Machine Learning Algorithms Can Use Wearable Sensor Data to Accurately Predict Six-Week Patient-Reported Outcome Scores Following Joint Replacement in a Prospective Trial

2019 ◽  
Vol 34 (10) ◽  
pp. 2242-2247 ◽  
Author(s):  
Stefano A. Bini ◽  
Romil F. Shah ◽  
Ilya Bendich ◽  
Joseph T. Patterson ◽  
Kevin M. Hwang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Joint Replacement ◽  
Learning Algorithms ◽  
Prospective Trial ◽  
Patient Reported Outcome ◽  
Machine Learning Algorithms ◽  
Sensor Data ◽  
Wearable Sensor ◽  
Patient Reported ◽  
Outcome Scores

Predicting 180-day mortality for women with ovarian cancer using machine learning and patient-reported outcome data.

2021 ◽  
Vol 39 (15_suppl) ◽  
pp. e13555-e13555
Author(s):  
Chris Sidey-Gibbons ◽  
Charlotte C. Sun ◽  
Cai Xu ◽  
Amy Schneider ◽  
Sheng-Chieh Lu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Ovarian Cancer ◽  
End Of Life ◽  
Learning Algorithms ◽  
The United States ◽  
Patient Reported Outcome ◽  
Machine Learning Algorithms ◽  
Electronic Health Record Data ◽  
Testing Dataset ◽  
Patient Reported

e13555 Background: Contra to national guidelines, women with ovarian cancer often receive aggressive treatment until the end-of-life. We trained machine learning algorithms to predict mortality within 180 days for women with ovarian cancer. Methods: Data were collected data from a single academic cancer institution in the United States. Women with recurrent ovarian cancer completed biopsychosocial patient-reported outcome measures (PROMs) every 90 days. We randomly partitioned our dataset into training and testing samples with a 2:1 ratio. We used synthetic minority oversampling to reduce class imbalance in the training dataset. We fitted training data to six machine learning algorithms and combined their classifications on the testing dataset into a voting ensemble. We assessed the accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUROC) for each algorithm. Results: We recruited 245 patients who completed 1319 assessments. The final voting ensemble performed well across all performance metrics (Accuracy = .79, Sensitivity = .71, Specificity = .80, AUROC = .76). The algorithm correctly identified 25 of the 35 women in the testing dataset who died within 180 days of assessment Conclusions: Machine learning algorithms trained using PROM data offer state-of-the-art performance in predicting whether a woman with ovarian cancer will reach the end-of-life within 180 days. We highlight the importance of PROM data in ML models of mortality. Our model exhibits substantial improvements in prediction sensitivity compared to other similar models trained using electronic health record data alone. This model could inform clinical decision making and improve the uptake of appropriate end-of-life care. Further research is warranted to expand on these findings in a larger, more diverse sample.

scholarly journals Predicting Obstetric Disease With Machine Learning Applied to Patient-Reported Data (Preprint)

2018 ◽  
Author(s):  
Danielle Bradley ◽  
Erin Landau ◽  
Adam Wolfberg ◽  
Alex Baron
Keyword(s):  
Machine Learning ◽  
At Risk ◽  
Mobile Apps ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Supervised Machine Learning ◽  
Obstetric Outcomes ◽  
Patient Reported ◽  
Data Points ◽  
Reported Data

