A Digital Twins Machine Learning Model for Forecasting Disease Progression in Stroke Patients
Background: Machine learning methods have been developed to predict the likelihood of a given event or classify patients into two or more diagnostic categories. Digital twin models, which forecast entire trajectories of patient health data, have potential applications in clinical trials and patient...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-06-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/12/5576 |
| _version_ | 1827689551748923392 |
|---|---|
| author | Angier Allen Anna Siefkas Emily Pellegrini Hoyt Burdick Gina Barnes Jacob Calvert Qingqing Mao Ritankar Das |
| author_facet | Angier Allen Anna Siefkas Emily Pellegrini Hoyt Burdick Gina Barnes Jacob Calvert Qingqing Mao Ritankar Das |
| author_sort | Angier Allen |
| collection | DOAJ |
| description | Background: Machine learning methods have been developed to predict the likelihood of a given event or classify patients into two or more diagnostic categories. Digital twin models, which forecast entire trajectories of patient health data, have potential applications in clinical trials and patient management. Methods: In this study, we apply a digital twin model based on a variational autoencoder to a population of patients who went on to experience an ischemic stroke. The digital twin’s ability to model patient clinical features was assessed with regard to its ability to forecast clinical measurement trajectories leading up to the onset of the acute medical event and beyond using International Classification of Diseases (ICD) codes for ischemic stroke and lab values as inputs. Results: The simulated patient trajectories were virtually indistinguishable from real patient data, with similar feature means, standard deviations, inter-feature correlations, and covariance structures on a withheld test set. A logistic regression adversary model was unable to distinguish between the real and simulated data area under the receiver operating characteristic (ROC) curve (AUC<sub>adversary</sub> = 0.51). Conclusion: Through accurate projection of patient trajectories, this model may help inform clinical decision making or provide virtual control arms for efficient clinical trials. |
| first_indexed | 2024-03-10T10:21:14Z |
| format | Article |
| id | doaj.art-2ddb76822b384f9e8266af3c6f174d41 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T10:21:14Z |
| publishDate | 2021-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-2ddb76822b384f9e8266af3c6f174d412023-11-22T00:23:13ZengMDPI AGApplied Sciences2076-34172021-06-011112557610.3390/app11125576A Digital Twins Machine Learning Model for Forecasting Disease Progression in Stroke PatientsAngier Allen0Anna Siefkas1Emily Pellegrini2Hoyt Burdick3Gina Barnes4Jacob Calvert5Qingqing Mao6Ritankar Das7Dascena, Inc., 12333 Sowden Rd Ste B PMB 65148, Houston, TX 77080, USADascena, Inc., 12333 Sowden Rd Ste B PMB 65148, Houston, TX 77080, USADascena, Inc., 12333 Sowden Rd Ste B PMB 65148, Houston, TX 77080, USACabell Huntington Hospital, 1340 Hal Greer Boulevard, Huntington, WV 25701, USADascena, Inc., 12333 Sowden Rd Ste B PMB 65148, Houston, TX 77080, USADascena, Inc., 12333 Sowden Rd Ste B PMB 65148, Houston, TX 77080, USADascena, Inc., 12333 Sowden Rd Ste B PMB 65148, Houston, TX 77080, USADascena, Inc., 12333 Sowden Rd Ste B PMB 65148, Houston, TX 77080, USABackground: Machine learning methods have been developed to predict the likelihood of a given event or classify patients into two or more diagnostic categories. Digital twin models, which forecast entire trajectories of patient health data, have potential applications in clinical trials and patient management. Methods: In this study, we apply a digital twin model based on a variational autoencoder to a population of patients who went on to experience an ischemic stroke. The digital twin’s ability to model patient clinical features was assessed with regard to its ability to forecast clinical measurement trajectories leading up to the onset of the acute medical event and beyond using International Classification of Diseases (ICD) codes for ischemic stroke and lab values as inputs. Results: The simulated patient trajectories were virtually indistinguishable from real patient data, with similar feature means, standard deviations, inter-feature correlations, and covariance structures on a withheld test set. A logistic regression adversary model was unable to distinguish between the real and simulated data area under the receiver operating characteristic (ROC) curve (AUC<sub>adversary</sub> = 0.51). Conclusion: Through accurate projection of patient trajectories, this model may help inform clinical decision making or provide virtual control arms for efficient clinical trials.https://www.mdpi.com/2076-3417/11/12/5576digital twinsvariational autoencodermachine learningalgorithmstrokedisease forecasting |
| spellingShingle | Angier Allen Anna Siefkas Emily Pellegrini Hoyt Burdick Gina Barnes Jacob Calvert Qingqing Mao Ritankar Das A Digital Twins Machine Learning Model for Forecasting Disease Progression in Stroke Patients Applied Sciences digital twins variational autoencoder machine learning algorithm stroke disease forecasting |
| title | A Digital Twins Machine Learning Model for Forecasting Disease Progression in Stroke Patients |
| title_full | A Digital Twins Machine Learning Model for Forecasting Disease Progression in Stroke Patients |
| title_fullStr | A Digital Twins Machine Learning Model for Forecasting Disease Progression in Stroke Patients |
| title_full_unstemmed | A Digital Twins Machine Learning Model for Forecasting Disease Progression in Stroke Patients |
| title_short | A Digital Twins Machine Learning Model for Forecasting Disease Progression in Stroke Patients |
| title_sort | digital twins machine learning model for forecasting disease progression in stroke patients |
| topic | digital twins variational autoencoder machine learning algorithm stroke disease forecasting |
| url | https://www.mdpi.com/2076-3417/11/12/5576 |
| work_keys_str_mv | AT angierallen adigitaltwinsmachinelearningmodelforforecastingdiseaseprogressioninstrokepatients AT annasiefkas adigitaltwinsmachinelearningmodelforforecastingdiseaseprogressioninstrokepatients AT emilypellegrini adigitaltwinsmachinelearningmodelforforecastingdiseaseprogressioninstrokepatients AT hoytburdick adigitaltwinsmachinelearningmodelforforecastingdiseaseprogressioninstrokepatients AT ginabarnes adigitaltwinsmachinelearningmodelforforecastingdiseaseprogressioninstrokepatients AT jacobcalvert adigitaltwinsmachinelearningmodelforforecastingdiseaseprogressioninstrokepatients AT qingqingmao adigitaltwinsmachinelearningmodelforforecastingdiseaseprogressioninstrokepatients AT ritankardas adigitaltwinsmachinelearningmodelforforecastingdiseaseprogressioninstrokepatients AT angierallen digitaltwinsmachinelearningmodelforforecastingdiseaseprogressioninstrokepatients AT annasiefkas digitaltwinsmachinelearningmodelforforecastingdiseaseprogressioninstrokepatients AT emilypellegrini digitaltwinsmachinelearningmodelforforecastingdiseaseprogressioninstrokepatients AT hoytburdick digitaltwinsmachinelearningmodelforforecastingdiseaseprogressioninstrokepatients AT ginabarnes digitaltwinsmachinelearningmodelforforecastingdiseaseprogressioninstrokepatients AT jacobcalvert digitaltwinsmachinelearningmodelforforecastingdiseaseprogressioninstrokepatients AT qingqingmao digitaltwinsmachinelearningmodelforforecastingdiseaseprogressioninstrokepatients AT ritankardas digitaltwinsmachinelearningmodelforforecastingdiseaseprogressioninstrokepatients |