NEWS

What are you interested in?

All topics
Arts
Social Sciences
Life Sciences
Medicine
Management
Engineering
Law
Humanities
General
Exact Sciences
Environment

Research

Apr 15th, 2025
Can AI Help Doctors Make Better Diagnoses?

A new TAU study explores how accurate AI can be when assisting with diagnoses in virtual urgent care.

  • Medicine

A new study led by Prof. Dan Zeltzer, a digital health expert from the Berglas School of Economics at Tel Aviv University, compared the quality of diagnostic and treatment recommendations made by artificial intelligence (AI) and physicians at Cedars-Sinai Connect, a virtual urgent care clinic in Los Angeles, operated in collaboration with Israeli startup K Health. The paper was published in Annals of Internal Medicine and presented at the annual conference of the American College of Physicians (ACP). This work was supported by funding from K Health.

 

AI vs. Physicians in Virtual Care

Prof. Zeltzer explains: "Cedars-Sinai operates a virtual urgent care clinic offering telemedical consultations with physicians specializing in family and emergency care. Recently, an AI system was integrated into the clinic—an algorithm based on machine learning that conducts initial intake through a dedicated chat incorporates data from the patient’s medical record and provides the attending physician with detailed diagnostic and treatment suggestions at the start of the visit -including prescriptions, tests, and referrals. After interacting with the algorithm, patients proceed to a video visit with a physician who ultimately determines the diagnosis and treatment. To ensure reliable AI recommendations, the algorithm—trained on medical records from millions of cases—only offers suggestions when its confidence level is high, not recommending about one out of five cases. In this study, we compared the quality of the AI system's recommendations with the physicians' actual decisions in the clinic".

 

Prof. Dan Zeltzer (Photo courtesy of Richard Haldis).

 

The researchers examined a sample of 461 online clinic visits over one month during the summer of 2024. The study focused on adult patients with relatively common symptoms—respiratory, urinary, eye, vaginal and dental. In all visits reviewed, patients were initially assessed by the algorithm, which provided recommendations, and then treated by a physician in a video consultation. Afterward, all recommendations—from both the algorithm and the physicians—were evaluated by a panel of four doctors with at least ten years of clinical experience, who rated each recommendation on a four-point scale: optimal, reasonable, inadequate, or potentially harmful. The evaluators assessed the recommendations based on the patient's medical history, the information collected during the visit, and transcripts of the video consultations.

 

AI Proves More Accurate Than Physicians in Study

The compiled ratings led to interesting conclusions: AI recommendations were rated as optimal in 77% of cases, compared to only 67% of the physicians' decisions; at the other end of the scale, AI recommendations were rated as potentially harmful in a smaller portion of cases than physicians' decisions (2.8% of AI recommendations versus 4.6% of physicians' decisions).  In 68% of the cases, the AI and the physician received the same score; in 21% of cases, the algorithm scored higher than the physician; and in 11% of cases, the physician's decision was considered better.

 

The explanations provided by the evaluators for the differences in ratings highlight several advantages of the AI system over human physicians: First, the AI more strictly adheres to medical association guidelines—for example, not prescribing antibiotics for a viral infection; second, AI more comprehensively identifies relevant information in the medical record—such as recurrent cases of a similar infection that may influence the appropriate course of treatment; and third, AI more precisely identifies symptoms that could indicate a more serious condition, such as eye pain reported by a contact lens wearer, which could signal an infection. Physicians, on the other hand, are more flexible than the algorithm and have an advantage in assessing the patient's actual condition. For example, if a COVID-19 patient reports shortness of breath, a doctor may recognize it as relatively mild respiratory congestion, whereas the AI, based solely on the patient's answers, might refer them unnecessarily to the emergency room.

 

A Step Closer to Supporting Doctors

Prof. Zeltzer concludes: "In this study, we found that AI, based on a targeted intake process, can provide diagnostic and treatment recommendations that are, in many cases, more accurate than those made by physicians. One limitation of the study is that we do not know which physicians reviewed the AI's recommendations in the available chart, or to what extent they relied on the recommendations. Thus, the study only measured the accuracy of the algorithm’s recommendations and not their impact on the physicians. The study's uniqueness lies in the fact that it tested the algorithm in a real-world setting with actual cases, while most studies focus on examples from certification exams or textbooks. The relatively common conditions included in our study represent about two-thirds of the clinic's case volume, thus the findings can be meaningful for assessing AI's readiness to serve as a decision-support tool in medical practice. We can envision a near future in which algorithms assist in an increasing portion of medical decisions, bringing certain data to the doctor's attention, and facilitating faster decisions with fewer human errors. Of course, many questions remain about the best way to implement AI in the diagnostic and treatment process, as well as the optimal integration between human expertise and artificial intelligence in medicine".

