Vivek Kumar Singh1, Utkarsh Shrivastava2, Lina Bouayad3,4, Balaji Padmanabhan1, Anna Ialynytchev4, Susan K Schultz5,6. 1. Information Systems and Decision Sciences, MUMA College of Business, University of South Florida, Tampa, Florida, USA. 2. Haworth College of Business, Department of Business Information Systems, Western Michigan University, Kalamazoo, Michigan, USA. 3. College of Business, Information Systems and Business Analytics, Florida International University, Miami, Florida, USA. 4. HSR&D Center of Innovation on Disability and Rehabilitation Research (CINDRR), James A. Haley Veterans Hospital, Tampa, Florida, USA. 5. James A. Haley Veterans Hospital, Geriatric Psychiatry, Tampa, Florida, USA. 6. Department of Psychiatry and Behavioral Neurosciences, Morsani College of Medicine, University of South Florida, Tampa, Florida, USA.
Abstract
Objective: Develop an approach, One-class-at-a-time, for triaging psychiatric patients using machine learning on textual patient records. Our approach aims to automate the triaging process and reduce expert effort while providing high classification reliability. Materials and Methods: The One-class-at-a-time approach is a multistage cascading classification technique that achieves higher triage classification accuracy compared to traditional multiclass classifiers through 1) classifying one class at a time (or stage), and 2) identification and application of the highest accuracy classifier at each stage. The approach was evaluated using a unique dataset of 433 psychiatric patient records with a triage class label provided by "I2B2 challenge," a recent competition in the medical informatics community. Results: The One-class-at-a-time cascading classifier outperformed state-of-the-art classification techniques with overall classification accuracy of 77% among 4 classes, exceeding accuracies of existing multiclass classifiers. The approach also enabled highly accurate classification of individual classes-the severe and mild with 85% accuracy, moderate with 64% accuracy, and absent with 60% accuracy. Discussion: The triaging of psychiatric cases is a challenging problem due to the lack of clear guidelines and protocols. Our work presents a machine learning approach using psychiatric records for triaging patients based on their severity condition. Conclusion: The One-class-at-a-time cascading classifier can be used as a decision aid to reduce triaging effort of physicians and nurses, while providing a unique opportunity to involve experts at each stage to reduce false positive and further improve the system's accuracy.
Objective: Develop an approach, One-class-at-a-time, for triaging psychiatricpatients using machine learning on textual patient records. Our approach aims to automate the triaging process and reduce expert effort while providing high classification reliability. Materials and Methods: The One-class-at-a-time approach is a multistage cascading classification technique that achieves higher triage classification accuracy compared to traditional multiclass classifiers through 1) classifying one class at a time (or stage), and 2) identification and application of the highest accuracy classifier at each stage. The approach was evaluated using a unique dataset of 433 psychiatricpatient records with a triage class label provided by "I2B2 challenge," a recent competition in the medical informatics community. Results: The One-class-at-a-time cascading classifier outperformed state-of-the-art classification techniques with overall classification accuracy of 77% among 4 classes, exceeding accuracies of existing multiclass classifiers. The approach also enabled highly accurate classification of individual classes-the severe and mild with 85% accuracy, moderate with 64% accuracy, and absent with 60% accuracy. Discussion: The triaging of psychiatric cases is a challenging problem due to the lack of clear guidelines and protocols. Our work presents a machine learning approach using psychiatric records for triaging patients based on their severity condition. Conclusion: The One-class-at-a-time cascading classifier can be used as a decision aid to reduce triaging effort of physicians and nurses, while providing a unique opportunity to involve experts at each stage to reduce false positive and further improve the system's accuracy.
Authors: Yindalon Aphinyanaphongs; Ioannis Tsamardinos; Alexander Statnikov; Douglas Hardin; Constantin F Aliferis Journal: J Am Med Inform Assoc Date: 2004-11-23 Impact factor: 4.497
Authors: Craig D Newgard; Kristan Staudenmayer; Renee Y Hsia; N Clay Mann; Eileen M Bulger; James F Holmes; Ross Fleischman; Kyle Gorman; Jason Haukoos; K John McConnell Journal: Health Aff (Millwood) Date: 2013-09 Impact factor: 6.301
Authors: Xiongcai Cai; Oscar Perez-Concha; Enrico Coiera; Fernando Martin-Sanchez; Richard Day; David Roffe; Blanca Gallego Journal: J Am Med Inform Assoc Date: 2015-09-15 Impact factor: 4.497
Authors: Nasim Farrohknia; Maaret Castrén; Anna Ehrenberg; Lars Lind; Sven Oredsson; Håkan Jonsson; Kjell Asplund; Katarina E Göransson Journal: Scand J Trauma Resusc Emerg Med Date: 2011-06-30 Impact factor: 2.953