scholarly journals Practical Considerations for Accuracy Evaluation in Sensor-Based Machine Learning and Deep Learning

Sensors ◽  
2019 ◽  
Vol 19 (16) ◽  
pp. 3491 ◽  
Author(s):  
Issam Hammad ◽  
Kamal El-Sankary
Keyword(s):  
Machine Learning ◽  
Thermal Noise ◽  
Error Resilience ◽  
Sensor Data ◽  
Accuracy Evaluation ◽  
Sensor Failure ◽  
Learning Models ◽  
Analog To Digital ◽  
The Impact ◽  
Machine Learning Models

Accuracy evaluation in machine learning is based on the split of data into a training set and a test set. This critical step is applied to develop machine learning models including models based on sensor data. For sensor-based problems, comparing the accuracy of machine learning models using the train/test split provides only a baseline comparison in ideal situations. Such comparisons won’t consider practical production problems that can impact the inference accuracy such as the sensors’ thermal noise, performance with lower inference quantization, and tolerance to sensor failure. Therefore, this paper proposes a set of practical tests that can be applied when comparing the accuracy of machine learning models for sensor-based problems. First, the impact of the sensors’ thermal noise on the models’ inference accuracy was simulated. Machine learning algorithms have different levels of error resilience to thermal noise, as will be presented. Second, the models’ accuracy using lower inference quantization was compared. Lowering inference quantization leads to lowering the analog-to-digital converter (ADC) resolution which is cost-effective in embedded designs. Moreover, in custom designs, analog-to-digital converters’ (ADCs) effective number of bits (ENOB) is usually lower than the ideal number of bits due to various design factors. Therefore, it is practical to compare models’ accuracy using lower inference quantization. Third, the models’ accuracy tolerance to sensor failure was evaluated and compared. For this study, University of California Irvine (UCI) ‘Daily and Sports Activities’ dataset was used to present these practical tests and their impact on model selection.

Implementing clinical decision support for oncology advanced care planning: A systems engineering framework to optimize the usability and utility of a machine learning predictive model in clinical practice.

2021 ◽  
Vol 39 (28_suppl) ◽  
pp. 330-330
Author(s):  
Teja Ganta ◽  
Stephanie Lehrman ◽  
Rachel Pappalardo ◽  
Madalene Crow ◽  
Meagan Will ◽  
...  
Keyword(s):  
Machine Learning ◽  
High Risk ◽  
Predictive Model ◽  
Systems Engineering ◽  
Care Planning ◽  
Learning Models ◽  
Predictive Tool ◽  
Risk Of Death ◽  
The Impact ◽  
Machine Learning Models

330 Background: Machine learning models are well-positioned to transform cancer care delivery by providing oncologists with more accurate or accessible information to augment clinical decisions. Many machine learning projects, however, focus on model accuracy without considering the impact of using the model in real-world settings and rarely carry forward to clinical implementation. We present a human-centered systems engineering approach to address clinical problems with workflow interventions utilizing machine learning algorithms. Methods: We aimed to develop a mortality predictive tool, using a Random Forest algorithm, to identify oncology patients at high risk of death within 30 days to move advance care planning (ACP) discussions earlier in the illness trajectory. First, a project sponsor defined the clinical need and requirements of an intervention. The data scientists developed the predictive algorithm using data available in the electronic health record (EHR). A multidisciplinary workgroup was assembled including oncology physicians, advanced practice providers, nurses, social workers, chaplain, clinical informaticists, and data scientists. Meeting bi-monthly, the group utilized human-centered design (HCD) methods to understand clinical workflows and identify points of intervention. The workgroup completed a workflow redesign workshop, a 90-minute facilitated group discussion, to integrate the model in a future state workflow. An EHR (Epic) analyst built the user interface to support the intervention per the group’s requirements. The workflow was piloted in thoracic oncology and bone marrow transplant with plans to scale to other cancer clinics. Results: Our predictive model performance on test data was acceptable (sensitivity 75%, specificity 75%, F-1 score 0.71, AUC 0.82). The workgroup identified a “quality of life coordinator” who: reviews an EHR report of patients scheduled in the upcoming 7 days who have a high risk of 30-day mortality; works with the oncology team to determine ACP clinical appropriateness; documents the need for ACP; identifies potential referrals to supportive oncology, social work, or chaplain; and coordinates the oncology appointment. The oncologist receives a reminder on the day of the patient’s scheduled visit. Conclusions: This workgroup is a viable approach that can be replicated at institutions to address clinical needs and realize the full potential of machine learning models in healthcare. The next steps for this project are to address end-user feedback from the pilot, expand the intervention to other cancer disease groups, and track clinical metrics.

