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

Artificial Intelligence-Based Prediction of Contrast Medium Doses for Computed Tomography Angiography Using Optimized Clinical Parameter Sets

OBJECTIVES

 In this paper, an artificial intelligence-based algorithm for predicting the optimal contrast medium dose for computed tomography (CT) angiography of the aorta is presented and evaluated in a clinical study. The prediction of the contrast dose reduction is modelled as a classification problem using the image contrast as the main feature.

METHODS

 This classification is performed by random decision forests (RDF) and k-nearest-neighbor methods (KNN). For the selection of optimal parameter subsets all possible combinations of the 22 clinical parameters (age, blood pressure, etc.) are considered using the classification accuracy and precision of the KNN classifier and RDF as quality criteria. Subsequently, the results of the evaluation were optimized by means of feature transformation using regression neural networks (RNN). These were used for a direct classification based on regressed Hounsfield units as well as preprocessing for a subsequent KNN classification.

RESULTS

 For feature selection, an RDF model achieved the highest accuracy of 84.42% and a KNN model achieved the best precision of 86.21%. The most important parameters include age, height, and hemoglobin. The feature transformation using an RNN considerably exceeded these values with an accuracy of 90.00% and a precision of 97.62% using all 22 parameters as input. However, also the feasibility of the parameter sets in routine clinical practice has to be considered, because some of the 22 parameters are not measured in routine clinical practice and additional measurement time of 15 to 20 minutes per patient is needed. Using the standard feature set available in clinical routine the best accuracy of 86.67% and precision of 93.18% was achieved by the RNN.

CONCLUSION

 We developed a reliable hybrid system that helps radiologists determine the optimal contrast dose for CT angiography based on patient-specific parameters.

Alpha-Synuclein, cyclooxygenase-2 and prostaglandins-EP2 receptors as neuroinflammatory biomarkers of autism spectrum disorders: Use of combined ROC curves to increase their diagnostic values

BACKGROUND

Autism spectrum disorder (ASD) is a neurodevelopmental disorder characterized by impairments in social interaction and restricted and repetitive behaviors. Neuroinflammation and abnormal lipid mediators have been identified in multiple investigations as an acknowledged etiological mechanism of ASD that can be targeted for therapeutic intervention.

METHODS

In this study, multiple regression and combined receiver operating characteristic (ROC) curve analyses were used to determine the relationship between the neuroinflammatory marker α-synuclein and lipid mediator markers related to inflammation induction, such as cyclooxygenase-2 and prostaglandin-EP2 receptors, in the etiology of ASD. Additionally, the study aimed to determine the linear combination that maximizes the partial area under ROC curves for a set of markers. Forty children with ASD and 40 age- and sex-matched controls were enrolled in the study. Using ELISA, the levels of α-synuclein, cyclo-oxygenase-2, and prostaglandin-EP2 receptors were measured in the plasma of both groups. Statistical analyses using ROC curves and multiple and logistic regression models were performed.

RESULTS

A remarkable increase in the area under the curve was observed using combined ROC curve analyses. Moreover, higher specificity and sensitivity of the combined markers were reported.

CONCLUSIONS

The present study indicates that measurement of the predictive value of selected biomarkers related to neuroinflammation and lipid metabolism in children with ASD using a ROC curve analysis should lead to a better understanding of the etiological mechanism of ASD and its link with metabolism. This information may facilitate early diagnosis and intervention.

A Personalized Medical Decision Support System Based on Explainable Machine Learning Algorithms and ECC Features: Data from the Real World

Artificial intelligence can help physicians improve the accuracy of breast cancer diagnosis. However, the effectiveness of AI applications is limited by doctors’ adoption of the results recommended by the personalized medical decision support system. Our primary purpose is to study the impact of external case characteristics (ECC) on the effectiveness of the personalized medical decision support system for breast cancer assisted diagnosis (PMDSS-BCAD) in making accurate recommendations. Therefore, we designed a novel comprehensive framework for case-based reasoning (CBR) that takes the impact of external features of cases into account, made use of the naive Bayes and k-nearest neighbor (KNN) algorithms (CBR-ECC), and developed a PMDSS-BCAD system by using the CBR-ECC model and external features as system components. Under the new case-based reasoning framework, the accuracy of the combined model of naive Bayes and KNN with an optimal K value of 2 is 99.40%. Moreover, in a real hospital scenario, users rated the PMDSS-BCAD system, which takes into account the external characteristics of the case, better than the original personalized system. These results suggest that PMDSS-BCD can not only provide doctors with more personalized and accurate results for auxiliary diagnosis, but also improve doctors’ trust in the results, so as to encourage doctors to adopt the results recommended by the personalized system.

