Cedars-Sinai is a non-profit healthcare organization based in Los Angeles. It consists of hospitals, clinics and research facilities. Founded in 1902, Cedars-Sinai has over 40 locations, employing over 4,500 doctors and nurses, serving over 1 million patients each year.
Situation analysis
Caroline Goldzweig, chief medical officer at Cedars-Sinai Medical Network, told Business Insider that organizations want to expand access to primary care for patients in a more efficient and convenient way. For example, individual doctor appointments may have long waits.
At the same time, Goldzweig said the focus could be on providing care as organizations seek to reduce the administrative burden on physicians, including patient intake and data entry.
To address these challenges, the organization launched Cedars-Sinai Connect in 2023. CSConnect is an artificial intelligence-driven virtual platform that allows patients to access healthcare support 24/7.
Goldzweig said AI technology allows providers to improve the speed of care while supporting patients better. “One other exciting thing is the ability to provide patient care in a way that meets needs,” she said.
Caroline Goldzweig is the Chief Medical Officer of Cedars-Sinai Medical Network. Provided by Cedars-Sinai
Key staff and partners
Goldzweig told Business Insider that CS Connect was built using K Health, a digital healthcare company that provides primary and emergency care services with AI. The Cedars-Sinai information technology team worked with K Health to synchronize the patient's electronic health records to the platform, she said.
Cedars-Sinai's Enterprise Data Intelligence and Digital Strategy team was also involved in creating CS Connect. They continue to manage it.
AI Action
The goal of AI tools is to allow providers to spend more time counselling and making treatment decisions for patients, rather than taking patients.
To access AI features, the patient logs in to CS Connect via the mobile app or its website. Goldzweig said the chat feature will start asking questions about the user's symptoms.
The AI algorithm compares a patient's response to an existing medical record with records of other patients in the system with similar symptoms. Next, we ask more detailed questions about the patient's specific health issues. For example, a chatbot may encourage patients to submit photos of sore throats or rashes.
Goldzweig said the chat feature is similar to how doctors identify patients' illnesses.
AI summarises patient information (a task that usually requires manual effort from a physician) and recommends treatment.
The data collected by CS Connect is “part of the efficiency process,” Goldzweig said. “Doctors can review it, understand what's going on, and verify what they're doing with their patients. They can ask some clear questions and get a little more history.”
Doctors can choose to oppose AI recommendations. Goldzweig said that in any case, they should be enrolled in each patient's treatment plan.
CS Connect has a chatbot that allows users to ask about their symptoms and recommend treatment. Provided by Cedars-Sinai
It worked, and how did the leader know?
Goldzweig told BI that approximately 42,000 individual patients use CS Connect.
In April 2025, CEDARS-SINAI published a study in the journal Annals of Internal Medicine, comparing CS AI treatment recommendations with final recommendations from physicians.
This study reviewed 461 physician-administered visits with AI recommendations for respiratory, urinary, vaginal, eye, and dental symptoms. Results showed that AI proposals are often rated as high quality when AI and physician recommendations differ.
This study found that 77% of AI recommendations were rated as optimal and 67% of physician decisions were rated as optimal.
For example, patients with a recurring urinary tract infection may encounter antibiotic resistance. Goldzweig said the AI was successful in identifying these patients and recommended bacterial cultures before prescribing antibiotics. In contrast, doctors sometimes prescribe medication without a test, and she said the infection could return.
Goldzweig added that the study suggests that AI tools tend to focus on guidelines, but that physicians have the ability to adapt medical guidelines based on the nuances of patients' cases.
Goldzweig said the study has limitations. We examined only a small number of medical conditions and did not take into account the nuances of individual patient cases. Another limitation is that medical chart reviewers can check if recommendations have been made by AI or a doctor.
Cedars-Sinai is working to expand CS Connect. The organization uses AI to steer remote patient surveillance technology to help manage chronic diseases such as hypertension. They also plan to use AI technology to connect direct emergency care visits to virtual care.
