Patient Flow Capacity Suite provides actionable intelligence to help you orchestrate care at every level. It supports enhanced care coordination and patient transitions by combining patient insights, care needs, and resource requirements to support care delivery at the right time, place, and care setting.
By clicking on the link, you will be leaving the official Royal Philips ("Philips") website. Any links to third-party websites that may appear on this site are provided only for your convenience and in no way represent any affiliation or endorsement of the information provided on those linked websites. Philips makes no representations or warranties of any kind with regard to any third-party websites or the information contained therein.
Predicts admission and discharge at various time intervals to support forecasting at enterprise, hospital and unit levels. Powered by machine learning, the algorithm uses retrospective hospital data, along with hourly patient data and weekly trends, to continuously adapt and help staff proactively prevent bottlenecks.
Enterprise Demand Capacity (Predicted Census)
Predicts admission and discharge at various time intervals to support forecasting at enterprise, hospital and unit levels. Powered by machine learning, the algorithm uses retrospective hospital data, along with hourly patient data and weekly trends, to continuously adapt and help staff proactively prevent bottlenecks.
Enterprise Demand Capacity (Predicted Census)
Predicts admission and discharge at various time intervals to support forecasting at enterprise, hospital and unit levels. Powered by machine learning, the algorithm uses retrospective hospital data, along with hourly patient data and weekly trends, to continuously adapt and help staff proactively prevent bottlenecks.
Predicts admission and discharge at various time intervals to support forecasting at enterprise, hospital and unit levels. Powered by machine learning, the algorithm uses retrospective hospital data, along with hourly patient data and weekly trends, to continuously adapt and help staff proactively prevent bottlenecks.
Recurring Patient Flag (RPF)
Recurring Patient Flag (RPF)
Helps identify recurring patients so they are triaged appropriately to optimally manage post-acute care and prevent bouncebacks. The algorithm uses multiple years of data from various US-based hospitals to define thresholds for number of emergency department visits, number of non-elective admissions, and days between current and previous admissions.
Recurring Patient Flag (RPF)
Helps identify recurring patients so they are triaged appropriately to optimally manage post-acute care and prevent bouncebacks. The algorithm uses multiple years of data from various US-based hospitals to define thresholds for number of emergency department visits, number of non-elective admissions, and days between current and previous admissions.
Recurring Patient Flag (RPF)
Helps identify recurring patients so they are triaged appropriately to optimally manage post-acute care and prevent bouncebacks. The algorithm uses multiple years of data from various US-based hospitals to define thresholds for number of emergency department visits, number of non-elective admissions, and days between current and previous admissions.
Helps identify recurring patients so they are triaged appropriately to optimally manage post-acute care and prevent bouncebacks. The algorithm uses multiple years of data from various US-based hospitals to define thresholds for number of emergency department visits, number of non-elective admissions, and days between current and previous admissions.
ST/AR Algorithm
ST/AR algorithm
Provides visualization of alarms and alarm trends to help prioritize telemetry patient reviews. Compared to the reference data base, the algorithm provides effective monitoring of arrhythmia events. Alarms are collected by PIC iX and sent to Patient Flow Capacity Suite, which displays yellow/red alarms and trends.
ST/AR algorithm
Provides visualization of alarms and alarm trends to help prioritize telemetry patient reviews. Compared to the reference data base, the algorithm provides effective monitoring of arrhythmia events. Alarms are collected by PIC iX and sent to Patient Flow Capacity Suite, which displays yellow/red alarms and trends.
ST/AR algorithm
Provides visualization of alarms and alarm trends to help prioritize telemetry patient reviews. Compared to the reference data base, the algorithm provides effective monitoring of arrhythmia events. Alarms are collected by PIC iX and sent to Patient Flow Capacity Suite, which displays yellow/red alarms and trends.
Provides visualization of alarms and alarm trends to help prioritize telemetry patient reviews. Compared to the reference data base, the algorithm provides effective monitoring of arrhythmia events. Alarms are collected by PIC iX and sent to Patient Flow Capacity Suite, which displays yellow/red alarms and trends.