scholarly journals Influence of social determinants of health and county vaccination rates on machine learning models to predict COVID-19 case growth in Tennessee

2021 ◽  
Vol 28 (1) ◽  
pp. e100439
Author(s):  
Lukasz S Wylezinski ◽  
Coleman R Harris ◽  
Cody N Heiser ◽  
Jamieson D Gray ◽  
Charles F Spurlock
Keyword(s):  
Machine Learning ◽  
Risk Factors ◽  
Social Determinants Of Health ◽  
Social Determinants ◽  
Determinants Of Health ◽  
Learning Models ◽  
Vaccination Rates ◽  
Data Framework ◽  
The Impact ◽  
Machine Learning Models

IntroductionThe SARS-CoV-2 (COVID-19) pandemic has exposed health disparities throughout the USA, particularly among racial and ethnic minorities. As a result, there is a need for data-driven approaches to pinpoint the unique constellation of clinical and social determinants of health (SDOH) risk factors that give rise to poor patient outcomes following infection in US communities.MethodsWe combined county-level COVID-19 testing data, COVID-19 vaccination rates and SDOH information in Tennessee. Between February and May 2021, we trained machine learning models on a semimonthly basis using these datasets to predict COVID-19 incidence in Tennessee counties. We then analyzed SDOH data features at each time point to rank the impact of each feature on model performance.ResultsOur results indicate that COVID-19 vaccination rates play a crucial role in determining future COVID-19 disease risk. Beginning in mid-March 2021, higher vaccination rates significantly correlated with lower COVID-19 case growth predictions. Further, as the relative importance of COVID-19 vaccination data features grew, demographic SDOH features such as age, race and ethnicity decreased while the impact of socioeconomic and environmental factors, including access to healthcare and transportation, increased.ConclusionIncorporating a data framework to track the evolving patterns of community-level SDOH risk factors could provide policy-makers with additional data resources to improve health equity and resilience to future public health emergencies.

scholarly journals Identification of Primary Antimicrobial Resistance Drivers in Agricultural Nontyphoidal Salmonella enterica Serovars by Using Machine Learning

mSystems ◽  
2019 ◽  
Vol 4 (4) ◽  
Author(s):  
Finlay Maguire ◽  
Muhammad Attiq Rehman ◽  
Catherine Carrillo ◽  
Moussa S. Diarra ◽  
Robert G. Beiko
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Antimicrobial Resistance ◽  
Broiler Chicken ◽  
Genomic Data ◽  
Set Covering ◽  
Learning Models ◽  
Commercial Chicken ◽  
The Impact ◽  
Machine Learning Models

