Effects of SVM parameter optimization on discrimination and calibration for post-procedural PCI mortality

Prediction Model for Unfavorable Outcome in Spontaneous Intracerebral Hemorrhage Based on Machine Learning

OBJECTIVE

The spontaneous intracerebral hemorrhage (ICH) remains a significant cause of mortality and morbidity throughout the world. The purpose of this retrospective study is to develop multiple models for predicting ICH outcomes using machine learning (ML).

METHODS

Between January 2014 and October 2021, we included ICH patients identified by computed tomography or magnetic resonance imaging and treated with surgery. At the 6-month check-up, outcomes were assessed using the modified Rankin Scale. In this study, four ML models, including Support Vector Machine (SVM), Decision Tree C5.0, Artificial Neural Network, Logistic Regression were used to build ICH prediction models. In order to evaluate the reliability and the ML models, we calculated the area under the receiver operating characteristic curve (AUC), specificity, sensitivity, accuracy, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio (DOR).

RESULTS

We identified 71 patients who had favorable outcomes and 156 who had unfavorable outcomes. The results showed that the SVM model achieved the best comprehensive prediction efficiency. For the SVM model, the AUC, accuracy, specificity, sensitivity, PLR, NLR, and DOR were 0.91, 0.92, 0.92, 0.93, 11.63, 0.076, and 153.03, respectively. For the SVM model, we found the importance value of time to operating room (TOR) was higher significantly than other variables.

CONCLUSION

The analysis of clinical reliability showed that the SVM model achieved the best comprehensive prediction efficiency and the importance value of TOR was higher significantly than other variables.

Mortality Prediction of Patients With Cardiovascular Disease Using Medical Claims Data Under Artificial Intelligence Architectures: Validation Study

Background

Cardiovascular disease (CVD) is the greatest health problem in Australia, which kills more people than any other disease and incurs enormous costs for the health care system. In this study, we present a benchmark comparison of various artificial intelligence (AI) architectures for predicting the mortality rate of patients with CVD using structured medical claims data. Compared with other research in the clinical literature, our models are more efficient because we use a smaller number of features, and this study could help health professionals accurately choose AI models to predict mortality among patients with CVD using only claims data before a clinic visit.

Objective

This study aims to support health clinicians in accurately predicting mortality among patients with CVD using only claims data before a clinic visit.

Methods

The data set was obtained from the Medicare Benefits Scheme and Pharmaceutical Benefits Scheme service information in the period between 2004 and 2014, released by the Department of Health Australia in 2016. It included 346,201 records, corresponding to 346,201 patients. A total of five AI algorithms, including four classical machine learning algorithms (logistic regression [LR], random forest [RF], extra trees [ET], and gradient boosting trees [GBT]) and a deep learning algorithm, which is a densely connected neural network (DNN), were developed and compared in this study. In addition, because of the minority of deceased patients in the data set, a separate experiment using the Synthetic Minority Oversampling Technique (SMOTE) was conducted to enrich the data.

Results

Regarding model performance, in terms of discrimination, GBT and RF were the models with the highest area under the receiver operating characteristic curve (97.8% and 97.7%, respectively), followed by ET (96.8%) and LR (96.4%), whereas DNN was the least discriminative (95.3%). In terms of reliability, LR predictions were the least calibrated compared with the other four algorithms. In this study, despite increasing the training time, SMOTE was proven to further improve the model performance of LR, whereas other algorithms, especially GBT and DNN, worked well with class imbalanced data.

Conclusions

Compared with other research in the clinical literature involving AI models using claims data to predict patient health outcomes, our models are more efficient because we use a smaller number of features but still achieve high performance. This study could help health professionals accurately choose AI models to predict mortality among patients with CVD using only claims data before a clinic visit.