Predictive value of selected biomarkers related to metabolism and oxidative stress in children with autism spectrum disorder

Autism spectrum disorder (ASD) as a neurodevelopmental disorder is characterized by impairments in social interaction, communication, and restricted, repetitive behavior. Several and reproducible studies have suggested that oxidative stress may represent one of the primary etiological mechanism of ASD that can be targeted for therapeutic intervention. In the present study, multiple regression and combined receiver operating characteristic (ROC) analysis were used to search for a relationship between impaired energy and oxidative metabolic pathways in the etiology of ASD and to find the linear combination that maximizes the partial area under a ROC curve for a pre-identified set of markers related to energy metabolism and oxidative stress. Thirty children with ASD and 30 age and gender matched controls were enrolled in the study. Using either spectrophotometric or ELISA-colorimetric assay, levels of lipid peroxides, vitamin E, vitamin C, glutathione (GSH)/glutathione disulfide (GSSG) together with the enzymatic activity of catalase, plasma glutathione peroxidase (GPx), and blood superoxide dismutase (SOD), were measured in peripheral blood samples, as biomarkers related to oxidative stress. Creatine kinase, ectonucleotidases (ADPase and ATPase) Na⁺/K⁺ (ATPase), lactate, inorganic phosphate, and levels of adenosine monophosphate (AMP), adenosine diphosphate (ADP), and adenosine triphosphate (ATP) together with adenylate energy charge, were also measured as markers of impaired energy metabolism. Statistical analysis using ROC curves, multiple and logistic regression were performed. A remarkable increase in the area under the curve for most of the combined markers, representing both energy impaired metabolism or oxidative stress, was observed by using combined ROC analyses. Moreover, higher specificity and sensitivity of the combined markers were also reported. The present study indicated that the measurement of the predictive value of selected biomarkers related to energy metabolism and oxidative stress in children with ASD using ROC analysis should lead to the better identification of the etiological mechanism of ASD associated with metabolism and diet. Agents with activity against the impaired metabolic pathway associated with ASD including the metabolic defects and involved enzymes hold a promise as a novel therapy for ASD.

Patient Similarity in Prediction Models Based on Health Data: A Scoping Review

Background

Physicians and health policy makers are required to make predictions during their decision making in various medical problems. Many advances have been made in predictive modeling toward outcome prediction, but these innovations target an average patient and are insufficiently adjustable for individual patients. One developing idea in this field is individualized predictive analytics based on patient similarity. The goal of this approach is to identify patients who are similar to an index patient and derive insights from the records of similar patients to provide personalized predictions..

Objective

The aim is to summarize and review published studies describing computer-based approaches for predicting patients’ future health status based on health data and patient similarity, identify gaps, and provide a starting point for related future research.

Methods

The method involved (1) conducting the review by performing automated searches in Scopus, PubMed, and ISI Web of Science, selecting relevant studies by first screening titles and abstracts then analyzing full-texts, and (2) documenting by extracting publication details and information on context, predictors, missing data, modeling algorithm, outcome, and evaluation methods into a matrix table, synthesizing data, and reporting results.

Results

After duplicate removal, 1339 articles were screened in abstracts and titles and 67 were selected for full-text review. In total, 22 articles met the inclusion criteria. Within included articles, hospitals were the main source of data (n=10). Cardiovascular disease (n=7) and diabetes (n=4) were the dominant patient diseases. Most studies (n=18) used neighborhood-based approaches in devising prediction models. Two studies showed that patient similarity-based modeling outperformed population-based predictive methods.

Conclusions

Interest in patient similarity-based predictive modeling for diagnosis and prognosis has been growing. In addition to raw/coded health data, wavelet transform and term frequency-inverse document frequency methods were employed to extract predictors. Selecting predictors with potential to highlight special cases and defining new patient similarity metrics were among the gaps identified in the existing literature that provide starting points for future work. Patient status prediction models based on patient similarity and health data offer exciting potential for personalizing and ultimately improving health care, leading to better patient outcomes.