Difference between revisions of "Medical decision support using machine learning for early detection of late onset neonatal sepsis"
(→Reference) |
|||
| Line 1: | Line 1: | ||
Creating Medical decision support using machine learning for early detection of late onset [https://www.nlm.nih.gov/medlineplus/ency/article/007303.htm/ neonatal sepsis] <ref name ="Mani">Mani, S., Ozdas, A., Aliferis, C., Varol, H. A., Chen, Q., Carnevale, R., ... & Weitkamp, J. H. (2014). Medical decision support using machine learning for early detection of late-onset neonatal sepsis. Journal of the American Medical Informatics Association, 21(2), 326-336. http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3932458/pdf/amiajnl-2013-001854.pdf </ref> | Creating Medical decision support using machine learning for early detection of late onset [https://www.nlm.nih.gov/medlineplus/ency/article/007303.htm/ neonatal sepsis] <ref name ="Mani">Mani, S., Ozdas, A., Aliferis, C., Varol, H. A., Chen, Q., Carnevale, R., ... & Weitkamp, J. H. (2014). Medical decision support using machine learning for early detection of late-onset neonatal sepsis. Journal of the American Medical Informatics Association, 21(2), 326-336. http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3932458/pdf/amiajnl-2013-001854.pdf </ref> | ||
| − | ==Abstract== | + | ===Abstract=== |
The objective for the study was to develop models for late-onset for neonatal sepsis. This study used machine learning (ML) which is a subfield in the artificial intelligence. Earlier work showed feasibility of building predictive models with clinical potential. | The objective for the study was to develop models for late-onset for neonatal sepsis. This study used machine learning (ML) which is a subfield in the artificial intelligence. Earlier work showed feasibility of building predictive models with clinical potential. | ||
| − | ==Design== | + | ===Design=== |
299 Infants admitted to neonatal intensive care unit in the Monroe Carell JR. Childrens hosptial at Vanderbilt | 299 Infants admitted to neonatal intensive care unit in the Monroe Carell JR. Childrens hosptial at Vanderbilt | ||
Developed Nine Machine Learning (ML) algorithms | Developed Nine Machine Learning (ML) algorithms | ||
| Line 14: | Line 14: | ||
Definition of late onset was defined as neonatal sepsis occurring over 72 hours after birth. | Definition of late onset was defined as neonatal sepsis occurring over 72 hours after birth. | ||
| − | ==Measurement== | + | ===Measurement=== |
Compared blood work | Compared blood work | ||
#sensitivity | #sensitivity | ||
| Line 21: | Line 21: | ||
#negative value | #negative value | ||
| − | ==Results== | + | ===Results=== |
Treatment sensitivity | Treatment sensitivity | ||
| Line 30: | Line 30: | ||
| − | ==Conclusion== | + | ===Conclusion=== |
The study showed that with the use of the [[EHR | electronic health record (EHR)]] and the machine learning (ML) algorithms exceeds the sensitivity and specificity of clinicians. | The study showed that with the use of the [[EHR | electronic health record (EHR)]] and the machine learning (ML) algorithms exceeds the sensitivity and specificity of clinicians. | ||
Revision as of 00:45, 11 November 2015
Creating Medical decision support using machine learning for early detection of late onset neonatal sepsis [1]
Contents
Abstract
The objective for the study was to develop models for late-onset for neonatal sepsis. This study used machine learning (ML) which is a subfield in the artificial intelligence. Earlier work showed feasibility of building predictive models with clinical potential.
Design
299 Infants admitted to neonatal intensive care unit in the Monroe Carell JR. Childrens hosptial at Vanderbilt Developed Nine Machine Learning (ML) algorithms
- Study of 18 month period
- Data
1826 total admission and sample size was 299.
Definition of late onset was defined as neonatal sepsis occurring over 72 hours after birth.
Measurement
Compared blood work
- sensitivity
- specificity
- Positive value
- negative value
Results
Treatment sensitivity
- Top three predictive variables
- hemotocrit
- packed cell volume
- Chorioamnionitis and Respiratory reate
Conclusion
The study showed that with the use of the electronic health record (EHR) and the machine learning (ML) algorithms exceeds the sensitivity and specificity of clinicians.
Related Concepts
Natural language processing (NLP)
Related Articles
Visualizing unstructured patient data for assessing diagnostic and therapeutic history
Reference
- ↑ Mani, S., Ozdas, A., Aliferis, C., Varol, H. A., Chen, Q., Carnevale, R., ... & Weitkamp, J. H. (2014). Medical decision support using machine learning for early detection of late-onset neonatal sepsis. Journal of the American Medical Informatics Association, 21(2), 326-336. http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3932458/pdf/amiajnl-2013-001854.pdf