ABSTRACT Nontyphoidal Salmonella (NTS) is a leading global cause of bacterial foodborne morbidity and mortality. Our ability to treat severe NTS infections has been impaired by increasing antimicrobial resistance (AMR). To understand and mitigate the global health crisis AMR represents, we need to link the observed resistance phenotypes with their underlying genomic mechanisms. Broiler chickens represent a key reservoir and vector for NTS infections, but isolates from this setting have been characterized in only very low numbers relative to clinical isolates. In this study, we sequenced and assembled 97 genomes encompassing 7 serotypes isolated from broiler chicken in farms in British Columbia between 2005 and 2008. Through application of machine learning (ML) models to predict the observed AMR phenotype from this genomic data, we were able to generate highly (0.92 to 0.99) precise logistic regression models using known AMR gene annotations as features for 7 antibiotics (amoxicillin-clavulanic acid, ampicillin, cefoxitin, ceftiofur, ceftriaxone, streptomycin, and tetracycline). Similarly, we also trained “reference-free” k-mer-based set-covering machine phenotypic prediction models (0.91 to 1.0 precision) for these antibiotics. By combining the inferred k-mers and logistic regression weights, we identified the primary drivers of AMR for the 7 studied antibiotics in these isolates. With our research representing one of the largest studies of a diverse set of NTS isolates from broiler chicken, we can thus confirm that the AmpC-like CMY-2 β-lactamase is a primary driver of β-lactam resistance and that the phosphotransferases APH(6)-Id and APH(3″-Ib) are the principal drivers of streptomycin resistance in this important ecosystem. IMPORTANCE Antimicrobial resistance (AMR) represents an existential threat to the function of modern medicine. Genomics and machine learning methods are being increasingly used to analyze and predict AMR. This type of surveillance is very important to try to reduce the impact of AMR. Machine learning models are typically trained using genomic data, but the aspects of the genomes that they use to make predictions are rarely analyzed. In this work, we showed how, by using different types of machine learning models and performing this analysis, it is possible to identify the key genes underlying AMR in nontyphoidal Salmonella (NTS). NTS is among the leading cause of foodborne illness globally; however, AMR in NTS has not been heavily studied within the food chain itself. Therefore, in this work we performed a broad-scale analysis of the AMR in NTS isolates from commercial chicken farms and identified some priority AMR genes for surveillance.

scholarly journals Rainfall Prediction for Udaipur, Rajasthan using Machine Learning Models Based on Temperature, Vapour Pressure and Relative Humidity

2020 ◽  
Vol 8 (6S) ◽  
pp. 133-137
Keyword(s):  
Machine Learning ◽  
Relative Humidity ◽  
Vapour Pressure ◽  
Predictor Variables ◽  
Ensemble Model ◽  
Learning Models ◽  
Rainfall Prediction ◽  
Predictor Importance ◽  
The Impact ◽  
Machine Learning Models

The study aims at Rainfall prediction using Machine Learning models using the minimum of features. The prediction here is based on temperature, vapour pressure and relative humidity. Numerous studies carried out earlier used more features than this study. A training-test split of 75-25 was used. The best results were obtained by combining the best of the candidate models into an ensemble model to identify that predictor importance of vapour pressure was 0.89 while that of relative humidity was 0.11 with temperature not seen as a significant predictor for rainfall though the high correlation of temperature (°C) with vapour pressure (Torr) and relative humidity (Percentage) suggests that the two predictor variables subsume the impact of temperature.

THE IMPACT OF ARTIFICIAL NEURAL NETWORK’S STRUCTURE ON ITS EFFICIENCY FOR FINANCIAL INDICATORS FORECASTING

2021 ◽  
Vol 2 (28) ◽  
pp. 44-51
Author(s):  
B. S. Ermakov ◽  
Keyword(s):  
Machine Learning ◽  
The Other ◽  
Financial Indicators ◽  
Test Results ◽  
Learning Models ◽  
Multiple Tests ◽  
Artificial Neural ◽  
The Impact ◽  
Overfitting Problem ◽  
Machine Learning Models

The article investigates the influence of artificial neural network’s structure on the results, with example of multlayer perceptron for forecasting some of the financial indicators. Multiple tests were made with various networks structures: different numbers of hidden layers and different numbers of neurons in these layers. Based on tests results, the increase of network’s size is effective to a certain extent, but at some point the further size increase is unreasonable. Also, the test results demonstrate that overfitting problem for multilayer perceptron is not as crucial as for the other machine learning models, such as regression. Key words: artificial neural networks, forecasting, multlayer perceptron, overfitting, artificial neural netwok’s size.