Readmission Prediction Score (RPS)
Readmission Prediction Score (RPS)
Supports clinical management at admission and discharge by identifying early indications of patient readmission risk and highlighting patients who may be more likely to be readmitted within 30 days. The machine learning based algorithm is trained on multi-year data from various US-based hospitals.
Readmission Prediction Score (RPS)
Supports clinical management at admission and discharge by identifying early indications of patient readmission risk and highlighting patients who may be more likely to be readmitted within 30 days. The machine learning based algorithm is trained on multi-year data from various US-based hospitals.
Readmission Prediction Score (RPS)
Supports clinical management at admission and discharge by identifying early indications of patient readmission risk and highlighting patients who may be more likely to be readmitted within 30 days. The machine learning based algorithm is trained on multi-year data from various US-based hospitals.
Supports clinical management at admission and discharge by identifying early indications of patient readmission risk and highlighting patients who may be more likely to be readmitted within 30 days. The machine learning based algorithm is trained on multi-year data from various US-based hospitals.
Transition Review Score (TRS)
Transition Review Score (TRS)
Supports early identification of patient needs in emergency department and general care. The machine learning-based
algorithm is trained on multi-year data from various US-based hospitals to provide high performance for predicting care escalation needs, six hours in advance.
Transition Review Score (TRS)
Supports early identification of patient needs in emergency department and general care. The machine learning-based
algorithm is trained on multi-year data from various US-based hospitals to provide high performance for predicting care escalation needs, six hours in advance.
Transition Review Score (TRS)
Supports early identification of patient needs in emergency department and general care. The machine learning-based
algorithm is trained on multi-year data from various US-based hospitals to provide high performance for predicting care escalation needs, six hours in advance.
Supports early identification of patient needs in emergency department and general care. The machine learning-based
algorithm is trained on multi-year data from various US-based hospitals to provide high performance for predicting care escalation needs, six hours in advance.
Actionable check list and care status
Actionable check list and care status
Supports proactive identification of patient trends. Care status provides an in-depth view at the patient level, with color-coded thresholds. The actionable checklist identifies items for completion at admission and discharge, with highlighting for delayed actions.
Actionable check list and care status
Supports proactive identification of patient trends. Care status provides an in-depth view at the patient level, with color-coded thresholds. The actionable checklist identifies items for completion at admission and discharge, with highlighting for delayed actions.
Actionable check list and care status
Supports proactive identification of patient trends. Care status provides an in-depth view at the patient level, with color-coded thresholds. The actionable checklist identifies items for completion at admission and discharge, with highlighting for delayed actions.
Supports proactive identification of patient trends. Care status provides an in-depth view at the patient level, with color-coded thresholds. The actionable checklist identifies items for completion at admission and discharge, with highlighting for delayed actions.
Med-Surg Remaining Length of Stay
Med-Surg Remaining Length of Stay (RLOS)
Supports the care team in discharge evaluation of patients. The machine learning-based algorithm is trained on multi-year data from US-based hospitals. It takes lab results, physiological parameters, trending, medications and reason for visit into account to provide an initial prediction four hours into the med-surg admission. Predications are updated at 24, 48 and 72 hours.
Med-Surg Remaining Length of Stay (RLOS)
Supports the care team in discharge evaluation of patients. The machine learning-based algorithm is trained on multi-year data from US-based hospitals. It takes lab results, physiological parameters, trending, medications and reason for visit into account to provide an initial prediction four hours into the med-surg admission. Predications are updated at 24, 48 and 72 hours.
Med-Surg Remaining Length of Stay (RLOS)
Supports the care team in discharge evaluation of patients. The machine learning-based algorithm is trained on multi-year data from US-based hospitals. It takes lab results, physiological parameters, trending, medications and reason for visit into account to provide an initial prediction four hours into the med-surg admission. Predications are updated at 24, 48 and 72 hours.
