In response to the rapidly evolving use and approval of AI medical devices in healthcare, a multi-institutional team of researchers at the UNC School of Medicine, Duke University, Ally Bank, Oxford University, Colombia University, and University of Miami have been on a mission to build public trust and evaluate how exactly AI and algorithmic technologies are being approved for use in patient care.

Together, Sammy Chouffani El Fassi, a MD candidate at the UNC School of Medicine and research scholar at Duke Heart Center, and Gail E. Henderson, PhD, professor at the UNC Department of Social Medicine, led a thorough analysis of clinical validation data for 500+ medical AI devices, revealing that approximately half of the tools authorized by the U.S. Food and Drug Administration (FDA) lacked reported clinical validation data. Their findings were published in Nature Medicine.

“Although AI device manufacturers boast of the credibility of their technology with FDA authorization, clearance does not mean that the devices have been properly evaluated for clinical effectiveness using real patient data,” said Chouffani El Fassi, who was first author on the paper. “With these findings, we hope to encourage the FDA and industry to boost the credibility of device authorization by conducting clinical validation studies on these technologies and making the results of such studies publicly available.”

Since 2016, the average number of medical AI device authorizations by the FDA per year has increased from 2 to 69, indicating tremendous growth in commercialization of AI medical technologies. The majority of approved AI medical technologies are being used to assist physicians with diagnosing abnormalities in radiological imaging, pathologic slide analysis, dosing medicine, and predicting disease progression.

Artificial intelligence is able to learn and perform such human-like functions by using combinations of algorithms. The technology is then given a plethora of data and sets of rules to follow, so that it can “learn” how to detect patterns and relationships with ease. From there, the device manufacturers need to ensure that the technology does not simply memorize the data previously used to train the AI, and that it can accurately produce results using never-before-seen solutions.

Regulation During a Rapid Proliferation of AI Medical Devices

Following the rapid proliferation of these devices and applications to the FDA, Chouffani El Fassi and Henderson et al. were curious about how clinically effective and safe the authorized devices are. Their team analyzed all submissions available on the FDA’s official database, titled “Artificial Intelligence and Machine Learning (AI/ML)-Enabled Medical Devices.”

“A lot of the devices that came out after 2016 were created new, or maybe they were similar to a product that already was on the market,” said Henderson. “Using these hundreds of devices in this database, we wanted to determine what it really means for an AI medical device to be FDA-authorized.”

Of the 521 device authorizations, 144 were labelled as “retrospectively validated,” 148 were “prospectively validated,” and 22 were validated using randomized controlled trials. Most notably, 226 of 521 FDA-approved medical devices, or approximately 43%, lacked published clinical validation data. A few of the devices used “phantom images” or computer-generated images that were not from a real patient, which did not technically meet the requirements for clinical validation.

Furthermore, the researchers found that the latest draft guidance, published by the FDA in September 2023, does not clearly distinguish between different types of clinical validation studies in its recommendations to manufacturers.

Types of Clinical Validation and A New Standard

In the realm of clinical validation, there are three different methods by which researchers and device manufacturers validate the accuracy of their technologies: retrospective validation, prospective validation, and subset of prospective validation called randomized controlled trials.

Retrospective validation involves feeding the AI model image data from the past, such as patient chest x-rays prior to the COVID-19 pandemic. Prospective validation, however, typically produces stronger scientific evidence because the AI device is being validated based on real-time data from patients. This is more realistic, according to the researchers, because it allows the AI to account for data variables that were not in existence when it was being trained, such as patient chest x-rays that were impacted by viruses during the COVID pandemic.

Randomized controlled trials are considered the gold standard for clinical validation. This type of prospective study utilizes random assignment controls for confounding variables that would differentiate the experimental and control groups, thus isolating the therapeutic effect of the device. For example, researchers could evaluate device performance by randomly assigning patients to have their CT scans read by a radiologist (control group) versus AI (experimental group).

Because retrospective studies, prospective studies, and randomized controlled trials produce various levels of scientific evidence, the researchers involved in the study recommend that the FDA and device manufactures should clearly distinguish between different types of clinical validation studies in its recommendations to manufacturers.

In their Nature Medicine publication, Chouffani El Fassi and Henderson et al. lay out definitions for the clinical validation methods which can be used as a standard in the field of medical AI.

