and Konya Burn Centers from January 2000 to March 2020. Patients who had high-voltage burn and previous history of kidney disease were excluded. Patient demographics, medical history, mechanism of injury, presence of inhalation injury, depth of burn, laboratory values, presence of oliguria, need for renal replacement therapy, central venous pressure, and prognosis were evaluated. These data were used in a "decision tree method" to create the Baskent University model to estimate risk of acute kidney injury in severe burn patients.

RESULTS

Our model provided an accuracy of 71.09% for risk estimation. Of 172 patients, 78 (45%) had different degrees of acute kidney injury, with 26 of these (15.1%) receiving renal replacement therapy. Our model showed that total burn surface area was the most important factor for estimation of acute kidney injury occurrence. Other important factors included serum creatinine value, burn injury severity score, hemoglobin value, neutrophil-to-lymphocyte ratio, and platelet count.

CONCLUSION

The Baskent University model for acute kidney injury may be helpful to determine risk of acute kidney injury in burn patients. This determination would allow appropriate treatment to be given to high-risk patients in the early period, reducing the incidence of acute kidney injury.

Evaluation of surface EMG-based recognition algorithms for decoding hand movements

Myoelectric pattern recognition (MPR) to decode limb movements is an important advancement regarding the control of powered prostheses. However, this technology is not yet in wide clinical use. Improvements in MPR could potentially increase the functionality of powered prostheses. To this purpose, offline accuracy and processing time were measured over 44 features using six classifiers with the aim of determining new configurations of features and classifiers to improve the accuracy and response time of prosthetics control. An efficient feature set (FS: waveform length, correlation coefficient, Hjorth Parameters) was found to improve the motion recognition accuracy. Using the proposed FS significantly increased the performance of linear discriminant analysis, K-nearest neighbor, maximum likelihood estimation (MLE), and support vector machine by 5.5%, 5.7%, 6.3%, and 6.2%, respectively, when compared with the Hudgins’ set. Using the FS with MLE provided the largest improvement in offline accuracy over the Hudgins feature set, with minimal effect on the processing time. Among the 44 features tested, logarithmic root mean square and normalized logarithmic energy yielded the highest recognition rates (above 95%). We anticipate that this work will contribute to the development of more accurate surface EMG-based motor decoding systems for the control prosthetic hands.

Global sensitivity analysis techniques for probabilistic ground water modeling

Global sensitivity analysis techniques are better suited for analyzing input-output relationships over the full range of parameter variations and model outcomes, as opposed to local sensitivity analysis carried out around a reference point. This article describes three such techniques: (1) stepwise rank regression analysis for building input-output models to identify key contributors to output variance, (2) mutual information (entropy) analysis for determining the strength of nonmonotonic patterns of input-output association, and (3) classification tree analysis for determining what variables or combinations are responsible for driving model output into extreme categories. These techniques are best applied in conjunction with Monte Carlo simulation-based probabilistic analyses. Two examples are presented to demonstrate the applicability of these methods. The usefulness of global sensitivity techniques is examined vis-a-vis local sensitivity analysis methods, and recommendations are provided for their applications in ground water modeling practice.

Medical diagnostic process optimization through the semantic integration of data resources

In this paper we study the optimization of medical diagnostic process from the data access point of view. According to many studies which showed that optimized diagnostic process can considerably improve efficiency in health care industry, we present a new approach to data integration within a diagnostic process. It is our belief that a unified access to data resources throughout the whole diagnostic process considerably improves the efficiency of the process itself. When combining the optimized data access with an existing algorithmic optimization method an optimized process can be achieved that takes into account the quality of a diagnosis, the individual needs of each patient, the associated costs, and the utilization of personnel/equipment. To enable an efficient management of data, we developed a semantic web based system for the integration of data resources within a medical diagnostic process. Then we combined the unified data access with our existing diagnostic process optimization framework that uses machine learning techniques and evolutionary algorithms. The new defined diagnostic process framework is finally used in a case-study for optimizing the diagnosing of the mitral valve prolapse syndrome in a regional hospital department.

A combined Fuzzy Cognitive Map and decision trees model for medical decision making

Fuzzy Cognitive Maps (FCMs) are an efficient modeling method providing flexibility on the simulated system's design. They consist of nodes-concepts and weighted edges that connect the nodes and represent the cause and effect relationships among them. The performance of FCMs is dependent on the initial weight setting and architecture. This shortcoming can be alleviated and the FCM model can be enhanced if a fuzzy rule base (IF-THEN rules) is available. This research proposes a successful attempt to combine fuzzy cognitive maps with decision tree generators. A combined Decision Tree-Fuzzy Cognitive Map (DT-FCM) model is proposed when different types of input data are available and the behavior of this model is studied. In this research work, we introduce a new hybrid modeling methodology for decision making tasks and we implement the proposed methodology at a medical problem.

Finding the right decision tree's induction strategy for a hard real world problem

Decision trees have been already successfully used in medicine, but as in traditional statistics, some hard real world problems can not be solved successfully using the traditional way of induction. In our experiments we tested various methods for building univariate decision trees in order to find the best induction strategy. On a hard real world problem of the Orthopaedic fracture data with 2637 cases, described by 23 attributes and a decision with three possible values, we built decision trees with four classical approaches, one hybrid approach where we combined neural networks and decision trees, and with an evolutionary approach. The results show that all approaches had problems with either accuracy, sensitivity, or decision tree size. The comparison shows that the best compromise in hard real world problem decision trees building is the evolutionary approach.

Towards more optimal medical diagnosing with evolutionary algorithms

Efficiency in hospital performance is becoming more and more important. Studies showed that diagnosis can considerably reduce the inefficiency, so one of the most important tasks in achieving greater hospital efficiency is to optimize the diagnostic process. For the best of the patient the diagnostic process has to be optimized regarding the number of the examinations and individualized in order to maximize accuracy, sensitivity and specificity. In addition the duration of the diagnostic process has to be minimized and the process has to be performed on the most reliable equipment. The main contribution of our paper is the introduction of the integrated computerized environment DIAPRO enabling the diagnostic process optimization. The DIAPRO is based on a single approach--evolutionary algorithms.

AI planning and scheduling in the medical hospital environment

Hospital management is a hard task due to the complexity of the organization, the costly infrastructure, the specialized services offered to different patients and the need for prompt reaction to emergencies. Artificial Intelligence planning and scheduling methods can offer substantial support to the management of hospitals, and help raising the standards of service. This editorial presents an overview of the achievements reported in therapy planning and hospital management together with a general roadmap of the published research in Artificial Intelligence planning and scheduling. Finally, a discussion for the future research and development in this area concludes the presentation.

The art of building decision trees

Decision support systems that help physicians are becoming a very important part of medical decision making. They are based on different models and the best of them are providing an explanation together with an accurate, reliable, and quick response. One of the most viable among models are decision trees, already successfully used for many medical decision-making purposes. Although effective and reliable, the traditional decision tree construction approach still contains several deficiencies. Therefore we decided to develop and compare several decision support models using four different approaches. We took statistical analysis, a MtDeciT, in our laboratory developed tool for building decision trees with a classical method, the well-known C5.0 tool and a self-adapting evolutionary decision support model that uses evolutionary principles for the induction of decision trees. Several solutions were evolved for the classification of metabolic and respiratory acidosis (MRA). A comparison between developed models and obtained results has shown that our approach can be considered as a good choice for different kinds of real-world medical decision making.