Supports the care team in discharge evaluation of patients. The machine learning-based algorithm is trained on multi-year data from US-based hospitals. It takes lab results, physiological parameters, trending, medications and reason for visit into account to provide an initial prediction four hours into the med-surg admission. Predications are updated at 24, 48 and 72 hours.
ICU Remaining Length of Stay
ICU Remaining Length of Stay (RLOS)
Specifically designed for the ICU to support the care team in discharge evaluation of patients. The machine learning-based algorithm models surviving and perishing patients as competing events and is trained on a rich ICU dataset that includes more than 260,000 samples from multiple US-based hospitals. It takes labs results, physiological parameters, evaluations, and reason for admission into account to predict if patient will be discharged in under 24 hours, 24-48 hours, or >48 hours.
ICU Remaining Length of Stay (RLOS)
Specifically designed for the ICU to support the care team in discharge evaluation of patients. The machine learning-based algorithm models surviving and perishing patients as competing events and is trained on a rich ICU dataset that includes more than 260,000 samples from multiple US-based hospitals. It takes labs results, physiological parameters, evaluations, and reason for admission into account to predict if patient will be discharged in under 24 hours, 24-48 hours, or >48 hours.
ICU Remaining Length of Stay (RLOS)
Specifically designed for the ICU to support the care team in discharge evaluation of patients. The machine learning-based algorithm models surviving and perishing patients as competing events and is trained on a rich ICU dataset that includes more than 260,000 samples from multiple US-based hospitals. It takes labs results, physiological parameters, evaluations, and reason for admission into account to predict if patient will be discharged in under 24 hours, 24-48 hours, or >48 hours.
Specifically designed for the ICU to support the care team in discharge evaluation of patients. The machine learning-based algorithm models surviving and perishing patients as competing events and is trained on a rich ICU dataset that includes more than 260,000 samples from multiple US-based hospitals. It takes labs results, physiological parameters, evaluations, and reason for admission into account to predict if patient will be discharged in under 24 hours, 24-48 hours, or >48 hours.
Predicts admission and discharge at various time intervals to support forecasting at enterprise, hospital and unit levels. Powered by machine learning, the algorithm uses retrospective hospital data, along with hourly patient data and weekly trends, to continuously adapt and help staff proactively prevent bottlenecks.
Enterprise Demand Capacity (Predicted Census)
Predicts admission and discharge at various time intervals to support forecasting at enterprise, hospital and unit levels. Powered by machine learning, the algorithm uses retrospective hospital data, along with hourly patient data and weekly trends, to continuously adapt and help staff proactively prevent bottlenecks.
Enterprise Demand Capacity (Predicted Census)
Predicts admission and discharge at various time intervals to support forecasting at enterprise, hospital and unit levels. Powered by machine learning, the algorithm uses retrospective hospital data, along with hourly patient data and weekly trends, to continuously adapt and help staff proactively prevent bottlenecks.
Predicts admission and discharge at various time intervals to support forecasting at enterprise, hospital and unit levels. Powered by machine learning, the algorithm uses retrospective hospital data, along with hourly patient data and weekly trends, to continuously adapt and help staff proactively prevent bottlenecks.
Recurring Patient Flag (RPF)
Recurring Patient Flag (RPF)
Helps identify recurring patients so they are triaged appropriately to optimally manage post-acute care and prevent bouncebacks. The algorithm uses multiple years of data from various US-based hospitals to define thresholds for number of emergency department visits, number of non-elective admissions, and days between current and previous admissions.
Recurring Patient Flag (RPF)
Helps identify recurring patients so they are triaged appropriately to optimally manage post-acute care and prevent bouncebacks. The algorithm uses multiple years of data from various US-based hospitals to define thresholds for number of emergency department visits, number of non-elective admissions, and days between current and previous admissions.