“We shared our findings with directors at the FDA who oversee medical device regulation, and we expect our work will inform their regulatory decision making,” said Chouffani El Fassi. “We also hope that our publication will inspire researchers and universities globally to conduct clinical validation studies on medical AI to improve the safety and effectiveness of these technologies. We’re looking forward to the positive impact this project will have on patient care at a large scale.”

Algorithms Can Save Lives

Chouffani El Fassi is currently working with UNC cardiothoracic surgeons Aurelie Merlo and Benjamin Haithcock as well as the executive leadership team at UNC Health to implement an algorithm in their electronic health record system that automates the organ donor evaluation and referral process.

In contrast to the field’s rapid production of AI devices, medicine is lacking basic algorithms, such as computer software that diagnose patients using simple lab values in electronic health records. Chouffani El Fassi says this is because implementation is often expensive and requires interdisciplinary teams that have expertise in both medicine and computer science.

Despite the challenge, UNC Health is on a mission to improve the organ transplant space.

“Finding a potential organ donor, evaluating their organs, and then having the organ procurement organization come in and coordinate an organ transplant is a lengthy and complicated process,” said Chouffani El Fassi. “If this very basic computer algorithm works, we could optimize the organ donation process. A single additional donor means several lives saved. With such a low threshold for success, we look forward giving more people a second chance at life.”

Other contributors to the study include Adonis Abdullah, Ying Fang, Sarabesh Natarajan, Awab Bin Masroor, Naya Kayali, Simran Prakash, Manesh R. Patel, William Ratliff, Zeshan Hussain, Justin Castillo, Ihsan Yüksel, Haonan Chen, Pengyu Guo, Hamilton McInnis, James E Hancock, Barbara J Evans, and Aurelie Merlo.

– Written by Kendall Daniels

The national poll of 1,006 people found:

• 75% believe using AI to minimize human errors is important.
• 71% would like AI to reduce wait times.
• 70% are comfortable with AI taking notes during an appointment.
• 66% believe AI should improve work-life balance for health care providers.

To address some of these issues, The Ohio State Wexner Medical Center is piloting the Microsoft Dragon Ambient eXperience (DAX) Copilot application. It uses conversational, ambient and generative AI to securely listen to a provider-patient visit and draft clinical notes in the patient’s electronic medical record. Rather than the provider typing the notes during the visit, they can focus on the patient then review and edit the notes afterward.

Ravi Tripathi, MD, chief health information officer at the Ohio State Wexner Medical Center, led the pilot program. From mid-January to mid-March this year, 24 physicians and advanced practice providers in primary care, cardiology and obstetrics and gynecology tested the technology during outpatient clinic visits. After obtaining the patient’s permission, the provider records the visit through the AI application. Once the visit is complete, the notes are organized and ready for review in less than a minute.

“We found it saved up to four minutes per visit. That’s time the physician can use to connect with the patient, do education and make sure they understand the plan going forward,” Tripathi said. “A few clinicians preferred their old workflow but, overall, 80% completed the pilot. In fact, we allowed them to keep using the AI solution afterward because it had significantly impacted their practices in the eight weeks of testing.”

One of the pilot participants was Harrison Jackson, MD, an internist who has been frustrated by the typing that has to take place during each patient visit.

“Documentation is necessary, but it takes away from the quality of patient interaction during a visit. I even apologize. I say, ‘I’m sorry, I know I’m making more eye contact with the computer than with you,’” Jackson said.

After testing AI documentation, Jackson reports some occasional missteps such as incorrect pronouns or mistaking one word for another – all things he said were easily fixed during his chart review. He supports the use of AI going forward in healthcare.

“I’m spending as much if not more time with each patient, and it’s higher quality time with more eye contact. I often mention aspects of a physical exam out loud for the AI program to capture, and it prompts a good conversation with my patient,” Jackson said. “I’ve also let our residents use the technology under my supervision, and we’ve noticed the quality of their patient interactions and the quality of plans they present have improved.”

While most Americans also see value in AI for healthcare, the survey found just over half (56%) still find it a little scary and 70% have concerns about data privacy.

“I know patients are concerned about the privacy and the security of their data, but we hold the artificial intelligence and this technology to the same standards that we hold our electronic medical record,” Tripathi said.

As of July 1, Ohio State expanded ambient documentation access to all providers in outpatient settings. In the first two weeks of expanded use, 100 clinicians regained 64 hours of time and satisfaction scores have improved from patients who say their conversations with their physicians were more valuable.