BACKGROUND The rise of highly engaging digital health mobile apps over the past few years has created repositories containing billions of patient-reported data points that have the potential to inform clinical research and advance medicine. OBJECTIVE To determine if self-reported data could be leveraged to create machine learning algorithms to predict the presence of, or risk for, obstetric outcomes and related conditions. METHODS More than 10 million women have downloaded Ovia Health’s three mobile apps (Ovia Fertility, Ovia Pregnancy, and Ovia Parenting). Data points logged by app users can include information about menstrual cycle, health history, current health status, nutrition habits, exercise activity, symptoms, or moods. Machine learning algorithms were developed using supervised machine learning methodologies, specifically, Gradient Boosting Decision Tree algorithms. Each algorithm was developed and trained using anywhere from 385 to 5770 features and data from 77,621 to 121,740 app users. RESULTS Algorithms were created to detect the risk of developing preeclampsia, gestational diabetes, and preterm delivery, as well as to identify the presence of existing preeclampsia. The positive predictive value (PPV) was set to 0.75 for all of the models, as this was the threshold where the researchers felt a clinical response—additional screening or testing—would be reasonable, due to the likelihood of a positive outcome. Sensitivity ranged from 24% to 75% across all models. When PPV was adjusted from 0.75 to 0.52, the sensitivity of the preeclampsia prediction algorithm rose from 24% to 85%. When PPV was adjusted from 0.75 to 0.65, the sensitivity of the preeclampsia detection or diagnostic algorithm increased from 37% to 79%. CONCLUSIONS Algorithms based on patient-reported data can predict serious obstetric conditions with accuracy levels sufficient to guide clinical screening by health care providers and health plans. Further research is needed to determine whether such an approach can improve outcomes for at-risk patients and reduce the cost of screening those not at risk. Presenting the results of these models to patients themselves could also provide important insight into otherwise unknown health risks.

Architecting IoT based Healthcare Systems Using Machine Learning Algorithms

2020 ◽  
pp. 40-66
Author(s):  
G. S. Karthick ◽  
P. B. Pankajavalli
Keyword(s):  
Machine Learning ◽  
Learning Algorithms ◽  
Healthcare Systems ◽  
Machine Learning Algorithms ◽  
Daily Activities ◽  
Sensor Data ◽  
Time Data ◽  
Sensory Data ◽  
Hybrid Classification ◽  
Smart Data

The rapid innovations in technologies endorsed the emergence of sensory equipment's connection to the Internet for acquiring data from the environment. The increased number of devices generates the enormous amount of sensor data from diversified applications of Internet of things (IoT). The generation of data may be a fast or real-time data stream which depends on the nature of applications. Applying analytics and intelligent processing over the data streams discovers the useful information and predicts the insights. Decision-making is a prominent process which makes the IoT paradigm qualified. This chapter provides an overview of architecting IoT-based healthcare systems with different machine learning algorithms. This chapter elaborates the smart data characteristics and design considerations for efficient adoption of machine learning algorithms into IoT applications. In addition, various existing and hybrid classification algorithms are applied to sensory data for identifying falls from other daily activities.

Anomaly Detection Using Temporal Data Mining in a Smart Home Environment

2008 ◽  
Vol 47 (01) ◽  
pp. 70-75 ◽  
Author(s):  
V. Jakkula ◽  
D. J. Cook
Keyword(s):  
Machine Learning ◽  
Smart Home ◽  
Learning Algorithms ◽  
Synthetic Data ◽  
Machine Learning Algorithms ◽  
Sensor Data ◽  
Temporal Data Mining ◽  
Activity Data ◽  
Real Activity ◽  
Smart Home Environment

Summary Objectives: To many people, home is a sanctuary. With the maturing of smart home technologies, many people with cognitive and physical disabilities can lead independent lives in their own homes for extended periods of time. In this paper, we investigate the design of machine learning algorithms that support this goal. We hypothesize that machine learning algorithms can be designed to automatically learn models of resident behavior in a smart home, and that the results can be used to perform automated health monitoring and to detect anomalies. Methods: Specifically, our algorithms draw upon the temporal nature of sensor data collected in a smart home to build a model of expected activities and to detect unexpected, and possibly health-critical, events in the home. Results: We validate our algorithms using synthetic data and real activity data collected from volunteers in an automated smart environment. Conclusions: The results from our experiments support our hypothesis that a model can be learned from observed smart home data and used to report anomalies, as they occur, in a smart home.

scholarly journals Classification of Children’s Sitting Postures Using Machine Learning Algorithms

2018 ◽  
Vol 8 (8) ◽  
pp. 1280 ◽  
Author(s):  
Yong Kim ◽  
Youngdoo Son ◽  
Wonjoon Kim ◽  
Byungki Jin ◽  
Myung Yun
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Monitoring System ◽  
Multinomial Logistic Regression ◽  
Learning Algorithms ◽  
Feedback System ◽  
Machine Learning Algorithms ◽  
Sensor Data ◽  
Future Research ◽  
Support Vector

