KenSci
KenSci Menu KenSci
KenSci Close KenSci

Operational analytics

Predict risk to improve operational efficiency

Operational analytics
Assimilate various conditions to provide the most optimal outcomes
Delivering ROI in 12 weeks

Assimilate various conditions to provide the most optimal outcomes

Healthcare organization, use the KenSci solution to manage their everyday operations better and in turn improve patient satisfaction scores. KenSci’s risk prediction platform for healthcare is engineered to ingest, transform and integrate disparate sources of healthcare data, including EHR, Claims, Admin/Finance, streaming and other sources. KenSci uses machine learning to recognize patterns in large volumes of data, helping health systems view the granular details of the patient’s history and predict future risks for optimal care.

Use cases we solve for

Emergency Department Demand Prediction
Emergency Department Utilization Prediction
Length of Stay Prediction
Emergency Department Demand Prediction
Emergency Department Demand Prediction
Emergency Department Utilization Prediction
Length of Stay Prediction
Emergency Department Demand Prediction

Emergency Department Demand Prediction

Emergency Department (ED) overcrowding is recognized as a national problem that hinders the delivery of both emergency and downstream medical services. Overcrowding in the ED has been linked to decreased quality of care, increased costs, and diminished patient dissatisfaction. Were ED administrators and staff ...

+ read more

Emergency Department (ED) overcrowding is recognized as a national problem that hinders the delivery of both emergency and downstream medical services. Overcrowding in the ED has been linked to decreased quality of care, increased costs, and diminished patient dissatisfaction. Were ED administrators and staff able to be alerted prior to severe overcrowding, they might be able to intervene to alleviate increased demand, before health care quality and access become compromised.

 

The deficit

Delays, interruptions, and cancellations are so common that patients and clinicians regard them as an inevitable part of the process of healthcare. Hospitals provide a prime example of the fact that waiting is intrinsic and almost intractable. Obtaining actionable data from patient flows is challenging. It requires data integration from multiple systems to support comparison across departments and workflows.

Improve operational efficiency

Improve operational efficiency

KenSci offers a locally-tuned, ML model-based solution that predicts patterns in Emergency Department Demand to enable operational staff to plan for staffing, on daily, weekly, and monthly basis.

Provide better care

Provide better care

This supports the delivery of enhanced care to patients needing emergency services – resulting in increased ED staff satisfaction, better patient satisfaction and ED throughput quality measures scores, and improved patient outcomes.

Insight into the future

Insight into the future

This solution enables the operational team to visualize future demand and act on precise prediction to optimally staff the ED and demonstrate improved sensitivity, specificity within a 4-hour timeliness.

Manage staffing better

Manage staffing better

The KenSci ED Demand Prediction tool enables the ED to have the right number of ED physicians and nurses to accommodate the patient population regardless of ED demand.

Emergency Department Utilization Prediction

Emergency Department Utilization Prediction

U.S. emergency departments (EDs) collectively experience 130 million encounters annually, and a large percentage of ED visits originate from a small proportion of patients who keep returning to the ED, commonly known as super-utilizers. In 2016, researchers found that of 1,443 patients presenting to the ED, 71%...

+ read more

U.S. emergency departments (EDs) collectively experience 130 million encounters annually, and a large percentage of ED visits originate from a small proportion of patients who keep returning to the ED, commonly known as super-utilizers. In 2016, researchers found that of 1,443 patients presenting to the ED, 71% percent had 2 or more visits and 15% had five or more visits within the previous 12 months. A significant fraction of the frequent ED user population is comprised of patients with complex, unmet needs for interventions, including mental health, substance abuse, transportation and housing, and chronic disease management services.

 

The deficit

Frequent readmissions for these conditions can cause ED throughput inefficiencies and overcrowding, resulting in a decreased quality of care and an increase in operational costs and patient dissatisfaction. Accurate prediction of ED readmissions is integral for cost-effective resource allocation planning to improve post-discharge intervention in high-risk patients.

Learn from existing data

Learn from existing data

KenSci’s ML Risk Prediction Platform and ED Readmission Prediction Solution utilizes individual patient information, including the patient’s demographics, diagnoses, and lab values from claims, EHR and other data sources to develop a risk score corresponding to a patient’s likelihood of utilizing the ED frequently.

Prediction based action

Prediction based action

Following EMR review and ML factor analysis, potentially modifiable situation included missed office visits, diabetes out of control and personal stress, the medical team is able to view the risk prediction.

Know the high utilizers

Know the high utilizers

The doctor can see that a patient has been flagged as having a high risk of becoming a frequent ED high utilizer through the KenSci Risk Prediction Solution that leverages Machine Learning to make this prediction.

Identify at risk patients

Identify at risk patients

This tool enables doctors to better understand the likelihood that a patient may return to the ED for exacerbations of her chronic disease.

Length of Stay Prediction

Length of Stay Prediction

To better serve patients and improve overall service, hospitals must coordinate the influx of patients and make decisions regarding staffing and resource allocation. Knowing the expected length of stay (LOS) for each patient is a part of the critical information to aid in these decisions. The accurate ...

+ read more

To better serve patients and improve overall service, hospitals must coordinate the influx of patients and make decisions regarding staffing and resource allocation. Knowing the expected length of stay (LOS) for each patient is a part of the critical information to aid in these decisions. The accurate estimation of LOS also affects planning future bed usage, identifying specialists for patients with multiple diagnoses, determining health insurance schemes and reimbursement systems in the private sector, planning discharge dates, and allowing families to better plan for the return of their relatives.

 

The deficit

Hospital LOS is often used as an indicator of efficiency of care and organizational performance. Ineffective prediction of LOS negatively affects cost, outcomes, and quality of care. LOS also impacts patient flow and discharge planning. Often, length of stay is predicted by the clinician’s judgement. The Real-Time Demand Capacity management tool (RTDC) is a LOS prediction method developed by the Institute for Healthcare Improvement that has shown variable results when pilot tested in hospitals, as it involves multiple steps and is ultimately subjective and, thus, susceptible to high variability.

Efficient resource management

Efficient resource management

With the help of the accurate estimation of the stay of patients, the hospital can plan for more efficient resource utilization. Predicting the probable discharge dates can help to determine available bed hours that results in higher average occupancy and less waste of resources in the hospital.

Data driven insights

Data driven insights

The KenSci Hospital Length of Stay Solution provides a view into how healthcare facilities can use information such as patient’s vitals, their history, and current symptoms and accurately predict how long they need to be treated and what type of care they need during their stay by applying machine learning.

Intervene early

Intervene early

A prediction model that can predict the LOS of a patient can be an effective tool for the healthcare providers to make proper plans for preventive interventions, to perform better health services and to manage hospital resources more efficiently.

Account for variables

Account for variables

The KenSci solution can make LOS predictions by utilizing machine learning which can factor in multiple variables simultaneously.

Stay one step ahead

  • Manage load and staffing

    Manage load and staffing

    Predict patient in-flow and optimize staff based on demand forecasts.

  • Manage patient costs and outcomes

    Manage patient costs and outcomes

    Know the high utilizers and transition to a system of value based care for better outcomes.

  • Gain insights to optimize costs

    Gain insights to optimize costs

    Know which parts of your operations are costing you to increase margins optimally.

Get in touch