Web-Based Healthcare Delivery Integrated System to Forecast COVID-19 Hospitalizations in a Marginalized Patient Population: A Case Study in Broome County, New York
We developed a web-based integrated healthcare delivery system with a user-friendly interface to help forecast COVID-19 hospitalizations in a marginalized patient population. The user-friendly interface is a COVID-19 Hospitalizations Control Dashboard (HCD). This dashboard displays historical and pr...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-01-01
|
| Series: | Advances in Public Health |
| Online Access: | http://dx.doi.org/10.1155/2024/6644557 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832543766344368128 |
|---|---|
| author | Anemone Kasasbeh Elie Issa Naseem Khan Mehmet Yildirim Amy Booth Hiroki Sayama |
| author_facet | Anemone Kasasbeh Elie Issa Naseem Khan Mehmet Yildirim Amy Booth Hiroki Sayama |
| author_sort | Anemone Kasasbeh |
| collection | DOAJ |
| description | We developed a web-based integrated healthcare delivery system with a user-friendly interface to help forecast COVID-19 hospitalizations in a marginalized patient population. The user-friendly interface is a COVID-19 Hospitalizations Control Dashboard (HCD). This dashboard displays historical and projected COVID-19 hospitalizations in Broome County, New York. The population in Broom County is considered marginalized due to the high poverty rate and the high percentage of persons 65 years old and above. The developed system allows the medical team to plan to ensure better bed management, less cancelation in elective surgeries, and fewer patients held in the emergency department, hence, better healthcare outcomes in the county. Data are retrieved from the New York State state-wide COVID-19 hospitalizations website. The forecasted COVID-19 hospitalizations are generated using a time series model. The model was initially trained using data that span over a period ranging from June 2020 to December 2022. However, the model is tuned periodically to encounter changes in the time series behavior. We tested the following methods to forecast the number of COVID-19 hospitalizations 7 days in advance: simple exponential smoothing, autoregressive integrated moving average (ARIMA), and multilayer perceptron neural networks. The candidate model was selected based on the akaike information criterion, Bayesian information criterion, and the root-mean-square error (RMSE). The chosen model was ARIMA (3, 1, 6) with an RMSE of 4.5. Results obtained from the selected model were promising; hence, the final model was used in the developed user interface. Deploying this system resulted in better bed utilization, fewer elective surgery cancelations, and refrainment from reaching an 85% bed occupancy rate, which led to the suspension of elective surgeries. This dashboard, along with other similar dashboards deployed in the organization, was selected as part of NYS best practice. This system is used as a warning system to allow for early interventions. |
| format | Article |
| id | doaj-art-425d8644b78a4cbd9fbb2f7c47016390 |
| institution | Kabale University |
| issn | 2314-7784 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Advances in Public Health |
| spelling | doaj-art-425d8644b78a4cbd9fbb2f7c470163902025-02-03T11:27:57ZengWileyAdvances in Public Health2314-77842024-01-01202410.1155/2024/6644557Web-Based Healthcare Delivery Integrated System to Forecast COVID-19 Hospitalizations in a Marginalized Patient Population: A Case Study in Broome County, New YorkAnemone Kasasbeh0Elie Issa1Naseem Khan2Mehmet Yildirim3Amy Booth4Hiroki Sayama5Department of Systems Science and Industrial EngineeringDepartment of Systems Science and Industrial EngineeringDepartment of Systems Science and Industrial EngineeringDepartment of Systems Science and Industrial EngineeringAdvanced Data AnalyticsDepartment of Systems Science and Industrial EngineeringWe developed a web-based integrated healthcare delivery system with a user-friendly interface to help forecast COVID-19 hospitalizations in a marginalized patient population. The user-friendly interface is a COVID-19 Hospitalizations Control Dashboard (HCD). This dashboard