Are AI-Enabled Biomarkers Shaping the Future of Early Cancer Diagnosis?

Cancer care is undergoing a fundamental shift. For decades, oncology relied on population averages, standardized protocols, and retrospective indicators to guide treatment. While this approach delivered scale, it often failed to account for individual risk, disease biology, and variability in outcomes. Today, precision oncology is redefining this paradigm placing the right patient, at the right time, on the right treatment pathway. At the center of this transformation lies a powerful enabler: AI-enabled biomarkers, which are increasingly enabling incidental detection &amp; stage shift in cancer care.

Precision oncology moves beyond a one-size-fits-all model toward individualized decision-making informed by data, biology, and risk. It enables care to move upstream, allowing clinicians to intervene with precision by aligning diagnostics, surveillance, and therapy to patient specific risk profiles.

This shift is driven by a simple but critical insight: timing matters. Identifying which patients need immediate escalation versus those who can be safely monitored directly impacts outcomes, resource utilization, and patient experience. Risk stratification is shaping treatment readiness, and it increasingly begins earlier than ever before in the care pathway, frequently triggered by incidental signals on routine imaging, creating opportunities for earlier diagnosis and downstream stage shift.

AI-enabled biomarkers represent a new class of clinical insight. Rather than relying on a single molecular signal, these biomarkers leverage machine learning to extract complex patterns from routine clinical data such as medical images. By analyzing thousands of subtle features simultaneously, AI brings scale, consistency, and earlier insights into incidental cancer detection risk and treatment readiness.

AI Biomarkers in Early Risk Stratification

One of the most significant shifts enabled by AI is that biomarkers are moving upstream. Risk stratification no longer begins after diagnosis; it increasingly starts at the point of first clinical contact or initial imaging.

This upstream approach has profound clinical and operational value. Earlier identification of high-risk patients enables faster diagnostic escalation, more efficient referral pathways, reduced delays in treatment initiation, and better allocation of specialist and imaging resources, all of which contribute to stage shift and early diagnosis.

Case Example: Qure’s AI Derived Imaging Biomarkers

A clear illustration of this shift is the Lung Nodule Malignancy Score (LNMS) developed by <a href="https://www.qure.ai/us">Qure.ai</a>. LNMS is a patented AI-derived biomarker designed to assess malignancy risk in lung nodules on <a href="https://www.qure.ai/product/qxr">chest X-rays</a>.

By analyzing radiographic patterns , the tool distinguishes higher-risk nodules from lower-risk ones early in the pathway.

The impact is tangible. Clinicians gain immediate insight into which patients warrant accelerated diagnostics and which can be monitored safely. This enables earlier diagnostic decisions, improved patient prioritization, and stronger precision oncology workflow without changing existing imaging practices, thereby increasing likelihood of detecting cancer at an earlier stage.

The true value of AI derived imaging biomarkers lies behind the pathway. Insights generated by AI do not exist in isolation; they inform downstream clinical actions.

Risk stratification influences decisions such as escalation of imaging or biopsy, urgency of specialist referrals, and treatment sequencing. By embedding AI-derived risk insights into routine workflows, care teams can move from reactive decision-making to proactive, data-informed action thereby enabling early diagnosis.

Broader Implications for Oncology and Clinical Trials

Beyond clinical care, AI derived imaging biomarkers are reshaping oncology research and drug development. By improving patient selection and eligibility matching, AI-enabled biomarkers can accelerate clinical trial enrollment, and improve outcome predictability.

AI derived imaging biomarkers are no longer experimental concepts they are becoming foundational infrastructure for modern cancer care. By moving risk stratification upstream, informing treatment readiness, and translating insight into action, they strengthen every layer of the precision oncology ecosystem.

As these tools mature, they will continue to complement and amplify precision medicine driving earlier intervention, smarter pathways, and better outcomes for patients worldwide.

large_blog_thumbnail.webp

medium_blog_thumbnail.webp

small_blog_thumbnail.webp

thumbnail_blog_thumbnail.webp

blog_thumbnail.webp

How AI-Enabled Biomarkers Improve Early Cancer Diagnosis.