The influence of hemodynamics on graft patency prediction model based on support vector machine

In the existing patency prediction model of coronary artery bypass grafting (CABG), the characteristics are based on graft flow, but no researchers selected hemodynamic factors as the characteristics. The purpose of this paper is to study whether the introduction of hemodynamic factors will affect the performance of the prediction model. Transit time flow-meter (TTFM) waveforms and 1-year postoperative patency results were obtained from 50 internal mammary arterial grafts (LIMA) and 82 saphenous venous grafts (SVG) in 60 patients. Taking TTFM waveforms as the boundary conditions, the CABG ideal models were constructed to obtain hemodynamic factors in grafts. Based on clinical characteristics and combination of clinical and hemodynamic characteristics, patency prediction models based on support vector machine (SVM) were constructed respectively. For LIMA, after the introduction of hemodynamic factors, the accuracy, sensitivity and specificity of the prediction model increased from 70.35%, 50% and 74.17% to 78.02%, 70% and 78.89%, respectively. For SVG, the accuracy, sensitivity and specificity of the prediction model increased from 63.24%, 40% and 76.91% to 74.41%, 60.1% and 82.73%, respectively. The performance of the prediction model can be improved by introducing hemodynamic factors into the characteristics of the model. The accuracy, sensitivity and specificity of the prediction results are higher with the addition of hemodynamic characteristics.

A practical computerized decision support system for predicting the severity of Alzheimer's disease of an individual

Computerized clinical decision support systems can help to provide objective, standardized, and timely dementia diagnosis. However, current computerized systems are mainly based on group analysis, discrete classification of disease stages, or expensive and not readily accessible biomarkers, while current clinical practice relies relatively heavily on cognitive and functional assessments (CFA). In this study, we developed a computational framework using a suite of machine learning tools for identifying key markers in predicting the severity of Alzheimer's disease (AD) from a large set of biological and clinical measures. Six machine learning approaches, namely Kernel Ridge Regression (KRR), Support Vector Regression, and k-Nearest Neighbor for regression and Support Vector Machine (SVM), Random Forest, and k-Nearest Neighbor for classification, were used for the development of predictive models. We demonstrated high predictive power of CFA. Predictive performance of models incorporating CFA was shown to consistently have higher accuracy than those based solely on biomarker modalities. We found that KRR and SVM were the best performing regression and classification methods respectively. The optimal SVM performance was observed for a set of four CFA test scores (FAQ, ADAS13, MoCA, MMSE) with multi-class classification accuracy of 83.0%, 95%CI = (72.1%, 93.8%) while the best performance of the KRR model was reported with combined CFA and MRI neuroimaging data, i.e., R ² = 0.874, 95%CI = (0.827, 0.922). Given the high predictive power of CFA and their widespread use in clinical practice, we then designed a data-driven and self-adaptive computerized clinical decision support system (CDSS) prototype for evaluating the severity of AD of an individual on a continuous spectrum. The system implemented an automated computational approach for data pre-processing, modelling, and validation and used exclusively the scores of selected cognitive measures as data entries. Taken together, we have developed an objective and practical CDSS to aid AD diagnosis.

Application of Hybrid Functional Groups to Predict ATP Binding Proteins

The ATP binding proteins exist as a hybrid of proteins with Walker A motif and universal stress proteins (USPs) having an alternative motif for binding ATP. There is an urgent need to find a reliable and comprehensive hybrid predictor for ATP binding proteins using whole sequence information. In this paper the open source LIBSVM toolbox was used to build a classifier at 10-fold cross-validation. The best hybrid model was the combination of amino acid and dipeptide composition with an accuracy of 84.57% and Mathews correlation coefficient (MCC) value of 0.693. This classifier proves to be better than many classical ATP binding protein predictors. The general trend observed is that combinations of descriptors performed better and improved the overall performances of individual descriptors, particularly when combined with amino acid composition. The work developed a comprehensive model for predicting ATP binding proteins irrespective of their functional motifs. This model provides a high probability of success for molecular biologists in predicting and selecting diverse groups of ATP binding proteins irrespective of their functional motifs.

Predicting complications of percutaneous coronary intervention using a novel support vector method

OBJECTIVE

To explore the feasibility of a novel approach using an augmented one-class learning algorithm to model in-laboratory complications of percutaneous coronary intervention (PCI).

MATERIALS AND METHODS

Data from the Blue Cross Blue Shield of Michigan Cardiovascular Consortium (BMC2) multicenter registry for the years 2007 and 2008 (n=41 016) were used to train models to predict 13 different in-laboratory PCI complications using a novel one-plus-class support vector machine (OP-SVM) algorithm. The performance of these models in terms of discrimination and calibration was compared to the performance of models trained using the following classification algorithms on BMC2 data from 2009 (n=20 289): logistic regression (LR), one-class support vector machine classification (OC-SVM), and two-class support vector machine classification (TC-SVM). For the OP-SVM and TC-SVM approaches, variants of the algorithms with cost-sensitive weighting were also considered.