 

Other authors involved in the study include Zehavi Kugler, MD; Lior Hayat, MD; Tamar Brufman, MD; Ran Ilan Ber, PhD; Keren Leibovich, PhD; Tom Beer, MSc; and Ilan Frank, MSc. Caroline Goldzweig, MD MSHS, and Joshua Pevnick, MD, MSHS.

Research

Apr 10th, 2025
This Is Why Children Took Part in Creating Prehistoric Cave Art

TAU study suggests that children were seen as mediators between the physical and spiritual worlds.

  • Humanities
  • Archeology

A team of Tel Aviv University researchers from prehistoric archaeology has proposed an innovative hypothesis regarding an intriguing question: Why did ancient humans bring their young children to cave painting sites, deep underground - through dark, meandering, hazardous passages? The researchers explain: “Next to many cave paintings, there is clear evidence of children as young as two. So far, most hypotheses have focused on the educational aspect — learning the community's traditions and customs. However, we believe that children also played a unique cultural role in these caves: Young children were credited with special qualities in the spiritual world, enabling them to communicate with entities from the beyond – which were believed to be accessible from the depths of the cave”.

 

The study was conducted by Dr. Ella Assaf, Dr. Yafit Kedar, and Prof. Ran Barkai from the Jacob M. Alkow Department of Archaeology and Ancient Near Eastern Cultures at Tel Aviv University. The paper was published in the journal Arts from MDPI.

 

Dr. Ella Assaf.

 

Children's Role in Cave Art: More Than Just Education

Dr. Assaf explains: “Cave art created by early humans is a fascinating phenomenon that intrigues many researchers. To date, around 400 caves containing cave art have been discovered, mainly in France and Spain, with the artwork dated between 40,000 and 12,000 years ago. There is solid evidence of children's participation in the artwork - handprints and finger paintings made by children aged two to twelve. In addition, footprints and handprints of children have been found in some caves, alongside those of adults. This naturally raises the question: Why were the children there? Why were young children taken on exhausting and hazardous journeys deep into the dark, meandering caves with low oxygen levels - crawling through crevices, descending shafts, and climbing rocks to reach their destination?

 

Finger paintings made by children in Rouffignac Cave, 14,000 to 20,000 years ago (Photo courtesy of Dr. Van Gelder).

 

Dr. Kedar elaborates: “Despite extensive research on cave art, few studies have focused on the presence of children. The prevailing hypothesis is that their participation served an educational purpose - passing down knowledge, traditions, and customs to the next generation. In our study, we argue that children's involvement had an additional meaning: In fact, they played an important, unique role of their own - direct communication with entities residing in the depths of the earth and otherworldly realms. This study follows our previous works, in which we presented cave artworks as expressions of cosmological approaches, with emphasis on relationships between humans and various entities”.

 

Children as Mediators Between Worlds in Ancient Rituals

Dr. Assaf adds: “Based on extensive studies about children in indigenous societies, along with new insights into rituals performed in caves with cave paintings, a new understanding is emerging regarding the role of children in the creation of cave art. By integrating data from these research fields, we were able, for the first time, to propose a novel and original explanation for the inclusion of children in creating cave paintings:  The world of childhood differs from that of adults, and children possess a range of unique mental and cognitive traits. For this reason, indigenous cultures worldwide, throughout history and prehistory, have viewed children as 'active agents' - mediators between this world and the entities inhabiting the natural world, the underworld, and the cosmos as a whole. In this way, children made a vital contribution to their communities - hunter-gatherers who lived in nature and sought to maintain continuous, respectful relationships with various entities: animals and plants that served as food sources, stones used for toolmaking, ancestral spirits, and more”.

 

Children’s footprints from Basura Cave, 14,000 years ago (Photo courtesy of Prof. Marco Romano – Romano et al. 2019).

 

Prof. Barkai: “Many of these societies regarded caves as gateways to the underworld - where, through shamanic rituals, they could communicate with cosmic entities and inhabitants of the underworld, to resolve existential problems. In this context, young children were perceived as liminal beings - belonging to both the realm they had left just recently (before birth) and the world they currently inhabit. Thus, small children were considered particularly suited to bridging the gap between the worlds and delivering messages to non-human entities. In this paper, we connect these insights and propose that children joined adults on journeys into the depths of caves and participated in painting and rituals as part of their role in the community—as ideal mediators with entities from the beyond”.

 

Prof. Ran Barkai.

Tel Aviv University makes every effort to respect copyright. If you own copyright to the content contained
here and / or the use of such content is in your opinion infringing Contact us as soon as possible >>