Survey Methodology

This study was conducted on behalf of The Ohio State University Comprehensive Cancer Center by SSRS on its Opinion Panel Omnibus platform. The SSRS Opinion Panel Omnibus is a national, twice-per-month, probability-based survey. Data collection was conducted from May 17 – 20, 2024, among a sample of 1,006 respondents. The survey was conducted via web (n=974) and telephone (n=32) and administered in English. The margin of error for total respondents is +/- 3.5 percentage points at the 95% confidence level. All SSRS Opinion Panel Omnibus data are weighted to represent the target population of U.S. adults ages 18 or older.

Video: Ohio State is thoughtfully implementing AI to help providers spend less time on the computer, and more time interacting with their patients.

view more Credit: The Ohio State University Wexner Medical Center

The researchers will present their results at the fall meeting of the American Chemical Society (ACS). ACS Fall 2024 is a hybrid meeting being held virtually and in person Aug. 18-22; it features about 10,000 presentations on a range of science topics.

AI’s vast number of uses has made it almost ubiquitous in today’s technological landscape. However, many AI models are black boxes, meaning it’s not clear exactly what steps are taken to produce a result. And when that result is something like a potential drug molecule, not understanding the steps might stir up skepticism with scientists and the public alike. “As scientists, we like justification,” explains Rebecca Davis, a chemistry professor at the University of Manitoba. “If we can come up with models that help provide some insight into how AI makes its decisions, it could potentially make scientists more comfortable with these methodologies.”

One way to provide that justification is with XAI. These machine learning algorithms can help us see behind the scenes of AI decision making. Though XAI can be applied in a variety of contexts, Davis’ research focuses on applying it to AI models for drug discovery, such as those used to predict new antibiotic candidates. Considering that thousands of candidate molecules can be screened and rejected to approve just one new drug — and antibiotic resistance is a continuous threat to the efficacy of existing drugs — accurate and efficient prediction models are critical. “I want to use XAI to better understand what information we need to teach computers chemistry,” says Hunter Sturm, a graduate student in chemistry in Davis’ lab who’s presenting the work at the meeting.

The researchers started their work by feeding databases of known drug molecules into an AI model that would predict whether a compound would have a biological effect. Then, they used an XAI model developed by collaborator Pascal Friederich at Germany’s Karlsruhe Institute of Technology to examine the specific parts of the drug molecules that led to the model’s prediction. This helped explain why a particular molecule had activity or not, according to the model, and that helped Davis and Sturm understand what an AI model might deem important and how it creates categories once it has examined many different compounds.

The researchers realized that XAI can see things that humans might have missed; it can consider far more variables and data points at once than a human brain. For example, when screening a set of penicillin molecules, the XAI found something interesting. “Many chemists think of penicillin’s core as the critical site for antibiotic activity,” says Davis. “But that’s not what the XAI saw.” Instead, it identified structures attached to that core as the critical factor in its classification, not the core itself. “This might be why some penicillin derivatives with that core show poor biological activity,” explains Davis.

In addition to identifying important molecular structures, the researchers hope to use XAI to improve predictive AI models. “XAI shows us what computer algorithms define as important for antibiotic activity,” explains Sturm. “We can then use this information to train an AI model on what it’s supposed to be looking for,” Davis adds.

Next, the team will partner with a microbiology lab to synthesize and test some of the compounds the improved AI models predict would work as antibiotics. Ultimately, they hope XAI will help chemists create better, or perhaps entirely different, antibiotic compounds, which could help stem the tide of antibiotic-resistant pathogens.

“AI causes a lot of distrust and uncertainty in people. But if we can ask AI to explain what it’s doing, there’s a greater likelihood that this technology will be accepted,” says Davis.

Sturm adds that he thinks AI applications in chemistry and drug discovery represent the future of the field. “Someone needs to lay the foundation. That’s what I hope I’m doing.”

The research was funded by the University of Manitoba, the Canadian Institutes of Health Research and the Digital Research Alliance of Canada.

A Q&A with the researcher will be posted on Sunday, Aug. 18. Reporters can access the video during the embargo period, and once the embargo is lifted the same URL will allow the public to access the content. Visit the ACS Fall 2024 program to learn more about this presentation, “Using Explainable Artificial Intelligence to explore the relationship between structure and activity,” and other science presentations.

