J&J enlists AI to streamline joint replacement surgery

Operating rooms are a significant source of revenue for healthcare organizations — and a main contributor to costs. As such, any cost savings in operating rooms can have broad financial impact on a healthcare facility’s bottom line.

One of the main reasons for the lower efficiency of operating rooms is the excessive amount of time taken in preparation for surgery.

“Managing inventory, both pre-operative and post-operative, is time consuming because the inventory replenishment process is reactive,” says Jim Swanson, CIO at US pharmaceutical and medical technologies company Johnson & Johnson.

As an example, Swanson points to total knee arthroplasty (TKA) and total hip arthroplasty (THA) procedures. “While appropriate component sizing in TKA and THA is essential to optimizing clinical outcomes, there are instances where the provided patient X-ray during the pre-surgery process has poor image quality, which prevents predicting the right implant part sizing. As a result, the healthcare organization must ship all possible standard sizes in for each surgery.”

This excess inventory at the facility can be a significant burden, Swanson says. “The operating room staff also spends too much time with pre-case setup and sterilization of the huge inventory,” he adds.

To address these issues, J&J launched Advance Case Management (ACM), a digitally integrated system that simplifies pre-surgery processes by utilizing case schedules and patient data. The system tackles the inventory management challenge by integrating directly with the customer’s healthcare system to enable real-time demand sensing. And, in late 2021, J&J introduced AI knee and hip implant machine-learning driven predictions specifically for TKA and THA implant sizing and patient surgical needs — a project that earned the company a 2023 CIO 100 Award for IT innovation and leadership.

“It is a way for healthcare providers to coordinate with DePuy Synthes, the orthopaedics company of Johnson & Johnson, to enhance preoperative coordination by making it smoother, simpler, and smarter,” Swanson says.

Developing a digitally integrated solution

J&J’s ACM team developed the solution in a true agile fashion, with a shippable product available after every sprint, Swanson says.

The system — which leverages a suite of digital tools, including HL7 EMR/DICOM industry-standard integrations, a NodeJS and React web app, an open API architecture, and microservices to integrate with external partners — makes use of in-house Redshift machine-learning algorithms to predict hip and knee implant sizing using patient biometrics in addition to X-ray images. ACM also includes a robust portal that offers case analytics around product utilization, surgery metrics, upcoming case schedules, case details, and templating insights.

“The primary data source is ACM’s internal case report, though we also rely on orthopaedic supply data from Mercy, a not-for-profit Catholic healthcare organization,” Swanson says. “For ACM case reports, data transfer occurs from a high-trust data environment and an automated pipeline is built to provide the most recent data to the data science team through Redshift tables. The data includes patient biometric information such as height, weight, age, and gender. These features tend to be available in most EMR [electronic medical record] systems and thus allow for scale of the solution.”

To predict component size for TKA and THA surgeries, J&J implemented a range of machine learning techniques. “After cleaning and harmonizing the data in terms of units and metrics, we develop multi-class classification models to predict component size specific to each brand and component. The primary prediction algorithm in production is ordinal logistic regression and different techniques are used to deal with the class imbalance problem (stratified sampling, SMOTE, etc.),” Swanson says.

Completed algorithms are shared via Amazon Web Services S3 infrastructure with the SC EMR IT team. Results are visualized in a Tableau dashboard for business stakeholders to track accuracy over time. Models are retrained approximately once per business quarter.

“The encrypted case schedule and patient information are electronically transferred securely. The data is used to determine the specification of the DePuy Synthes implant range and the instrument set for each surgery,” says Swanson.

Overcoming obstacles along the way

Swanson and his team had to deal with a few challenges while developing ACM. The two major ones were getting commercial buy-in to accelerate adoption of the solution and ensuring its effective marketing as there were distinct regional go-to-market processes that challenged the backlog prioritization.

“We secured commercial buy-in by demonstrating that the ML algorithm’s prediction accuracy was over 90% and that the service itself had a massive time-savings impact on both the rep and the surgeons, which generated organic excitement and confidence within the commercial and customer communities,” says Swanson, who this year was also inducted into the CIO Hall of Fame.

“The issue of marketing was overcome by empowering strong global business and technology product owners to drive clear prioritization and clarify the end-value of the most critical features that would enable both regions to go to market effectively,” he says.

Benefits for all stakeholders

Launched in collaboration with DePuy Synthes Joint Reconstruction Commercial Partners and the Medical Devices Strategic Customer Group, ACM has delivered significant benefits to healthcare organizations and patients alike.

“The solution has delivered 63% reduction in instrument trays required in the operating room, 8-to-14-minute reduction (approximately 15%) in operating room setup time, 50% reduction in on-hand customer inventory, and about 4.5 hours per week reduction of high-touch, task-related logistics for sales consultants, enabling greater focus on customer needs in support of the patients we serve,” Swanson says, adding that ACM supported over 24,000 procedures in 2022, more than double the 10,000 procedures it supported in 2021.

To address physician surgical preferences within the same connected care site, J&J’s development team also introduced a customizable surgeon preference module.

“Our templating team and the ACM product implemented a module that allows our surgical staff to identify their preferences for surgical parts. Each surgeon has their unique preferences for each procedure type, so having a module that captures those differences allows us to proactively meet the needs of their instrument trays and product requirements in advance,” says Swanson.

With direct customer EMR/EHR connectivity, J&J can gain insight into the needs of a specific surgical case prior to it occurring and make shipment and inventory decisions in real-time based on that information. Rather than shipping all possible standard sizes for each surgery, the company can predict and ship only according to a specific patient’s needs.

“Customers on ACM rate their partnership and experience with J&J more favorably as it transforms the inventory replenishment process from reactive to proactive, driving efficiency throughout the supply chain and allowing speed and agility for accurate prediction to enhance preparation for individual patient and surgery,” says Swanson.

Patients meanwhile are also benefitting from ACM’s ability to streamline part-sizing and inventory prep by reducing the amount of time they must spend in the care setting in advance of surgery.

“The ACM program is a great example of a new healthcare business model that is helping Johnson & Johnson achieve its goal of becoming the provider of choice. It has shown that the challenge of inventory management can be simplified when both parties involved work together and use technology to remove process inefficiency,” Swanson says, adding, “We are now moving to accelerate our integrators and intermediaries to increase penetration at trauma centers. Trauma and spine are key opportunity areas to leverage the algorithm and platform.”

Artificial Intelligence, CIO 100, Healthcare Industry