Prediction of hospital-onset COVID-19 using networks of patient contact: an observational study
Purpose: Predicting healthcare-acquired infections (HAIs) has the potential to revolutionise the prevention and control of transmissible infections. Existing prediction models for HAIs, however, fail to capture fully the contact-driven nature of infectious diseases. Here, we investigate the epidemio...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-03-01
|
| Series: | International Journal of Infectious Diseases |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1201971221011504 |
| _version_ | 1819107710114725888 |
|---|---|
| author | A. Myall J. Price R. Peach M. Abbas S. Mookerjee I. Ahmad D. Ming N.J. Zhu F. Ramzan A. Weisse A.H. Holmes M. Barahona |
| author_facet | A. Myall J. Price R. Peach M. Abbas S. Mookerjee I. Ahmad D. Ming N.J. Zhu F. Ramzan A. Weisse A.H. Holmes M. Barahona |
| author_sort | A. Myall |
| collection | DOAJ |
| description | Purpose: Predicting healthcare-acquired infections (HAIs) has the potential to revolutionise the prevention and control of transmissible infections. Existing prediction models for HAIs, however, fail to capture fully the contact-driven nature of infectious diseases. Here, we investigate the epidemiological predictivity of patient contact patterns through a forecasting model for hospital-onset COVID-19 infection (HOCI). Methods & Materials: Our cohort comprises all patient admissions at a large London NHS Trust between 1/04/2020 and 1/04/2021. For patients, we consider (i) their hospital pathway, (ii) patient contacts, and (iii) date of COVID-19 infection. We consider rolling 14-day windows and forecast patient infection over the subsequent 7 days. Over each window, we construct a patient contact network and compute network features that capture contact centrality. We then combine network features, hospital environmental variables and patient clinical data to predict subsequent infections. Results: A total of 51,157 patient admissions/episodes were observed during the study. Across all models, we find that contact-network features showed the highest performance (0.91 AUC-ROC). A reduced model with the six most predictive variables was almost as predictive and contained five features from patient contact (including direct contact with and network proximity to infectious cases) and only one environmental variable (length of stay). Conclusion: Our results reveal that the number of direct contacts and network proximity to infectious patient(s) are highly predictive of HOCI. Such contact-based risk factors are easily extracted from routinely collected electronic health records providing a highly accessible route to improve personalised disease prognostics in future models. |
| first_indexed | 2024-12-22T02:58:21Z |
| format | Article |
| id | doaj.art-d355291b5e8245068934336ff508a673 |
| institution | Directory Open Access Journal |
| issn | 1201-9712 |
| language | English |
| last_indexed | 2024-12-22T02:58:21Z |
| publishDate | 2022-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Journal of Infectious Diseases |
| spelling | doaj.art-d355291b5e8245068934336ff508a6732022-12-21T18:41:14ZengElsevierInternational Journal of Infectious Diseases1201-97122022-03-01116S109S110Prediction of hospital-onset COVID-19 using networks of patient contact: an observational studyA. Myall0J. Price1R. Peach2M. Abbas3S. Mookerjee4I. Ahmad5D. Ming6N.J. Zhu7F. Ramzan8A. Weisse9A.H. Holmes10M. Barahona11Imperial College London, London, United Kingdom; Corresponding author.Imperial College Healthcare NHS Trust, London, United KingdomImperial College London, London, United KingdomImperial College London, London, United KingdomImperial College Healthcare NHS Trust, London, United KingdomImperial College London, London, United KingdomImperial College Healthcare NHS Trust, London, United KingdomImperial College London, London, United KingdomImperial College London, London, United KingdomThe University of Edinburgh, Edinburgh, United KingdomImperial College London, London, United Kingdom; Imperial College Healthcare NHS Trust, London, United KingdomImperial College London, London, United KingdomPurpose: Predicting healthcare-acquired infections (HAIs) has the potential to revolutionise the prevention and control of transmissible infections. Existing prediction models for HAIs, however, fail to capture fully the contact-driven nature of infectious diseases. Here, we investigate the epidemiological predictivity of patient contact patterns through a forecasting model for hospital-onset COVID-19 infection (HOCI). Methods & Materials: Our cohort comprises all patient admissions at a large London NHS Trust between 1/04/2020 and 1/04/2021. For patients, we consider (i) their hospital pathway, (ii) patient contacts, and (iii) date of COVID-19 infection. We consider rolling 14-day windows and forecast patient infection over the subsequent 7 days. Over each window, we construct a patient contact network and compute network features that capture contact centrality. We then combine network features, hospital environmental variables and patient clinical data to predict subsequent infections. Results: A total of 51,157 patient admissions/episodes were observed during the study. Across all models, we find that contact-network features showed the highest performance (0.91 AUC-ROC). A reduced model with the six most predictive variables was almost as predictive and contained five features from patient contact (including direct contact with and network proximity to infectious cases) and only one environmental variable (length of stay). Conclusion: Our results reveal that the number of direct contacts and network proximity to infectious patient(s) are highly predictive of HOCI. Such contact-based risk factors are easily extracted from routinely collected electronic health records providing a highly accessible route to improve personalised disease prognostics in future models.http://www.sciencedirect.com/science/article/pii/S1201971221011504 |
| spellingShingle | A. Myall J. Price R. Peach M. Abbas S. Mookerjee I. Ahmad D. Ming N.J. Zhu F. Ramzan A. Weisse A.H. Holmes M. Barahona Prediction of hospital-onset COVID-19 using networks of patient contact: an observational study International Journal of Infectious Diseases |
| title | Prediction of hospital-onset COVID-19 using networks of patient contact: an observational study |
| title_full | Prediction of hospital-onset COVID-19 using networks of patient contact: an observational study |
| title_fullStr | Prediction of hospital-onset COVID-19 using networks of patient contact: an observational study |
| title_full_unstemmed | Prediction of hospital-onset COVID-19 using networks of patient contact: an observational study |
| title_short | Prediction of hospital-onset COVID-19 using networks of patient contact: an observational study |
| title_sort | prediction of hospital onset covid 19 using networks of patient contact an observational study |
| url | http://www.sciencedirect.com/science/article/pii/S1201971221011504 |
| work_keys_str_mv | AT amyall predictionofhospitalonsetcovid19usingnetworksofpatientcontactanobservationalstudy AT jprice predictionofhospitalonsetcovid19usingnetworksofpatientcontactanobservationalstudy AT rpeach predictionofhospitalonsetcovid19usingnetworksofpatientcontactanobservationalstudy AT mabbas predictionofhospitalonsetcovid19usingnetworksofpatientcontactanobservationalstudy AT smookerjee predictionofhospitalonsetcovid19usingnetworksofpatientcontactanobservationalstudy AT iahmad predictionofhospitalonsetcovid19usingnetworksofpatientcontactanobservationalstudy AT dming predictionofhospitalonsetcovid19usingnetworksofpatientcontactanobservationalstudy AT njzhu predictionofhospitalonsetcovid19usingnetworksofpatientcontactanobservationalstudy AT framzan predictionofhospitalonsetcovid19usingnetworksofpatientcontactanobservationalstudy AT aweisse predictionofhospitalonsetcovid19usingnetworksofpatientcontactanobservationalstudy AT ahholmes predictionofhospitalonsetcovid19usingnetworksofpatientcontactanobservationalstudy AT mbarahona predictionofhospitalonsetcovid19usingnetworksofpatientcontactanobservationalstudy |