Development and Interpretation of Multiple Machine Learning Models for Predicting Postoperative Delayed Remission of Acromegaly Patients During Long-Term Follow-Up

We present a novel platform for testing the effect of interventions on life- and health-span of a short-lived semi transparent freshwater organism, sensitive to drugs with complex behavior and physiology - the planktonic crustacean Daphnia magna. Within this platform, dozens of complex behavioural features of both routine motion and response to stimuli are continuously accurately quantified for large homogeneous cohorts via an automated phenotyping pipeline. We build predictive machine learning models calibrated using chronological age and extrapolate onto phenotypic age. We further apply the model to estimate the phenotypic age under pharmacological perturbation. Our platform provides a scalable framework for drug screening and characterization in both life-long and instant assays as illustrated using long term dose response profile of metformin and short term assay of such well-studied substances as caffeine and alcohol.

Download Full-text

Data-Driven Approach for Predicting and Explaining the Risk of Long-Term Unemployment

E3S Web of Conferences ◽

10.1051/e3sconf/202021401023 ◽

2020 ◽

Vol 214 ◽

pp. 01023

Author(s):

Linan (Frank) Zhao

Keyword(s):

Machine Learning ◽

Age Groups ◽

Learning Models ◽

Public Authorities ◽

Ensemble Machine Learning ◽

European Public ◽

Data Driven Approach ◽

Using Data ◽

Machine Learning Models

Long-term unemployment has significant societal impact and is of particular concerns for policymakers with regard to economic growth and public finances. This paper constructs advanced ensemble machine learning models to predict citizens’ risks of becoming long-term unemployed using data collected from European public authorities for employment service. The proposed model achieves 81.2% accuracy on identifying citizens with high risks of long-term unemployment. This paper also examines how to dissect black-box machine learning models by offering explanations at both a local and global level using SHAP, a state-of-the-art model-agnostic approach to explain factors that contribute to long-term unemployment. Lastly, this paper addresses an under-explored question when applying machine learning in the public domain, that is, the inherent bias in model predictions. The results show that popular models such as gradient boosted trees may produce unfair predictions against senior age groups and immigrants. Overall, this paper sheds light on the recent increasing shift for governments to adopt machine learning models to profile and prioritize employment resources to reduce the detrimental effects of long-term unemployment and improve public welfare.

Download Full-text

30Machine learning to predict the long-term risk of myocardial infarction and cardiac death based on clinical risk, coronary calcium and epicardial adipose tissue: a prospective study

European Heart Journal ◽

10.1093/eurheartj/ehz747.0002 ◽

2019 ◽

Vol 40 (Supplement_1) ◽

Cited By ~ 1

Author(s):

F C Commandeur ◽

P J Slomka ◽

M Goeller ◽

X Chen ◽

S Cadet ◽

...

Keyword(s):