Systematic Review of Approaches to Preserve Machine Learning Performance in the Presence of Temporal Dataset Shift in Clinical Medicine

2021 ◽  
Vol 12 (04) ◽  
pp. 808-815
Author(s):  
Lin Lawrence Guo ◽  
Stephen R. Pfohl ◽  
Jason Fries ◽  
Jose Posada ◽  
Scott Lanyon Fleming ◽  
...  
Keyword(s):  
Machine Learning ◽  
Decision Making ◽  
Clinical Decision Making ◽  
Clinical Medicine ◽  
Mitigation Strategies ◽  
Learning Performance ◽  
Learning Models ◽  
Dataset Shift ◽  
The Impact ◽  
Machine Learning Models

Abstract Objective The change in performance of machine learning models over time as a result of temporal dataset shift is a barrier to machine learning-derived models facilitating decision-making in clinical practice. Our aim was to describe technical procedures used to preserve the performance of machine learning models in the presence of temporal dataset shifts. Methods Studies were included if they were fully published articles that used machine learning and implemented a procedure to mitigate the effects of temporal dataset shift in a clinical setting. We described how dataset shift was measured, the procedures used to preserve model performance, and their effects. Results Of 4,457 potentially relevant publications identified, 15 were included. The impact of temporal dataset shift was primarily quantified using changes, usually deterioration, in calibration or discrimination. Calibration deterioration was more common (n = 11) than discrimination deterioration (n = 3). Mitigation strategies were categorized as model level or feature level. Model-level approaches (n = 15) were more common than feature-level approaches (n = 2), with the most common approaches being model refitting (n = 12), probability calibration (n = 7), model updating (n = 6), and model selection (n = 6). In general, all mitigation strategies were successful at preserving calibration but not uniformly successful in preserving discrimination. Conclusion There was limited research in preserving the performance of machine learning models in the presence of temporal dataset shift in clinical medicine. Future research could focus on the impact of dataset shift on clinical decision making, benchmark the mitigation strategies on a wider range of datasets and tasks, and identify optimal strategies for specific settings.

scholarly journals Detection and Evaluation of Machine Learning Bias

2021 ◽  
Vol 11 (14) ◽  
pp. 6271
Author(s):  
Salem Alelyani
Keyword(s):  
Machine Learning ◽  
Cognitive Bias ◽  
Research Community ◽  
Training Data ◽  
Learning Models ◽  
Open Research ◽  
Research Questions ◽  
And Behavior ◽  
The Impact ◽  
Machine Learning Models

Machine learning models are built using training data, which is collected from human experience and is prone to bias. Humans demonstrate a cognitive bias in their thinking and behavior, which is ultimately reflected in the collected data. From Amazon’s hiring system, which was built using ten years of human hiring experience, to a judicial system that was trained using human judging practices, these systems all include some element of bias. The best machine learning models are said to mimic humans’ cognitive ability, and thus such models are also inclined towards bias. However, detecting and evaluating bias is a very important step for better explainable models. In this work, we aim to explain bias in learning models in relation to humans’ cognitive bias and propose a wrapper technique to detect and evaluate bias in machine learning models using an openly accessible dataset from UCI Machine Learning Repository. In the deployed dataset, the potentially biased attributes (PBAs) are gender and race. This study introduces the concept of alternation functions to swap the values of PBAs, and evaluates the impact on prediction using KL divergence. Results demonstrate females and Asians to be associated with low wages, placing some open research questions for the research community to ponder over.

scholarly journals The Future of PHM Could be Tiny under Cloud: Exploring Potential Application Patterns of TinyML in PHM Scenarios

2021 ◽  
Vol 13 (1) ◽  
Author(s):  
Xingyu Zhou ◽  
Zhuangwei Kang ◽  
Robert Canady ◽  
Shunxing Bao ◽  
Daniel Allen Balasubramanian ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Remaining Useful Life ◽  
Data Driven ◽  
Learning Models ◽  
Level Data ◽  
Data Source ◽  
Single Data ◽  
The Impact ◽  
Machine Learning Models

