Use of AI in the medical field.

Machine learning (ML) and AI in medicine allow clinical trial sponsors to fill in the gaps when real-world evidence is incomplete or inconsistent. Trials suggest it can do even more, detecting early indicators of disease and even quantifying pain.

“Real-world evidence (RWE) rarely has the same rigor as research data. RWE is collected through electronic health records (EHRs) as well as through clinical trials. Although agencies want real-world evidence, the quality is not yet adequate to provide meaningful insights. Machine learning can pull this information,” Jaydev Thakkar, COO, Bioantstold BioSpace.

Real application of AI in the medical field

An example of AI in the medical field comes from the Ministry of Health in Singapore. With data from thousands of COVID-19 patients, the ministry is using machine learning to detect COVID-19 patients before clear symptoms are detectable without performing PCR-based testing. Data analysis can also detect worsening patients, Thakkar said. He said he expects that data to be released in the near future.

“When applying AI/ML to clinical trials, there are still hesitations,” Thakkar said. Besides the perception of novelty, the pharmaceutical industry is concerned about the comfort level of regulators when AI/ML is used. “It’s a big factor holding back the use of AI, but the mindset is changing,” Thakkar said.

The use of AI in the medical field is partly due to the fact that COVID-19 makes it difficult to conduct traditional clinical trials. “Managing patient load and site load for clinical trials is a major concern for sponsors. Consider the number of times patients are asked to complete on-site surveys or assessments,” he began. With COVID-19, many patients are reluctant to expose themselves to the risks of going to a healthcare facility, so they drop out of the trial or do not enroll. “Much of this data can be collected digitally, offsite, to reduce patient burden and therefore address recruitment delays,” Thakkar explained. AI/ML can help bridge the data gaps and inconsistencies inherent in RWE by extracting data from large groups of patients.

AI in the medical field, however, can play a bigger role. Biofourmis is working with Chugai Pharmaceutical in Japan to objectively determine the pain level of patients with endometriosis using its Biovitals® platform. “Traditional subjective assessments have significant variability, so they are not an optimal way to identify drug efficacy or perform drug titrations to deliver pain medication to patients. Instead, we can objectively identify the level of pain by collecting data through sensors and quantifying that information,” he said.

The Biovitals platform detects more than 20 physiological changes, such as skin temperature, heart rate or electrodermal activities that suggest, for example, frustration. Feeding this data into an algorithm compares the data to that of millions of other patients. In Chugai’s study, this provides a way to objectively quantify pain. This project is in the clinical trial phase, “evaluating clinical research and improving the algorithm”. It’s too early in the trials to share results, but the initial data is fairly accurate, Thakkar said.

In another example, AI in the medical field can improve patient adherence. Remote sensors or wearable devices are an increasingly common part of clinical trials. By determining whether patients actually wear them or those who complete the necessary online surveys, AI analytics can determine their level of engagement and predict which patients might drop out of trials.

When clinical trials consider patient burden by selecting devices that integrate well into patients’ daily lives, patients are more likely to stay engaged. Therefore, pharmaceutical developers gain significant insights by using patient-friendly devices and in doing so discover new parameters and signals that may be missed when patients are only seen episodically.

As clinical trial sponsors begin to use AI/ML in clinical trials, Thakkar said, “We are primarily seeing a shift towards endpoint design leveraging RWE by applying AI/ML to more effectively design protocols and outcomes to identify the change introduced by the therapy,” Thakkar said. For example, trying to measure the effectiveness of a heart failure drug by recording patients’ daily step counts may be less effective than measuring their sedentary hours or the intensity of their walks. By applying data collected from many trials, you can create more meaningful metrics. »

Many AI algorithms in the medical field are applicable to clinical research, but are not yet commercially available. The FDA, however, supports their use, Thakkar said. “We work with the FDA, and it’s very welcoming. For trial sponsors, the agency encourages early engagement, with an explanation of how you plan to use AI/ML in clinical research. By engaging early, companies can incorporate FDA feedback into the design of their clinical trials. Biofourmis works with at least eight pharmaceutical companies to apply AI tools.

“Continuous data collection is essential, but it is difficult for the human eye to detect subtle, but meaningful signals in high volumes of data. AI/ML, however, can find signals that can be statistically proven,” Thakkar said. The information this tool can reveal is an important addition not only to drug development, but also to the advancement of predictive and personalized medicine.