RESULTS

The OP-SVM algorithm and its cost-sensitive variant achieved the highest area under the receiver operating characteristic curve for the majority of the PCI complications studied (eight cases). Similar improvements were observed for the Hosmer-Lemeshow χ(2) value (seven cases) and the mean cross-entropy error (eight cases).

CONCLUSIONS

The OP-SVM algorithm based on an augmented one-class learning problem improved discrimination and calibration across different PCI complications relative to LR and traditional support vector machine classification. Such an approach may have value in a broader range of clinical domains.

Detection and identification of potential biomarkers of breast cancer

PURPOSE

Noninvasive and convenient biomarkers for early diagnosis of breast cancer remain an urgent need. The aim of this study was to discover and identify potential protein biomarkers specific for breast cancer.

METHODS

Two hundred and eighty-two (282) serum samples with 124 breast cancer and 158 controls were randomly divided into a training set and a blind-testing set. Serum proteomic profiles were analyzed using SELDI-TOF-MS. Candidate biomarkers were purified by HPLC, identified by LC-MS/MS and validated using ProteinChip immunoassays and western blot technique.

RESULTS

A total of 3 peaks (m/z with 6,630, 8,139 and 8,942 Da) were screened out by support vector machine to construct the classification model with high discriminatory power in the training set. The sensitivity and specificity of the model were 96.45 and 94.87%, respectively, in the blind-testing set. The candidate biomarker with m/z of 6,630 Da was found to be down-regulated in breast cancer patients, and was identified as apolipoprotein C-I. Another two candidate biomarkers (8,139, 8,942 Da) were found up-regulated in breast cancer and identified as C-terminal-truncated form of C3a and complement component C3a, respectively. In addition, the level of apolipoprotein C-I progressively decreased with the clinical stages I, II, III and IV, and the expression of C-terminal-truncated form of C3a and complement component C3a gradually increased in higher stages.

CONCLUSIONS

We have identified a set of biomarkers that could discriminate breast cancer from non-cancer controls. An efficient strategy, including SELDI-TOF-MS analysis, HPLC purification, MALDI-TOF-MS trace and LC-MS/MS identification, has been proved very successful.

Discovery and identification of potential biomarkers of papillary thyroid carcinoma

Background

Thyroid carcinoma is the most common endocrine malignancy and a common cancer among the malignancies of head and neck. Noninvasive and convenient biomarkers for diagnosis of papillary thyroid carcinoma (PTC) as early as possible remain an urgent need. The aim of this study was to discover and identify potential protein biomarkers for PTC specifically.

Methods

Two hundred and twenty four (224) serum samples with 108 PTC and 116 controls were randomly divided into a training set and a blind testing set. Serum proteomic profiles were analyzed using SELDI-TOF-MS. Candidate biomarkers were purified by HPLC, identified by LC-MS/MS and validated using ProteinChip immunoassays.

Results

A total of 3 peaks (m/z with 9190, 6631 and 8697 Da) were screened out by support vector machine (SVM) to construct the classification model with high discriminatory power in the training set. The sensitivity and specificity of the model were 95.15% and 93.97% respectively in the blind testing set. The candidate biomarker with m/z of 9190 Da was found to be up-regulated in PTC patients, and was identified as haptoglobin alpha-1 chain. Another two candidate biomarkers (6631, 8697 Da) were found down-regulated in PTC and identified as apolipoprotein C-I and apolipoprotein C-III, respectively. In addition, the level of haptoglobin alpha-1 chain (9190 Da) progressively increased with the clinical stage I, II, III and IV, and the expression of apolipoprotein C-I and apolipoprotein C-III (6631, 8697 Da) gradually decreased in higher stages.

Conclusion

We have identified a set of biomarkers that could discriminate PTC from non-cancer controls. An efficient strategy, including SELDI-TOF-MS analysis, HPLC purification, MALDI-TOF-MS trace and LC-MS/MS identification, has been proved successful.