Dataiku Case Studies Patient Scheduling Optimization (Patient No Show Predictive Analytics)

Edit This Case Study Record

	Patient Scheduling Optimization (Patient No Show Predictive Analytics) Dataiku

Patient Scheduling Optimization (Patient No Show Predictive Analytics)

Dataiku

Technology Category	Analytics & Modeling - Predictive Analytics
Applicable Industries	Healthcare & Hospitals
Applicable Functions	Business Operation
Use Cases	Predictive Replenishment
Services	Data Science Services
Challenge	The healthcare industry is grappling with a high rate of patient no-shows, with studies indicating that 5-10% of scheduled patients miss their appointments. This has a significant impact on the financial health of healthcare organizations and their ability to care for other patients. Primary care physicians lose an average revenue of $228 for every no-show, and the lost revenue for specialists is even higher. When a patient misses an appointment, overhead costs including staffing, insurance, and utilities are not reimbursed. Cancellations with primary care physicians also impact the number of necessary specialist referrals those physicians can make. Combined, these factors contribute to significant revenue loss for physicians. To help minimize the occurrence of no-shows and thus reduce associated costs, Intermedix decided to develop and operationalize a no-show predictor that would assist office managers in scheduling appointments. Read More
About Customer	Intermedix, founded in 2002, delivers technology-enabled services and SaaS solutions to healthcare providers, government agencies, and corporations. As a leading provider of technology-enabled solutions for the global health and safety net, Intermedix supports more than 15,000 healthcare providers with practice management, revenue cycle management, and data analytic tools. The company connects more than 95 percent of the U.S. population with crisis management and emergency preparedness technologies. Intermedix is now helping more than 50 clinics reduce costs related to patient no-shows. Read More
Solution	Intermedix introduced Dataiku DSS to their data science team to develop and operationalize a no-show predictor. The team set up the automatic ingestion and crunching of historical, appointment, and demographic patient data. The data scientists built a predictive model that scores individual patients based on the probability of them missing an appointment for an allocated time slot. This output is automatically fed directly to each individual clinic several times per week depending on demand. Office managers and schedulers can use this predictive report to optimize physician schedules and patient appointments. The development and deployment of such an application to cover site-specific patterns would typically take 3+ months. However, with Dataiku DSS, Intermedix’s data science team was able to prototype and deliver the solution in just one month. Read More Log in to view content
Contents

Technology Category

Analytics & Modeling - Predictive Analytics

Applicable Industries

Healthcare & Hospitals

Applicable Functions

Business Operation

Use Cases

Predictive Replenishment

Services

Data Science Services

Challenge

The healthcare industry is grappling with a high rate of patient no-shows, with studies indicating that 5-10% of scheduled patients miss their appointments. This has a significant impact on the financial health of healthcare organizations and their ability to care for other patients. Primary care physicians lose an average revenue of $228 for every no-show, and the lost revenue for specialists is even higher. When a patient misses an appointment, overhead costs including staffing, insurance, and utilities are not reimbursed. Cancellations with primary care physicians also impact the number of necessary specialist referrals those physicians can make. Combined, these factors contribute to significant revenue loss for physicians. To help minimize the occurrence of no-shows and thus reduce associated costs, Intermedix decided to develop and operationalize a no-show predictor that would assist office managers in scheduling appointments.

About Customer

Intermedix, founded in 2002, delivers technology-enabled services and SaaS solutions to healthcare providers, government agencies, and corporations. As a leading provider of technology-enabled solutions for the global health and safety net, Intermedix supports more than 15,000 healthcare providers with practice management, revenue cycle management, and data analytic tools. The company connects more than 95 percent of the U.S. population with crisis management and emergency preparedness technologies. Intermedix is now helping more than 50 clinics reduce costs related to patient no-shows.

Solution

Intermedix introduced Dataiku DSS to their data science team to develop and operationalize a no-show predictor. The team set up the automatic ingestion and crunching of historical, appointment, and demographic patient data. The data scientists built a predictive model that scores individual patients based on the probability of them missing an appointment for an allocated time slot. This output is automatically fed directly to each individual clinic several times per week depending on demand. Office managers and schedulers can use this predictive report to optimize physician schedules and patient appointments. The development and deployment of such an application to cover site-specific patterns would typically take 3+ months. However, with Dataiku DSS, Intermedix’s data science team was able to prototype and deliver the solution in just one month.

Impact #1	Easy access by office managers to automatically generated predictive reports within existing scheduling system.
Impact #2	Scoring of time slots to allow schedulers to know when most likely times for availabilities exist.
Impact #3	Reports are automatically generated 2 or 3 times per week.

Impact #1

Easy access by office managers to automatically generated predictive reports within existing scheduling system.

Impact #2

Scoring of time slots to allow schedulers to know when most likely times for availabilities exist.

Impact #3

Reports are automatically generated 2 or 3 times per week.

Benefit #1	Reduced the development and deployment time of the application from 3+ months to just one month.
Benefit #2	Helping more than 50 clinics reduce costs related to patient no-shows.
Benefit #3	Primary care physicians are potentially saving an average revenue of $228 for every no-show prevented.

Benefit #1

Reduced the development and deployment time of the application from 3+ months to just one month.

Benefit #2

Helping more than 50 clinics reduce costs related to patient no-shows.

Benefit #3

Primary care physicians are potentially saving an average revenue of $228 for every no-show prevented.

Download PDF Version

Overview

Patient Scheduling Optimization (Patient No Show Predictive Analytics)

Operational Impact

Quantitative Benefit