Machine Learning ◽

Myocardial Infarction ◽

Adipose Tissue ◽

Cardiac Death ◽

Epicardial Adipose Tissue ◽

Long Term Follow Up ◽

Ascvd Risk ◽

Asymptomatic Subjects

Abstract Background/Introduction Machine learning (ML) allows objective integration of clinical and imaging data for the prediction of events. ML prediction of cardiovascular events in asymptomatic subjects over long-term follow-up, utilizing quantitative CT measures of coronary artery calcium (CAC) and epicardial adipose tissue (EAT) have not yet been evaluated. Purpose To analyze the ability of machine learning to integrate clinical parameters with coronary calcium and EAT quantification in order to improve prediction of myocardial infarction (MI) and cardiac death in asymptomatic subjects. Methods We assessed 2071 consecutive subjects [1230 (59%) male, age: 56.049.03] from the EISNER (Early Identification of Subclinical Atherosclerosis by Noninvasive Imaging Research) trial with long-term follow-up after non-enhanced cardiac CT. CAC (Agatston) score, age-and-gender-adjusted CAC percentile, and aortic calcium scores were obtained. EAT volume and density were quantified using a fully automated deep learning method. Extreme gradient boosting, a ML algorithm, was trained using demographic variables, plasma lipid panel measurements, risk factors as well as CAC, aortic calcium and EAT measures from CAC CT scans. ML was validated using 10-fold cross validation; event prediction was evaluated using area-under-receiver operating characteristic curve (AUC) analysis and Cox proportional hazards regression. Optimal ML cut-point for risk of MI and cardiac death was determined by highest Youden's index (sensitivity + specificity – 1). Results At 152 years' follow-up, 76 events of MI and/or cardiac death had occurred. ML obtained a significantly higher AUC than the ASCVD risk and CAC score in predicting events (ML: 0.81; ASCVD: 0.76, p<0.05; CAC: 0.75, p<0.01, Figure A). ML performance was mostly driven by age, ASCVD risk and calcium as shown by the variable importance (Figure B); however, all variables with non-zero gain contributed to the ML performance. ML achieved a sensitivity and specificity of 77.6% and 73.5%, respectively. For an equal specificity, ASCVD and CAC scores obtained a sensitivity of 61.8% and 67.1%, respectively. High ML risk was associated with a high risk of suffering an event by Cox regression (HR: 9.25 [95% CI: 5.39–15.87], p<0.001; survival curves in Figure C). The relationships persisted when adjusted for age, gender, CAC, CAC percentile, aortic calcium score, and ASCVD risk score; with a hazard ratio of 3.42 for high ML risk (HR: 3.42 [95% CI: 1.54–7.57], p=0.002). Conclusion(s) Machine learning used to integrate clinical and quantitative imaging-based variables significantly improves prediction of MI and cardiac death in asymptomatic subjects undergoing CAC assessment, compared to standard risk assessment methods. Acknowledgement/Funding NHLBI 1R01HL13361, Bundesministerium für Bildung und Forschung (01EX1012B), Dr. Miriam and Sheldon G. Adelson Medical Research Foundation

Download Full-text

Reducing error propagation for long term energy forecasting using multivariate prediction

10.29007/mbb7 ◽

2020 ◽

Author(s):

Maher Selim ◽

Ryan Zhou ◽

Wenying Feng ◽

Omar Alam

Keyword(s):

Machine Learning ◽

Learning Models ◽

Short Term ◽

Energy Forecasting ◽

Opposite Behavior ◽

Multivariate Prediction ◽

Term Energy ◽

Short And Long Term ◽

Machine Learning Models

Many statistical and machine learning models for prediction make use of historical data as an input and produce single or small numbers of output values. To forecast over many timesteps, it is necessary to run the program recursively. This leads to a compounding of errors, which has adverse effects on accuracy for long forecast periods. In this paper, we show this can be mitigated through the addition of generating features which can have an “anchoring” effect on recurrent forecasts, limiting the amount of compounded error in the long term. This is studied experimentally on a benchmark energy dataset using two machine learning models LSTM and XGBoost. Prediction accuracy over differing forecast lengths is compared using the forecasting MAPE. It is found that for LSTM model the accuracy of short term energy forecasting by using a past energy consumption value as a feature is higher than the accuracy when not using past values as a feature. The opposite behavior takes place for the long term energy forecasting. For the XGBoost model, the accuracy for both short and long term energy forecasting is higher when not using past values as a feature.

Download Full-text

Long-Term Impacts of Fair Machine Learning

Ergonomics in Design The Quarterly of Human Factors Applications ◽

10.1177/1064804619884160 ◽

2019 ◽

Vol 28 (3) ◽

pp. 7-11

Author(s):

Xueru Zhang ◽

Mohammad Mahdi Khalili ◽

Mingyan Liu

Keyword(s):

Machine Learning ◽

Real World ◽

Human Beings ◽

Learning Models ◽

Real World Data ◽

World Data ◽

Fairness Concerns ◽

Fairness Constraints ◽

Machine Learning Models

Machine learning models developed from real-world data can inherit potential, preexisting bias in the dataset. When these models are used to inform decisions involving human beings, fairness concerns inevitably arise. Imposing certain fairness constraints in the training of models can be effective only if appropriate criteria are applied. However, a fairness criterion can be defined/assessed only when the interaction between the decisions and the underlying population is well understood. We introduce two feedback models describing how people react when receiving machine-aided decisions and illustrate that some commonly used fairness criteria can end with undesirable consequences while reinforcing discrimination.

