Artificial intelligence now plays a direct role in how clinicians detect disease, prioritize cases, and coordinate care. At Qure.ai, the role spans radiology, emergency medicine, infectious disease, and clinical research across health systems worldwide. Jim Mercadante, Chief Commercial Officer at Qure.ai, joined the company after more than two decades in medtech and healthcare technology, including leadership roles at Abbott, Johnson & Johnson, GE, Terumo, and RapidAI. Today, Jim focuses on scaling AI solutions that work inside real clinical workflows. Jim explains to how Qure.ai approaches early detection, clinical coordination, and global deployment.
Jim, what values and services define Qure.ai?
Qure.ai is a healthcare AI company specializing in diagnostic support and care management. We create tools that help clinicians spot lung nodules, neurocritical findings, and infectious diseases earlier in the care pathway. Our aim is to empower clinicians to make quicker decisions, start treatment sooner, and streamline care coordination.
Qure.ai started in 2016 and now has teams in New York, London, Dubai, and Mumbai. You’ll find our solutions in over 105 countries and more than 4,800 clinical sites. In the US, we have 19 FDA-cleared findings for lung and neurocritical conditions. Globally, we support 65 CE-certified findings and multiple national validations. In 2025, TIME named Qure.ai in its TIME100 Most Influential Companies for expanding access to diagnosis for high-burden diseases.
How does Qure.ai’s AI support earlier lung cancer detection?
Lung cancer is still the leading cause of cancer-related death in the US, and late diagnosis is a big reason why. Our lung portfolio helps by making detection, measurement, and patient management easier across different imaging types.
We provide an FDA-cleared suite of tools that clinicians can use as standalone tools or together in a single workflow. Our Chest X-ray AI spots lung nodules incidentally, while our CT-based tools handle measurement, quantification, and follow-up. When teams combine these tools, the benefits grow throughout the care pathway. We call this approach “image to intervention”; supporting every step from detection to diagnosis and treatment coordination.
At University Hospitals Cleveland Medical Center in Ohio, our Chest X-ray AI acts as a second reader for radiologists. It helps with lung cancer surveillance during routine imaging, including emergency department and pre-op scans. This approach works alongside CT screening programs that focus on high-risk groups.
In areas with limited CT screening, our Chest X-ray AI increases access to screening. One recent example is the CREATE study with AstraZeneca, presented at the 2025 European Society for Medical Oncology Congress. The study used routine chest X-rays to evaluate our AI-powered Lung Nodule Malignancy Score in Egypt, India, Indonesia, Mexico, and Turkey.
Out of more than 700 participants, our system identified 96 percent of confirmed lung cancer cases. Nearly 60 percent were in people who never smoked, including some under age 50. We detected 46 percent of cases at stages I to III, when treatment options are wider.
How does AI improve response in neurocritical care?
In neurocritical care, timing is everything. Our head CT solution quickly triages intracranial hemorrhages and other critical findings. The system flags scans in minutes so care teams can respond right away.
Our solution helps emergency physicians, neurologists, and neurosurgeons by cutting down delays between imaging and intervention. It delivers 97 percent sensitivity for intracranial hemorrhage triage and enables 6 times more patients to be treated within 30 minutes of CT imaging.
Clinicians always make the final call. Our AI ensures urgent cases move up in the workflow, especially in busy settings where high volumes can slow things down.
How does Qure.ai support pharmaceutical trials?
Every pharmaceutical partnership is unique. In some trials, we help identify patients with specific disease characteristics. In others, we use imaging biomarkers as endpoints to measure treatment response or disease progression.
Our tools standardize measurements like lung nodule size, volume, and growth across different sites and patient groups. The consistency makes data easier to compare, which is crucial for regulatory submissions and statistical analysis.
In infectious disease research, we’re supporting a tuberculosis trial where our AI quantifies pulmonary cavities. The system measures cavity count and size, helping with patient stratification and tracking treatment response. This type of standardized imaging data enables trials run more efficiently.
How does Qure.ai adapt AI for different healthcare systems globally?
Deploying AI in over 105 countries means staying flexible. We train our algorithms on more than a billion data sets from diverse regions, imaging types, age groups, and populations. This broad approach ensures our AI performs well in any care setting, from big-city hospitals to rural clinics.
Having the right representation in our training data is key when AI enters frontline care. We build our systems to fit within any existing infrastructure, whether it’s advanced or more limited.
What innovations is Qure.ai working on next?
In early 2026, we received a multi-million-dollar grant from the Gates Foundation to advance di-agnostics for tuberculosis and pneumonia in under-resourced areas. We’re partnering with the World Health Organisation to support global lung health diagnostic pathways.
The database will feature de-identified clinical histories, chest X-rays, thoracic ultrasounds, high-resolution CT scans, cough recordings, and lab markers. This resource will help researchers worldwide develop and validate new AI models.
The grant also supports developing of AI-enabled point-of-care ultrasound tools to detect TB and pneumonia early. Both diseases are curable when diagnosed in time. TB causes about 1.23 million deaths a year, and pneumonia causes about 2 million deaths annually, including 700,000 children under five.
How do you see AI shaping healthcare in the next 12 to 18 months?
We’re shifting from isolated AI tools to connected systems that link detection, patient management, and population insights. Agentic AI and large language models will make it easier for data to flow between devices, providers, and patients.
The focus must stay practical. Success comes from building systems clinicians use every day, not from standalone algorithms that sit outside real care delivery.
For Jim, moving healthcare AI forward depends on real-world deployment, not just theory. At Qure.ai, we focus on building systems that fit clinical reality, help clinicians make earlier decisions, and improve coordination across the board. As health systems deal with uneven resources and growing demand, its approach reflects a shift toward AI that clinicians trust, patients experience, and systems can sustain.
Qure.ai is a health tech company using deep learning to interpret medical imaging and make healthcare more equitable worldwide, with FGDA-cleared AI solutions that detect and manage conditions like tuberculosis, lung cancer, pediatric TB and stroke while helping clinicians prioritize treatment and improve patient quality of life.