This research was presented at a meeting of the American Chemical Society. ACS does not conduct research, but publishes and publicizes peer-reviewed scientific studies.

Trusted names including Hilary Jones, Michael Mosley and Rangan Chatterjee are being used to promote products claiming to fix high blood pressure and diabetes, and to sell hemp gummies, explains journalist Chris Stokel-Walker.

Deepfaking is the use of artificial intelligence (AI) to map a digital likeness of a real-life human being onto a video of a body that isn’t theirs. Reliable evidence on how convincing it is can be hard to come by, but one recent study suggests that up to half of all people shown deepfakes talking about scientific subjects cannot distinguish them from authentic videos.

John Cormack, a retired doctor based in Essex, worked with The BMJ to try and capture a sense of the scale of so-called deepfaked doctors across social media.

“The bottom line is, it’s much cheaper to spend your cash on making videos than it is on doing research and coming up with new products and getting them to market in the conventional way,” he says.

The slew of questionable content on social media co-opting the likenesses of popular doctors and celebrities is an inevitable consequence of the AI revolution we’re currently living through, says Henry Ajder, an expert on deepfake technology. “The rapid democratisation of accessible AI tools for voice cloning and avatar generation has transformed the fraud and impersonation landscape.”

“There’s been a significant increase in this kind of activity,” says Jones, who employs a social media specialist to trawl the web for deepfake videos that misrepresent his views and tries to take them down. “Even if you do, they just pop up the next day under a different name.”

A spokesperson for Meta, the company that owns both Facebook and Instagram, on which many of the videos found by Cormack were hosted, told The BMJ: “We will be investigating the examples highlighted by the British Medical Journal. We don’t permit content that intentionally deceives or seeks to defraud others, and we’re constantly working to improve detection and enforcement. We encourage anyone who sees content that might violate our policies to report it so we can investigate and take action.”

Deepfakes work by preying on people’s emotions, writes Stokel-Walker, and when it comes to medical products, that emotional connection with the individual telling you about the wonder drug or magnificent medical product matters all the more.

Someone you don’t know trying to sell you on the virtues of a particular treatment may raise suspicions. But if they’re someone you’ve seen before on social media, television or radio, you’re more likely to believe what they’re saying.

Spotting deepfakes can be tricky too, says Ajder, as the technology has improved. “It’s difficult to quantify how effective this new form of deepfake fraud is, but the growing volume of videos now circulating would suggest bad actors are having some success.”

For those whose likenesses are being co-opted, there’s seemingly very little they can do about it, but Stokel-Walker offers some tips on what to do if you find a deepfake. For instance, take a careful look at the content to make sure your suspicions are well-founded then leave a comment, questioning its veracity. Use the platform’s built-in reporting tools to voice your concerns, and finally report the person who or account that shared the post.

Researchers published their results in Big Data Mining and Analytics on April 22.

DED can affect a wide array of people, including those who wear contact lenses, makeup, stay up late, look at screens for a long time and are over 30 years old. Symptoms of this disease are dry eyes, irritation and burning, tears, eye fatigue and pain. One can easily see how this disease has the potential to drastically impact a large portion of the modern world’s population. Here is where the combined efforts of ophthalmic disease detection and the world of computer scientists and engineers can help.

“By addressing challenges, imparting insights, and delineating future research pathways, it contributes substantially to the advancement of ophthalmic disease detection through sophisticated technological modalities,” said Mini Han Wang, author and researcher.

There are seven facets to this AI-based disease detection. Timely intervention via the AI screening process and correct prognosis is the first part. The use of exhaustive surveys for DED through AI is another, and this is a supporting principle to ensure a level of thoroughness and trustworthiness throughout the process. A systematic approach follows, as well as the marriage of computer science and engineering with ophthalmology. Then, the standards for DED detection must be devised and upheld for future researchers and practitioners, which will naturally lead to the advancement of the field. Finally, all the research, methodologies and tools must be compiled so researchers, scholars and practitioners can have all of the information currently out there available to them.

While the ophthalmologists set the guidelines regarding the framework of the disease and flags for diagnosis, the AI does a lot of the heavy lifting. Ideally, this AI would use images and videos taken from a user’s cell phone to help reach users across the world. The AI can then utilize these images, as well as risk factors in the patient’s life, to make a smart and well-informed prognosis. Further, AI continuously learns and can help propel research forward by contributing to predictive models for DED.