Download Full-text

Supplementary material to "Long-term trends of ambient nitrate (NO<sub>3</sub><sup>−</sup>) concentrations across China based on ensemble machine-learning models"

10.5194/essd-2020-243-supplement ◽

2020 ◽

Author(s):

Rui Li ◽

Lulu Cui ◽

Yilong Zhao ◽

Wenhui Zhou ◽

Hongbo Fu

Keyword(s):

Machine Learning ◽

Learning Models ◽

Ensemble Machine Learning ◽

Long Term Trends ◽

Supplementary Material ◽

Machine Learning Models

Download Full-text

Covid-19 and Economics Forecasting on Advanced andEmerging Countries

EconoQuantum ◽

10.18381/eq.v18i1.7222 ◽

2020 ◽

Vol 18 (1) ◽

pp. 21-43

Author(s):

Abraham Ramírez García ◽

◽

Ana Lorena Jiménez Preciado ◽

Keyword(s):

Machine Learning ◽

Developing Economies ◽

Economic Recovery ◽

Leading Indicators ◽

Learning Models ◽

Slow Recovery ◽

Final Size ◽

Virus Spreading ◽

Machine Learning Models

Objective: To estimate the size and the dynamics of the coro-navirus (covid-19) pandemic in Advanced, Emerging, and Developing Economies, and to determine its implications for economic growth.Methodology: A susceptible Infected Recovered (sir) mod-el is implemented, we calculate the size of the pandemic through numerical integration and phase diagrams for covid-19 trajectory; finally, we use ensemble models (ran-dom forest) to forecast economic growth.Results: We confirm that there are differences in pandemic spread and size among countries; likewise, the trajectories show a long-term spiral cycle. Economic recovery is expect-ed to be slow and gradual for most of the economies.Limitations: All countries differ in covid-19 test applica-tions, which could lead to inaccurate total confirmed cases and an imprecise estimate of the pandemic’s spread and size. In addition, there is a lack of leading indicators in some countries, generating a higher mse of some machine learning models. Originality: To implement economic-epidemiological mod-els to analyze the evolution and virus’ spreading through-out time.Conclusions: It is found the pandemic’s final size to be be-tween 74-77%. Likewise, it is demonstrated that covid-19 is endemic, with a constant prevalence of 9 years on av-erage. The spread of the pandemic has caused countries to self-induce in an unprecedented recession with a slow recovery.

Download Full-text

Pharmacoepidemiology and Big Data Analytics: Challenges and Opportunities when Moving towards Precision Medicine

CHIMIA International Journal for Chemistry ◽

10.2533/chimia.2019.1012 ◽

2019 ◽

Vol 73 (12) ◽

pp. 1012-1017

Author(s):

Andrea M. Burden

Keyword(s):

Machine Learning ◽

Language Processing ◽

Real World ◽

Big Data Analytics ◽

Large Size ◽

Challenges And Opportunities ◽

Long Term Follow Up ◽

Machine Learning Applications

Pharmacoepidemiology is the study of the safety and effectiveness of medications following market approval. The increased availability and size of healthcare utilization databases allows for the study of rare adverse events, sub-group analyses, and long-term follow-up. These datasets are large, including thousands of patient records spanning multiple years of observation, and representative of real-world clinical practice. Thus, one of the main advantages is the possibility to study the real-world safety and effectiveness of medications in uncontrolled environments. Due to the large size (volume), structure (variety), and availability (velocity) of observational healthcare databases there is a large interest in the application of natural language processing and machine learning, including the development of novel models to detect drug–drug interactions, patient phenotypes, and outcome prediction. This report will provide an overview of the current challenges in pharmacoepidemiology and where machine learning applications may be useful for filling the gap.

Download Full-text