Sitting on a chair in an awkward posture or sitting for a long period of time is a risk factor for musculoskeletal disorders. A postural habit that has been formed cannot be changed easily. It is important to form a proper postural habit from childhood as the lumbar disease during childhood caused by their improper posture is most likely to recur. Thus, there is a need for a monitoring system that classifies children’s sitting postures. The purpose of this paper is to develop a system for classifying sitting postures for children using machine learning algorithms. The convolutional neural network (CNN) algorithm was used in addition to the conventional algorithms: Naïve Bayes classifier (NB), decision tree (DT), neural network (NN), multinomial logistic regression (MLR), and support vector machine (SVM). To collect data for classifying sitting postures, a sensing cushion was developed by mounting a pressure sensor mat (8 × 8) inside children’s chair seat cushion. Ten children participated, and sensor data was collected by taking a static posture for the five prescribed postures. The accuracy of CNN was found to be the highest as compared with those of the other algorithms. It is expected that the comprehensive posture monitoring system would be established through future research on enhancing the classification algorithm and providing an effective feedback system.

Comparison of common machine learning algorithms trained with multi-zone models for identifying the location and strength of indoor pollutant sources

2020 ◽  
pp. 1420326X2093157
Author(s):  
Yu Huang ◽  
Zhi Gao ◽  
Hongguang Zhang
Keyword(s):  
Machine Learning ◽  
Meteorological Parameters ◽  
Human Life ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Identification Accuracy ◽  
Sensor Data ◽  
Support Vector ◽  
Accurate Identification ◽  
Pollutant Sources

The accurate identification of the characteristics of pollutant sources can effectively prevent the loss of human life and property damage caused by the sudden release of harmful chemicals in emergency situations. Machine learning algorithms, artificial neural network (ANN), support vector machine (SVM), k-nearest neighbour (KNN) and naive Bayesian (NB) classification can be used to identify the location of pollutant sources with limited sensor data inputs. In this study, the identification accuracy of the four above-mentioned machine learning algorithms was investigated and compared, considering the different sensor layouts, eigenvector inputs, meteorological parameters and number of samples. The results show that the collection of pollutant concentrations over an extended period of time could improve identification accuracy. Additional sensors were required to reach the same identification accuracy after the introduction of distributed meteorological parameters. Increasing the number of trained samples by a factor of five improved the identification accuracy of KNN by 22% and that of SVM by 1.7%; however, ANN and NB classification remained basically unchanged. When identifying the release mass of the pollutant source, multiple linear, ANN and SVM regression models were adopted. Results show that ANN performs best, whereas SVM provides the least optimal performance.

The Annotation of Global Positioning System (GPS) Data with Activity Purposes Using Multiple Machine Learning Algorithms

2014 ◽  
pp. 119-133 ◽  
Author(s):  
Sofie Reumers ◽  
Feng Liu ◽  
Davy Janssens ◽  
Geert Wets
Keyword(s):  
Machine Learning ◽  
Learning Algorithms ◽  
Detailed Comparison ◽  
Machine Learning Algorithms ◽  
Sensor Data ◽  
Personal Digital Assistants ◽  
Gps Data ◽  
Additional Costs ◽  
Simulation Systems ◽  
Type Information

The aim of this chapter is to evaluate whether GPS data can be annotated or semantically enriched with different activity categories, allowing GPS data to be used in the future in simulation systems. The data in the study stems from a paper-and-pencil activity-travel diary survey and a corresponding survey in which GPS-enabled Personal Digital Assistants (PDAs) were used. A set of new approaches, which are all independent of additional sensor data and map information, thus significantly reducing additional costs and making the set of techniques relatively easily transferable to other regions, are proposed. Furthermore, this chapter makes a detailed comparison of different machine learning algorithms to semantically enrich GPS data with activity type information.

Sign in / Sign up

Export Citation Format

Share Document