The use of AI detection for DED holds a lot of promise, especially considering the risk factors are often normal activities in many people’s everyday lives. To make the detection methods accessible enough and accurate enough, further research needs to be done.

“However, there are still challenges for engineers to select the diagnostic standards and combinations of different types of datasets. By using trustworthy algorithms, images and videos captured from phones for accessibility purposes, a holistic approach to healthcare for early screening is possible,” said Wang.

With continued testing and collaboration between engineers and ophthalmologists, there is great potential for this method of testing to be useful in contributing to early screening of DED and subsequent therapeutic actions taken for the patient to reduce a worsening condition or to recover some quality of life.

Mini Han Wang and Xiangrong Yu of the Zhuhai People’s Hospital with Mini Han Wang also of the Department of Ophthalmology and Visual Sciences at the Chinese University of Hong Kong, The Faculty of Data Sciences at City University of Macau and the Department of big data at the Zhuhai Institute of Advanced Technology at the Chinese Academy of Sciences, Lumin Xing of the First Affiliated Hospital of Shandong First Medical University, Yi Pan of the Shenzhen Institute of Advanced Technology Chinese Academy of Sciences, Feng Gu of the College of Staten Island at the City University of New York, Junbin Fang at the Department of Optoelectronic Engineering at Jinan University, Chi Pui Pang, Kelvin KL Chong, Carol Yim-Lui Cheung and Xulin Liao of the Department of Ophthalmology and Visual Sciences at The Chinese University of Hong Kong, Xiaoxiao Fang with the Zhuhai Aier Eye Hospital, Jie Yang of the College of Artificial Intelligence at Chongqing Industry and Trade Polytechnic, Ruoyu Zhou and Wenjian Liu with the Faculty of Data Science at City University of Macao, Xiaoshu Zhou with the Centre for Science and Technology Exchange and Cooperation between China and Portuguese-Speaking Countries, and Fengling Wang with the School of Artificial Intelligence at Hezhou Univeristy contributed to this research.

The National Natural Science Foundation of China Natural, the Shenzhen Key Laboratory of Intelligent Bioinformatics, the Shenzhen Science and Technology Program, the Guangdong Basic and Applied Basic Research Foundation, the Zhuhai Technology and Research Foundation, the Project of Humanities and Social Science of MOE, the Science and Technology Research Program of Chongqing Municipal Education Commission and the Natural Science Foundation of Chongqing China made this research possible.

In a new study, researchers from the Mass General Brigham MESH Incubator found that ChatGPT, a generative artificial intelligence (AI) chatbot, showed promise as a tool to manage polypharmacy and deprescription. These findings, published April 18^th in the Journal of Medical Systems, demonstrate the first use case of AI models in medicine management.

To evaluate its utility, the investigators provided ChatGPT with different clinical scenarios and asked it a set of decision-making questions. Each scenario featured the same elderly patient taking a mixture of medications but included variations in cardiovascular disease history (CVD) and degree of impairment in activities of daily living (ADL).

When asked yes or no questions about reducing prescribed drugs, ChatGPT consistently recommended deprescribing medications in patients without a history of CVD. However, it was more cautious when overlying CVD was introduced, and more likely to keep the patient’s medication regimen unchanged. In both cases, the researchers observed that ADL impairment severity did not seem to affect decision outcomes.

The team also noted that ChatGPT had a tendency to disregard pain and favored deprescribing pain medications over other drug types like statins or antihypertensives. In addition, ChatGPT responses varied when presented with the same scenario in new chat sessions — which the authors suggest could reflect inconsistency in commonly reported clinical deprescribing trends on which the model was trained.

More than 40 percent of older adults meet the criteria for polypharmacy. The rate of seniors on Medicare seeing more specialists on their care teams has increased in recent years, leaving primary care providers to oversee medication management. An effective AI tool could help aid this practice, according to the researchers.

“Our study provides the first use case of ChatGPT as a clinical support tool for medication management,” said senior corresponding author Marc Succi, MD, Associate Chair of Innovation and Commercialization at Mass General Brigham Radiology and Executive Director of the MESH Incubator.  “While caution should be taken to increase accuracy of such models, AI-assisted polypharmacy management could help alleviate the increasing burden on general practitioners. Further research with specifically trained AI tools may significantly enhance the care of aging patients.”

