Cancer patients face special difficulties that make waiting times very stressful. They often need many tests, treatments, surgeries, and follow-up visits. All these require careful scheduling and organization.
Research led by Yaron Shaposhnik, an assistant professor at Simon Business School, shows that patients at large U.S. cancer hospitals feel more worried about waiting times. This makes it important to improve how hospitals manage waits.
Shaposhnik’s team worked with a big cancer hospital that used a real-time locating system (RTLS). This system has many sensors and electronic badges to track where patients and staff are.
The system collects data about patient movement and staff availability. This helps analyze and predict wait times.
They combined usual operations research methods with machine learning to find patterns that cause delays.
One problem was that the data was not perfect. Sometimes patients forgot to scan their badges or the system had temporary failures.
Even so, the researchers made a mathematical model that accounted for these problems. This made wait time predictions more accurate.
They also found missing data about why some patients were seen first, beyond just who arrived first.
This led to new projects to better understand how to prioritize patients and improve scheduling.
Real-time locating systems are very useful for lowering wait times in hospitals.
RTLS technology automatically tracks patients, staff, and equipment inside the hospital.
This provides important information about workflow problems and resource use.
When hospitals use RTLS well, it helps departments work better together, makes patient movement faster, and improves use of rooms and equipment.
In cancer care, RTLS helps make sure patients who need urgent treatment like chemotherapy get priority.
This helps reduce delays caused by miscommunication or slow movement of patients.
Shaposhnik’s project showed that using RTLS data with machine learning tools predicts patient wait times better.
It also points out places where scheduling can improve.
This helps hospitals plan ahead instead of only reacting to problems, allowing better use of resources.
Using artificial intelligence (AI) together with automation can help reduce patient wait times and improve how hospitals work.
AI processes a lot of data from RTLS, health records, staffing lists, and appointments to give useful information.
Shaposhnik says that while AI tools are strong, they cannot replace human decisions in complex healthcare situations.
Instead, AI should help administrators by giving better predictions and real-time data.
For example, AI can predict delays caused by staff shortages or crowded clinics.
Operations research methods then improve scheduling based on these predictions.
One use is AI-driven tools for assistants who care for patients.
These tools can update patients on expected wait times, helping reduce stress.
Automated systems can also alert staff about delays so they can act faster to keep patient flow smooth.
AI can also help balance workloads for doctors and avoid crowding in places like infusion therapy.
By spreading out appointments more evenly, these systems help prevent bottlenecks and make the best use of doctor time.
Memorial Healthcare System in Pembroke Pines, Florida, shows how real-time data and AI can improve hospital work and shorten wait times.
They created a Care Coordination Center (CCC) that works all day every day to improve patient safety and care.
The CCC is 3,000 square feet with 31 workstations.
Staff at the center watch patient flow, bed availability, and staffing using real-time screens powered by AI.
This helps them respond quickly and work together better.
Main parts of the CCC include:
Elizabeth Justen, chair of the local hospital board, said the CCC’s use of real-time data and teamwork greatly improves patient safety and care delivery.
The Virtual Nursing program helps by letting nurses do some tasks from afar.
This frees up time for nurses who are with patients in person, which also helps lower wait times by making admissions and discharges faster.
Besides RTLS and AI, other digital tools help cancer hospitals work better.
Siemens Healthineers offers partnerships that focus on data, connected medical devices, and AI to improve clinical and operational work.
Their Digital Service Line Optimization automates routine tasks so teams can focus more on patient care.
The Digital Enterprise Advancement uses data insights to manage performance and patient flow.
One key technology, RTLS, improves tracking of assets, staff, and patients to cut wait times and costs.
Using lean management with digital tools has improved areas like radiology and infusion therapy.
Hospitals using these methods can sometimes save more than $1 million a year by speeding up patient flow and better using resources.
Some examples are:
These examples are from outside U.S. cancer hospitals but show how digital solutions can improve clinical operations and patient care worldwide.
Many ideas from these examples can help cancer care in the U.S. too.
Shaposhnik points out that machine learning and operations research work well together in hospital management.
Machine learning is good at making predictions from data.
Operations research focuses on improving processes and making decisions.
This combination helps make wait time forecasts more accurate and improves scheduling.
However, Shaposhnik warns against trusting AI too much.
Health decisions still need human judgment and oversight.
Doctors and staff make choices based on data plus clinical issues like how serious a patient’s disease is and individual needs.
Machine learning supports by giving real-time data and spotting problems human managers might miss.
The research also shows it is important to collect better data on why patients are prioritized.
Scheduling models should include urgency and risk, not just who arrived first.
Administrators and IT managers in cancer hospitals should take these steps to lower wait times:
Using these steps will help cancer hospitals manage patient flow better, cut wait times, and ease patient worries about delays.
This will improve how hospitals operate and how patients feel about their care.
Busy cancer hospitals face heavy workloads and complex care pathways that add to patient wait times.
AI and workflow automation offer ways to reduce these problems, improve efficiency, and improve patient experience without adding extra staff.
AI can analyze many sources of data—appointments, staffing, equipment status, and patient locations—to spot possible scheduling problems and delays before they happen.
When AI is linked with hospital systems, it can suggest actions like changing appointment times or moving staff to reduce delays.
Workflow automation helps by handling routine tasks such as check-ins, reminders, and paperwork.
This lets clinical staff spend more time with patients, which helps speed up processing and reduce bottlenecks.
Examples of AI and automation in cancer hospitals are:
Shaposhnik’s research, along with successful places like Memorial Healthcare’s Care Coordination Center, shows that AI and automation used with human guidance can reduce wait times and improve care delivery in cancer hospitals.
Lowering patient wait times in cancer hospitals is a difficult task that needs detailed data analysis, real-time monitoring, and smart scheduling.
Using tools like RTLS, AI, and workflow automation alongside traditional methods offers a practical way to improve patient care and hospital work.
Projects such as Shaposhnik’s research and the Memorial Healthcare System’s Care Coordination Center show that technology can help coordinate care, reduce delays, and use staff and resources better.
For hospital administrators and IT managers, using these new tools is an important step toward better meeting the needs of cancer patients and improving how hospitals work.
Yaron Shaposhnik focuses on developing and applying machine learning tools and methodologies to improve operational decisions across various contexts, particularly in healthcare.
The hospital utilizes a real-time locating system with sensors and badges to analyze data and predict patient wait times, aiming to improve operational efficiency.
Wait times are crucial as they directly affect patient experience, especially in a cancer hospital where patients are often anxious about their treatments.
Shaposhnik applied traditional operations research methods along with machine learning tools to analyze badge data for predicting wait times.
They addressed issues related to imperfect data, such as patients forgetting to scan their badges and system malfunctions impacting data accuracy.
They identified the need to collect data on why certain patients are prioritized for treatment, beyond mere arrival time.
They plan to develop an interface for clinician assistants to inform patients of their anticipated wait times and optimize provider scheduling.
The scheduling tool aims to optimize provider sessions to minimize patient wait times while managing the flow of services like bloodwork and infusion therapy.
Shaposhnik emphasizes that while machine learning tools are powerful, healthcare resource allocation decisions should not be solely delegated to machines.
The goal is to improve patient experiences and outcomes through the combination of machine learning, traditional methods, and practical application in healthcare.
Simbo is using AI agents to automate all phone related workflows. Connect now to know more.
Schedule AI Agents Demo Now© Since 2019, Simbo AI.