Recurring Patient Flag (RPF)
Helps identify recurring patients so they are triaged appropriately to optimally manage post-acute care and prevent bouncebacks. The algorithm uses multiple years of data from various US-based hospitals to define thresholds for number of emergency department visits, number of non-elective admissions, and days between current and previous admissions.
Helps identify recurring patients so they are triaged appropriately to optimally manage post-acute care and prevent bouncebacks. The algorithm uses multiple years of data from various US-based hospitals to define thresholds for number of emergency department visits, number of non-elective admissions, and days between current and previous admissions.
ST/AR Algorithm
ST/AR algorithm
Provides visualization of alarms and alarm trends to help prioritize telemetry patient reviews. Compared to the reference data base, the algorithm provides effective monitoring of arrhythmia events. Alarms are collected by PIC iX and sent to Patient Flow Capacity Suite, which displays yellow/red alarms and trends.
ST/AR algorithm
Provides visualization of alarms and alarm trends to help prioritize telemetry patient reviews. Compared to the reference data base, the algorithm provides effective monitoring of arrhythmia events. Alarms are collected by PIC iX and sent to Patient Flow Capacity Suite, which displays yellow/red alarms and trends.
ST/AR algorithm
Provides visualization of alarms and alarm trends to help prioritize telemetry patient reviews. Compared to the reference data base, the algorithm provides effective monitoring of arrhythmia events. Alarms are collected by PIC iX and sent to Patient Flow Capacity Suite, which displays yellow/red alarms and trends.
Provides visualization of alarms and alarm trends to help prioritize telemetry patient reviews. Compared to the reference data base, the algorithm provides effective monitoring of arrhythmia events. Alarms are collected by PIC iX and sent to Patient Flow Capacity Suite, which displays yellow/red alarms and trends.
Readmission Prediction Score (RPS)
Readmission Prediction Score (RPS)
Supports clinical management at admission and discharge by identifying early indications of patient readmission risk and highlighting patients who may be more likely to be readmitted within 30 days. The machine learning based algorithm is trained on multi-year data from various US-based hospitals.
Readmission Prediction Score (RPS)
Supports clinical management at admission and discharge by identifying early indications of patient readmission risk and highlighting patients who may be more likely to be readmitted within 30 days. The machine learning based algorithm is trained on multi-year data from various US-based hospitals.
Readmission Prediction Score (RPS)
Supports clinical management at admission and discharge by identifying early indications of patient readmission risk and highlighting patients who may be more likely to be readmitted within 30 days. The machine learning based algorithm is trained on multi-year data from various US-based hospitals.
Supports clinical management at admission and discharge by identifying early indications of patient readmission risk and highlighting patients who may be more likely to be readmitted within 30 days. The machine learning based algorithm is trained on multi-year data from various US-based hospitals.
Transition Review Score (TRS)
Transition Review Score (TRS)
Supports early identification of patient needs in emergency department and general care. The machine learning-based
algorithm is trained on multi-year data from various US-based hospitals to provide high performance for predicting care escalation needs, six hours in advance.
Transition Review Score (TRS)
Supports early identification of patient needs in emergency department and general care. The machine learning-based
algorithm is trained on multi-year data from various US-based hospitals to provide high performance for predicting care escalation needs, six hours in advance.
Transition Review Score (TRS)
Supports early identification of patient needs in emergency department and general care. The machine learning-based
algorithm is trained on multi-year data from various US-based hospitals to provide high performance for predicting care escalation needs, six hours in advance.
Supports early identification of patient needs in emergency department and general care. The machine learning-based
algorithm is trained on multi-year data from various US-based hospitals to provide high performance for predicting care escalation needs, six hours in advance.
Actionable check list and care status
Actionable check list and care status
Supports proactive identification of patient trends. Care status provides an in-depth view at the patient level, with color-coded thresholds. The actionable checklist identifies items for completion at admission and discharge, with highlighting for delayed actions.
Actionable check list and care status
Supports proactive identification of patient trends. Care status provides an in-depth view at the patient level, with color-coded thresholds. The actionable checklist identifies items for completion at admission and discharge, with highlighting for delayed actions.