Deep learning has shown impressive performance acrosshealth management and prognostics applications. Nowadays, an emerging trend of machine learning deployment on resource constraint hardware devices like micro-controllers(MCU) has aroused much attention. Given the distributed andresource constraint nature of many PHM applications, using tiny machine learning models close to data source sensors for on-device inferences would be beneficial to save both time andadditional hardware resources. Even though there has beenpast works that bring TinyML on MCUs for some PHM ap-plications, they are mainly targeting single data source usage without higher-level data incorporation with cloud computing.We study the impact of potential cooperation patterns betweenTinyML on edge and more powerful computation resources oncloud and how this would make an impact on the application patterns in data-driven prognostics. We introduce potential ap-plications where sensor readings are utilized for system health status prediction including status classification and remaining useful life regression. We find that MCUs and cloud com-puting can be adaptive to different kinds of machine learning models and combined in flexible ways for diverse requirement.Our work also shows limitations of current MCU-based deep learning in data-driven prognostics And we hope our work can

scholarly journals Influence of social determinants of health and county vaccination rates on machine learning models to predict COVID-19 case growth in Tennessee

2021 ◽  
Author(s):  
Lukasz S Wylezinski ◽  
Coleman R Harris ◽  
Cody N Heiser ◽  
Jamieson D Gray ◽  
Charles F Spurlock
Keyword(s):  
Machine Learning ◽  
Risk Factors ◽  
Social Determinants Of Health ◽  
Social Determinants ◽  
The United States ◽  
Determinants Of Health ◽  
Learning Models ◽  
Vaccination Rates ◽  
The Impact ◽  
Machine Learning Models

The SARS-CoV-2 (COVID-19) pandemic has exposed health disparities throughout the United States, particularly among racial and ethnic minorities. As a result, there is a need for data-driven approaches to pinpoint the unique constellation of clinical and social determinants of health (SDOH) risk factors that give rise to poor patient outcomes following infection in US communities. We combined county-level COVID-19 testing data, COVID-19 vaccination rates, and SDOH information in Tennessee. Between February-May 2021, we trained machine learning models on a semi-monthly basis using these datasets to predict COVID-19 incidence in Tennessee counties. We then analyzed SDOH data features at each time point to rank the impact of each feature on model performance. Our results indicate that COVID-19 vaccination rates play a crucial role in determining future COVID-19 disease risk. Beginning in mid-March 2021, higher vaccination rates significantly correlated with lower COVID-19 case growth predictions. Further, as the relative importance of COVID-19 vaccination data features grew, demographic SDOH features such as age, race, and ethnicity decreased while the impact of socioeconomic and environmental factors, including access to healthcare and transportation, increased. Incorporating a data framework to track the evolving patterns of community-level SDOH risk factors could provide policymakers with additional data resources to improve health equity and resilience to future public health emergencies.

scholarly journals A general method for estimating the prevalence of influenza-like-symptoms with Wikipedia data

PLoS ONE ◽  
2021 ◽  
Vol 16 (8) ◽  
pp. e0256858
Author(s):  
Giovanni De Toni ◽  
Cristian Consonni ◽  
Alberto Montresor
Keyword(s):  
Machine Learning ◽  
The Netherlands ◽  
State Of The Art ◽  
Data Sources ◽  
Learning Models ◽  
Personalized Pagerank ◽  
Web Searches ◽  
The Impact ◽  
Machine Learning Models ◽  
General Method

Influenza is an acute respiratory seasonal disease that affects millions of people worldwide and causes thousands of deaths in Europe alone. Estimating in a fast and reliable way the impact of an illness on a given country is essential to plan and organize effective countermeasures, which is now possible by leveraging unconventional data sources like web searches and visits. In this study, we show the feasibility of exploiting machine learning models and information about Wikipedia’s page views of a selected group of articles to obtain accurate estimates of influenza-like illnesses incidence in four European countries: Italy, Germany, Belgium, and the Netherlands. We propose a novel language-agnostic method, based on two algorithms, Personalized PageRank and CycleRank, to automatically select the most relevant Wikipedia pages to be monitored without the need for expert supervision. We then show how our model can reach state-of-the-art results by comparing it with previous solutions.

Sign in / Sign up

Export Citation Format

Share Document