displays historical and projected COVID-19 hospitalizations in Broome County, New York. The population in Broom County is considered marginalized due to the high poverty rate and the high percentage of persons 65 years old and above. The developed system allows the medical team to plan to ensure better bed management, less cancelation in elective surgeries, and fewer patients held in the emergency department, hence, better healthcare outcomes in the county. Data are retrieved from the New York State state-wide COVID-19 hospitalizations website. The forecasted COVID-19 hospitalizations are generated using a time series model. The model was initially trained using data that span over a period ranging from June 2020 to December 2022. However, the model is tuned periodically to encounter changes in the time series behavior. We tested the following methods to forecast the number of COVID-19 hospitalizations 7 days in advance: simple exponential smoothing, autoregressive integrated moving average (ARIMA), and multilayer perceptron neural networks. The candidate model was selected based on the akaike information criterion, Bayesian information criterion, and the root-mean-square error (RMSE). The chosen model was ARIMA (3, 1, 6) with an RMSE of 4.5. Results obtained from the selected model were promising; hence, the final model was used in the developed user interface. Deploying this system resulted in better bed utilization, fewer elective surgery cancelations, and refrainment from reaching an 85% bed occupancy rate, which led to the suspension of elective surgeries. This dashboard, along with other similar dashboards deployed in the organization, was selected as part of NYS best practice. This system is used as a warning system to allow for early interventions.http://dx.doi.org/10.1155/2024/6644557 |
| spellingShingle | Anemone Kasasbeh Elie Issa Naseem Khan Mehmet Yildirim Amy Booth Hiroki Sayama Web-Based Healthcare Delivery Integrated System to Forecast COVID-19 Hospitalizations in a Marginalized Patient Population: A Case Study in Broome County, New York Advances in Public Health |
| title | Web-Based Healthcare Delivery Integrated System to Forecast COVID-19 Hospitalizations in a Marginalized Patient Population: A Case Study in Broome County, New York |
| title_full | Web-Based Healthcare Delivery Integrated System to Forecast COVID-19 Hospitalizations in a Marginalized Patient Population: A Case Study in Broome County, New York |
| title_fullStr | Web-Based Healthcare Delivery Integrated System to Forecast COVID-19 Hospitalizations in a Marginalized Patient Population: A Case Study in Broome County, New York |
| title_full_unstemmed | Web-Based Healthcare Delivery Integrated System to Forecast COVID-19 Hospitalizations in a Marginalized Patient Population: A Case Study in Broome County, New York |
| title_short | Web-Based Healthcare Delivery Integrated System to Forecast COVID-19 Hospitalizations in a Marginalized Patient Population: A Case Study in Broome County, New York |
| title_sort | web based healthcare delivery integrated system to forecast covid 19 hospitalizations in a marginalized patient population a case study in broome county new york |
| url | http://dx.doi.org/10.1155/2024/6644557 |
| work_keys_str_mv | AT anemonekasasbeh webbasedhealthcaredeliveryintegratedsystemtoforecastcovid19hospitalizationsinamarginalizedpatientpopulationacasestudyinbroomecountynewyork AT elieissa webbasedhealthcaredeliveryintegratedsystemtoforecastcovid19hospitalizationsinamarginalizedpatientpopulationacasestudyinbroomecountynewyork AT naseemkhan webbasedhealthcaredeliveryintegratedsystemtoforecastcovid19hospitalizationsinamarginalizedpatientpopulationacasestudyinbroomecountynewyork AT mehmetyildirim webbasedhealthcaredeliveryintegratedsystemtoforecastcovid19hospitalizationsinamarginalizedpatientpopulationacasestudyinbroomecountynewyork AT amybooth webbasedhealthcaredeliveryintegratedsystemtoforecastcovid19hospitalizationsinamarginalizedpatientpopulationacasestudyinbroomecountynewyork AT hirokisayama webbasedhealthcaredeliveryintegratedsystemtoforecastcovid19hospitalizationsinamarginalizedpatientpopulationacasestudyinbroomecountynewyork |