Actionable check list and care status
Supports proactive identification of patient trends. Care status provides an in-depth view at the patient level, with color-coded thresholds. The actionable checklist identifies items for completion at admission and discharge, with highlighting for delayed actions.
Supports proactive identification of patient trends. Care status provides an in-depth view at the patient level, with color-coded thresholds. The actionable checklist identifies items for completion at admission and discharge, with highlighting for delayed actions.
Med-Surg Remaining Length of Stay
Med-Surg Remaining Length of Stay (RLOS)
Supports the care team in discharge evaluation of patients. The machine learning-based algorithm is trained on multi-year data from US-based hospitals. It takes lab results, physiological parameters, trending, medications and reason for visit into account to provide an initial prediction four hours into the med-surg admission. Predications are updated at 24, 48 and 72 hours.
Med-Surg Remaining Length of Stay (RLOS)
Supports the care team in discharge evaluation of patients. The machine learning-based algorithm is trained on multi-year data from US-based hospitals. It takes lab results, physiological parameters, trending, medications and reason for visit into account to provide an initial prediction four hours into the med-surg admission. Predications are updated at 24, 48 and 72 hours.
Med-Surg Remaining Length of Stay (RLOS)
Supports the care team in discharge evaluation of patients. The machine learning-based algorithm is trained on multi-year data from US-based hospitals. It takes lab results, physiological parameters, trending, medications and reason for visit into account to provide an initial prediction four hours into the med-surg admission. Predications are updated at 24, 48 and 72 hours.
Supports the care team in discharge evaluation of patients. The machine learning-based algorithm is trained on multi-year data from US-based hospitals. It takes lab results, physiological parameters, trending, medications and reason for visit into account to provide an initial prediction four hours into the med-surg admission. Predications are updated at 24, 48 and 72 hours.
ICU Remaining Length of Stay
ICU Remaining Length of Stay (RLOS)
Specifically designed for the ICU to support the care team in discharge evaluation of patients. The machine learning-based algorithm models surviving and perishing patients as competing events and is trained on a rich ICU dataset that includes more than 260,000 samples from multiple US-based hospitals. It takes labs results, physiological parameters, evaluations, and reason for admission into account to predict if patient will be discharged in under 24 hours, 24-48 hours, or >48 hours.
ICU Remaining Length of Stay (RLOS)
Specifically designed for the ICU to support the care team in discharge evaluation of patients. The machine learning-based algorithm models surviving and perishing patients as competing events and is trained on a rich ICU dataset that includes more than 260,000 samples from multiple US-based hospitals. It takes labs results, physiological parameters, evaluations, and reason for admission into account to predict if patient will be discharged in under 24 hours, 24-48 hours, or >48 hours.
ICU Remaining Length of Stay (RLOS)
Specifically designed for the ICU to support the care team in discharge evaluation of patients. The machine learning-based algorithm models surviving and perishing patients as competing events and is trained on a rich ICU dataset that includes more than 260,000 samples from multiple US-based hospitals. It takes labs results, physiological parameters, evaluations, and reason for admission into account to predict if patient will be discharged in under 24 hours, 24-48 hours, or >48 hours.
Specifically designed for the ICU to support the care team in discharge evaluation of patients. The machine learning-based algorithm models surviving and perishing patients as competing events and is trained on a rich ICU dataset that includes more than 260,000 samples from multiple US-based hospitals. It takes labs results, physiological parameters, evaluations, and reason for admission into account to predict if patient will be discharged in under 24 hours, 24-48 hours, or >48 hours.
Products or functionality may not be available in all geographies. Please check with your Philips representative for complete portfolio availability.
By clicking on the link, you will be leaving the official Royal Philips ("Philips") website. Any links to third-party websites that may appear on this site are provided only for your convenience and in no way represent any affiliation or endorsement of the information provided on those linked websites. Philips makes no representations or warranties of any kind with regard to any third-party websites or the information contained therein.
