Using Explainable Machine Learning to Improve Intensive Care Unit Alarm Systems

González-Nóvoa, José A.; Busto, Laura; Rodríguez-Andina, Juan J.; Fariña, José; Segura, Marta; Gómez, Vanesa; Vila, Dolores; Veiga, César

doi:10.3390/s21217125

Cited by 19 publications

(13 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, explainable machine learning techniques could be employed [ 29 ] using SHAP analysis to identify where a SHAP value of features affects the prediction models, namely if a feature affects having MACE or not. Such a SHAP values plot can further show the positive and negative relationships of the variables with the target variable (1 or 0 predictions of the classifier, namely having a MACE or not, respectively), in other words, information about the way a variable is contributing to predict MACE.…”

Section: Resultsmentioning

confidence: 99%

Using Machine Learning Techniques to Predict MACE in Very Young Acute Coronary Syndrome Patients

et al. 2022

View full text Add to dashboard Cite

Coronary artery disease is a chronic disease with an increased expression in the elderly. However, different studies have shown an increased incidence in young subjects over the last decades. The prediction of major adverse cardiac events (MACE) in very young patients has a significant impact on medical decision-making following coronary angiography and the selection of treatment. Different approaches have been developed to identify patients at a higher risk of adverse outcomes after their coronary anatomy is known. This is a prognostic study of combined data from patients ≤40 years old undergoing coronary angiography (n = 492). We evaluated whether different machine learning (ML) approaches could predict MACE more effectively than traditional statistical methods using logistic regression (LR). Our most effective model for long-term follow-up (60 ± 27 months) was random forest (RF), obtaining an area under the curve (AUC) = 0.79 (95%CI 0.69–0.88), in contrast with LR, obtaining AUC = 0.66 (95%CI 0.53–0.78, p = 0.021). At 1-year follow-up, the RF test found AUC 0.80 (95%CI 0.71–0.89) vs. LR 0.50 (95%CI 0.33–0.66, p < 0.001). The results of our study support the hypothesis that ML methods can improve both the identification of MACE risk patients and the prediction vs. traditional statistical techniques even in a small sample size. The application of ML techniques to focus the efforts on the detection of MACE in very young patients after coronary angiography could help tailor upfront follow-up strategies in such young patients according to their risk of MACE and to be used for proper assignment of health resources.

show abstract

Section: Resultsmentioning

confidence: 99%

Using Machine Learning Techniques to Predict MACE in Very Young Acute Coronary Syndrome Patients

et al. 2022

View full text Add to dashboard Cite

show abstract

“…That poses an intriguing question: how can you trust a model’s decisions if you cannot fully justify how it got there? There has been the latest trend in the growth of XAI for a better understanding of the AI black boxes [ 49 , 136 , 137 , 138 , 139 ]. Grad-CAM or Grad-CAM++ produces a coarse clustering map showing the key regions in the picture for predicting any target idea (say, “COVID-19” in a classification network) by using the gradients of any target concept (say, “COVID-19” in a classification network) in the final convolutional layer.…”

Section: Discussionmentioning

confidence: 99%

COVLIAS 2.0-cXAI: Cloud-Based Explainable Deep Learning System for COVID-19 Lesion Localization in Computed Tomography Scans

Suri¹,

Agarwal²,

Chabert

et al. 2022

Diagnostics

View full text Add to dashboard Cite

Background: The previous COVID-19 lung diagnosis system lacks both scientific validation and the role of explainable artificial intelligence (AI) for understanding lesion localization. This study presents a cloud-based explainable AI, the “COVLIAS 2.0-cXAI” system using four kinds of class activation maps (CAM) models. Methodology: Our cohort consisted of ~6000 CT slices from two sources (Croatia, 80 COVID-19 patients and Italy, 15 control patients). COVLIAS 2.0-cXAI design consisted of three stages: (i) automated lung segmentation using hybrid deep learning ResNet-UNet model by automatic adjustment of Hounsfield units, hyperparameter optimization, and parallel and distributed training, (ii) classification using three kinds of DenseNet (DN) models (DN-121, DN-169, DN-201), and (iii) validation using four kinds of CAM visualization techniques: gradient-weighted class activation mapping (Grad-CAM), Grad-CAM++, score-weighted CAM (Score-CAM), and FasterScore-CAM. The COVLIAS 2.0-cXAI was validated by three trained senior radiologists for its stability and reliability. The Friedman test was also performed on the scores of the three radiologists. Results: The ResNet-UNet segmentation model resulted in dice similarity of 0.96, Jaccard index of 0.93, a correlation coefficient of 0.99, with a figure-of-merit of 95.99%, while the classifier accuracies for the three DN nets (DN-121, DN-169, and DN-201) were 98%, 98%, and 99% with a loss of ~0.003, ~0.0025, and ~0.002 using 50 epochs, respectively. The mean AUC for all three DN models was 0.99 (p < 0.0001). The COVLIAS 2.0-cXAI showed 80% scans for mean alignment index (MAI) between heatmaps and gold standard, a score of four out of five, establishing the system for clinical settings. Conclusions: The COVLIAS 2.0-cXAI successfully showed a cloud-based explainable AI system for lesion localization in lung CT scans.

show abstract

“…XGBoost stands out for its ability to obtain the best results in different benchmarks, and is one of the best-optimized algorithms for computing parallelization, which makes it one of the most used in recent biomedical works [9]- [11]. In addition, it has support for GPUs, which allows the capacity of the algorithm to be fully exploited.…”

Section: B Estimation Model: Xgboostmentioning

confidence: 99%

Using Bayesian Optimization and Wavelet Decomposition in GPU for Arterial Blood Pressure Estimation

González-Nóvoa¹,

Busto²,

Santana³

et al. 2022

2022 44th Annual International Conference of the IEEE Engineering in Medicine &Amp; Biology Society (EMBC)

Self Cite

View full text Add to dashboard Cite

Continuous monitoring of arterial blood pressure (ABP) of patients in hospital is currently carried out in an invasive way, which could represent a risk for them. In this paper, a noninvasive methodology to optimize ABP estimators using electrocardiogram and photoplethysmography signals is proposed. For this, the XGBoost machine learning model, optimized with Bayesian techniques, is executed in a Graphics Processing Unit, which drastically reduces execution time. The methodology is evaluated using the MIMIC-III Waveform Database. Systolic and diastolic pressures are estimated with mean absolute error values of 15.85 and 11.59 mmHg, respectively, similar to those of the state of the art. The main advantage of the proposed methodology with respect to others of the current state of the art is that it allows the optimization of the estimator model to be performed automatically and more efficiently at the computational level for the data available.Clinical Relevance-This approach has the advantage of using noninvasive methods to continuously monitor patient's arterial blood pressure, reducing the risk for patients.

show abstract

Using Explainable Machine Learning to Improve Intensive Care Unit Alarm Systems

Cited by 19 publications

References 18 publications

Using Machine Learning Techniques to Predict MACE in Very Young Acute Coronary Syndrome Patients

Using Machine Learning Techniques to Predict MACE in Very Young Acute Coronary Syndrome Patients

COVLIAS 2.0-cXAI: Cloud-Based Explainable Deep Learning System for COVID-19 Lesion Localization in Computed Tomography Scans

Using Bayesian Optimization and Wavelet Decomposition in GPU for Arterial Blood Pressure Estimation

Contact Info

Product

Resources

About