Machine Learning Hyperparameter Fine Tuning Service on Dynamic Cloud Resource Allocation System - taking Heart Sounds as an Example

Background An ongoing outbreak of a novel coronavirus (2019-nCoV) pneumonia continues to affect the whole world including major countries such as China, USA, Italy, France and the United Kingdom. We present outcome (‘recovered’, ‘isolated’ or ‘death’) risk estimates of 2019-nCoV over ‘early’ datasets. A major consideration is the likelihood of death for patients with 2019-nCoV. Method Accounting for the impact of the variations in the reporting rate of 2019-nCoV, we used machine learning techniques (AdaBoost, bagging, extra-trees, decision trees and k-nearest neighbour classifiers) on two 2019-nCoV datasets obtained from Kaggle on March 30, 2020. We used ‘country’, ‘age’ and ‘gender’ as features to predict outcome for both datasets. We included the patient’s ‘disease’ history (only present in the second dataset) to predict the outcome for the second dataset. Results The use of a patient’s ‘disease’ history improves the prediction of ‘death’ by more than sevenfold. The models ignoring a patent’s ‘disease’ history performed poorly in test predictions. Conclusion Our findings indicate the potential of using a patient’s ‘disease’ history as part of the feature set in machine learning techniques to improve 2019-nCoV predictions. This development can have a positive effect on predictive patient treatment and can result in easing currently overburdened healthcare systems worldwide, especially with the increasing prevalence of second and third wave re-infections in some countries.

show abstract

“…The best performance for each run based on our specified criteria. In addition, the hyperparameter values were validated using Optunity [47,48].…”

Section: Hyper-parameter Settingsmentioning

confidence: 99%

Maintaining proper health records improves machine learning predictions for novel 2019-nCoV

Khan

Ramsahai²

2021

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

show abstract

“…The best performance for each run based on our specified criteria. In addition, the hyper-parameter values were validated using opt unity [47,48]. Even though we experimented on many different hyper-parameter settings for each model to attain an 'optimal' value, our attempts and the search performed using Optunity were not exhaustive.…”

Section: Hyper-parameter Settingsmentioning

confidence: 99%

Maintaining proper health records improves machine learning predictions for novel 2019-nCoV

Khan

Ramsahai

2021

Preprint

View full text Add to dashboard Cite

Background: An ongoing outbreak of a novel coronavirus (2019-nCoV) pneumonia continues to affect the whole world including major countries such as China, USA, Italy, France and the United Kingdom. We present outcome (’recovered’, ’isolated’ or ’death’) risk estimates of 2019-nCoV over ’early’ datasets. A major consideration is the likelihood of death for patients with 2019-nCoV.Method: Accounting for the impact of the variations in the reporting rate of 2019-nCoV, we used machine learning techniques (AdaBoost, bagging, extra-trees, decision trees and k-nearest Neighbour classifiers) on two 2019-nCoV datasets obtained from Kaggle on March 30, 2020. We used ’country’, ’age’ and ’gender’ as features to predict outcome for both datasets. We included the patient’s ’disease’ history (only present in the second dataset) to predict the outcome for the second dataset.Results: The use of a patient’s ’disease’ history improves the prediction of ’death’ by more than 7-fold. The models ignoring a patent’s ’disease’ history performed poorly in test predictions.Conclusion: Our findings indicate the potential of using a patient’s ’disease’ history as part of the feature set in machine learning techniques to improve 2019-nCoV predictions. This development can have a positive effect on predictive patient treatment and can result in easing currently overburdened healthcare systems worldwide, especially with the increasing prevalence of second and third wave re-infections in some countries.

show abstract

“…The best performance for each run based on our specified criteria. In addition, the hyper-parameter values were validated using Optunity [47,48]. Even though we experimented on many different hyper-parameter settings for each model to attain an 'optimal' value, our attempts and the search performed using Optunity were not exhaustive.…”

Section: Hyper-parameter Settingsmentioning

confidence: 99%

Maintaining proper health records improves machine learning predictions for novel 2019-nCoV

Khan

Ramsahai

2020

Preprint

View full text Add to dashboard Cite

Background: An ongoing outbreak of a novel coronavirus (2019-nCoV) pneumonia continues to aect the whole world including major countries such as China, USA, Italy, France and the United Kingdom. We present outcome ('recovered', 'isolated' or 'death') risk estimates of 2019-nCoV over 'early' datasets. A major consideration is the likelihood of death for patients with 2019-nCoV.Method: Accounting for the impact of the variations in the reporting rate of 2019-nCoV, we used machine learning techniques (AdaBoost, bagging, extra-trees, decision trees and k-nearest neighbour classiers) on two 2019-nCoVdatasets obtained from Kaggle on March 30, 2020. We used 'country', 'age' and 'gender' as features to predict outcome for both datasets. We included the patient's 'disease' history (only present in the second dataset) to predict the outcome for the second dataset.Results: The use of a patient's 'disease' history improves the prediction of 'death' by more than 7-fold. The models ignoring a patent's 'disease' history performed poorly in test predictions.Conclusion: Our ndings indicate the potential of using a patient's 'disease' history as part of the feature set in machine learning techniques to improve 2019-nCoV predictions. This development can have a positive eect on predictive patient treatment and can result in easing currently overburdened healthcare systems worldwide, especially with the increasing prevalence of second and third wave re-infections in some countries.

show abstract

Machine Learning Hyperparameter Fine Tuning Service on Dynamic Cloud Resource Allocation System - taking Heart Sounds as an Example

Cited by 3 publications

References 4 publications

Maintaining proper health records improves machine learning predictions for novel 2019-nCoV

Maintaining proper health records improves machine learning predictions for novel 2019-nCoV

Maintaining proper health records improves machine learning predictions for novel 2019-nCoV

Maintaining proper health records improves machine learning predictions for novel 2019-nCoV

Contact Info

Product

Resources

About