Arya Rao, lead author, MESH researcher and Harvard Medical student, added “Our findings suggest that AI-based tools can play an important role in ensuring safe medication practices for older adults; it is imperative that we continue to refine these tools to account for the complexities of medical decision-making.”

Read more in the Journal of Medical Systems.

“For years, the debate has centred on how to improve the efficiency of healthcare. Thanks to advances in generative AI and language modelling, there are now opportunities to reduce the administrative burden on healthcare professionals. This will allow doctors to spend more time with their patients,” explains Cyrus Brodén, an orthopaedic physician and researcher at Uppsala University Hospital and Uppsala University.

Administrative tasks take up a large share of a doctor’s working hours, reducing the time for patient contact and contributing to a stressful work situation. Researchers at Uppsala University Hospital and Uppsala University, in collaboration with Danderyd Hospital and the University Hospital of Basel, Switzerland, have shown in a new study that the AI model ChatGPT can write administrative medical notes up to ten times faster than doctors without compromising quality.

The aim of the study was to assess the quality and effectiveness of the ChatGPT tool when producing medical record notes. The researchers used six virtual patient cases that mimicked real cases in both structure and content. Discharge documents for each case were generated by orthopaedic physicians. ChatGPT-4 was then asked to generate the same notes. The quality assessment was carried out by an expert panel of 15 people who were unaware of the source of the documents. As a secondary metric, the time required to create the documents was compared.

“The results show that ChatGPT-4 and human-generated notes are comparable in quality overall, but ChatGPT-4 produced discharge documents ten times faster than the doctors,” notes Brodén.

“Our interpretation is that advanced large language models like ChatGPT-4 have the potential to change the way we work with administrative tasks in healthcare. I believe that generative AI will have a major impact on healthcare and that this could be the beginning of a very exciting development,” he maintains.

The plan is to launch an in-depth study shortly, with researchers collecting 1,000 medical patient records. Again, the aim is to use ChatGPT to produce similar administrative notes in the patient records.

“This will be an interesting and resource-intensive project involving many partners. We are already working actively to fulfil all data management and confidentiality requirements to get the study under way,” concludes Brodén.

Rosenberg, G. S., Magnéli, M., Barle, N., Kontakis, M. G., Müller, A. M., Wittauer, M., Gordon, M., & Brodén, C.. 2024: ChatGPT-4 generates orthopedic discharge documents faster than humans maintaining comparable quality: a pilot study of 6 cases. Acta Orthopaedica, 95, 152-156. https://doi.org/10.2340/17453674.2024.40182

“This is important news for patients. Normally, it takes 6 to 8 weeks before it is known whether an antidepressant will work,” says Professor of Neuroradiology at Amsterdam UMC, Liesbeth Reneman.

The research team analysed whether they could predict the effect of the antidepressant sertraline, one of the most  commonly prescribed drugs in the United States and Europe. In a previous study conducted in the United States, MRI scans and clinical data were administered to 229 patients with major depression before and after a week of treatment with sertraline or placebo. The Amsterdam researchers then developed and applied an algorithm to this data to investigate whether they could predict the treatment response to sertraline.

This analysis showed that  1/3 of patients would respond to the drug and in 2/3 not. “With this method, we can already prevent 2/3 of the number of ‘erroneous’ prescriptions of sertraline and thus offer better quality of care for the patient. Because the drug also has side effects,” says Reneman.

The right drug, much faster
“The algorithm suggested that blood flow in the anterior cingulate cortex, the area of brain involved in emotion regulation, would be predictive of the efficacy of the drug. And at the second measurement, a week after the start, the severity of their symptoms turned out to be additionally predictive” says Eric Ruhé, psychiatrist at Radboudumc.

In the future, this new method may help to better tailor sertraline treatment to the individual patient. Currently, there is no exact prediction tool. The patient is given the medication and after 6 to 8 weeks – in practice often up to several months – it is checked whether the medication works. If the symptoms do not subside, the patient is given another antidepressant, and this process can repeat itself several times. This standard method often takes weeks, if not months. It also saves society costs, because as long as the patient continues to suffer from the serious depressive symptoms, he or she cannot fully participate in society.

Follow-up examination
In one in three depressed patients, there is still no improvement in the symptoms after several treatment steps. Therefore, there is an urgent need for a solution that allows a faster determination of the effectiveness of antidepressants in severe depression. In the coming period, the researchers will improve the algorithm by adding extra information.