Working at Qure.ai, much of my reading revolves around healthcare, the devastating impact of diseases like tuberculosis (TB), and the transformative role AI can play in addressing these challenges. But <a href="https://www.cdc.gov/tb/stories/mary.html" target="_blank">a story</a> I came across recently stood out as a poignant reminder of why this work matters and the driving force behind everything I strive to articulate.&nbsp;

Seventeen-month-old Zemira was a vibrant, active child, eagerly hitting her developmental milestones; calling out “mama,” climbing couches, and exploring her world with curiosity. But after a trip to the Philippines, her parents began noticing troubling changes. Zemira grew lethargic, lost her appetite, and started vomiting daily. What followed was a whirlwind of tests and an extended hospital stay that eventually confirmed the diagnosis: tuberculosis.&nbsp;&nbsp;

For her parents, the diagnosis was both shocking and terrifying. Thanks to timely intervention and months of treatment, Zemira made a full recovery. But her story underscores the fact that while Zemira was fortunate, the silent persistence of TB means countless children across the world devastated by it are not as lucky, as they continue to face delayed diagnoses and a lack of access to life-saving care.&nbsp;

From the highlands of Lesotho to the remote, rural villages of Bihar, and the underserved communities of Nigeria, Qure.ai is working hand in hand with local partners to bridge critical gaps in pediatric TB care through the power of AI.&nbsp;&nbsp;

Every one of these regions reveals a story far beyond numbers. A story of children who are often invisible in the global fight against TB. They remind us that children are not statistics; they are lives full of potential waiting to be saved. Every intervention matters, and AI can overcome geographical, social, and systemic barriers, ensuring that no child, no matter how distant or disadvantaged, is left behind.&nbsp;

The <a href="https://www.who.int/teams/global-tuberculosis-programme/tb-reports/global-tuberculosis-report-2024" target="_blank">WHO Global TB Report 2024</a> reveals that an estimated 1.29 million children and adolescents under 15 years of age fell ill with TB, accounting for about 12% of the global TB incidence of 10.8 million cases. Even more distressing is the fact that 15% of all TB-related deaths among HIV-negative individuals in 2023 were children and young adolescents. This stark reality underscores the preventable and curable nature of TB, making these deaths not only tragic but also a grim reminder of the vulnerability of children due to systemic gaps in timely access to care.&nbsp;

While global efforts to combat TB have intensified, significant challenges persist. Nearly half of all children affected by TB remain undiagnosed and untreated, highlighting critical diagnostic and treatment gaps. The enduring global pediatric TB burden emphasizes the need for equitable and innovative solutions to address these systemic barriers and ensure every child receives the care they deserve. Today, AI healthcare solutions offer innovative approaches to address these long-standing challenges. In pediatric TB, where nonspecific symptoms and diagnostic difficulties often delay treatment, AI-driven solutions like Qure.ai’s qXR and qTrack are helping to reinforce health systems.&nbsp;

qXR is the world's most widely used AI for comprehensive chest X-ray reporting, providing pre-read assistance in &lt;1 minute with detailed lung findings. &nbsp;qTrack is an end-to-end AI-powered disease &amp; program management platform for tuberculosis through smart prompts, hardware-agnostic image viewing for AI-annotated Chest X-Rays and CTs, cross-departmental scan sharing, and custom notifications for suspect cases.&nbsp;

Qure.ai offers the only comprehensive digital solution for Pediatric TB detection and management, addressing both clinical and operational complexities with precision and reliability. Its AI-powered CXR screening supports WHO’s <a href="https://www.who.int/news/item/15-05-2023-tdr-and-who-announce-tda4child--an-operational-research-package-to-generate-data-on-treatment-decision-algorithms-for-pulmonary-tuberculosis-in-children" target="_blank">Treatment Decision Algorithm</a> (TDA) A, facilitating early detection and improved case management. This solution is WHO-evaluated* and CE MDR-certified#, ensuring they meet global safety and performance standards.&nbsp;

Built using gold standard microbiologically tested pediatric CXRs and clinically diagnosed cases, and validated through rigorous internal studies Qure.ai’s technology is finely tuned to handle the unique challenges of diagnosing TB in children. The solutions empower healthcare providers in resource-constrained settings to confidently identify and treat cases, reducing turnaround times and enabling timely interventions for high-risk groups.&nbsp;

In Africa, our pediatric TB initiative in collaboration with Partners in Health (PIH) Lesotho is strengthening health systems and improving outcomes. Qure’s AI-powered solutions have enabled screenings in Lebakeng, evaluating over 200 children since the program’s inception. These efforts are not just about numbers but about transforming lives, ensuring children previously excluded from healthcare access are now reached in the fight against TB.&nbsp;

Qure.ai is also working with Janna Health Nigeria to expand pediatric TB screenings. Operating in resource-constrained settings, these partnerships highlight the critical role of AI in closing diagnostic gaps and advancing equitable care pathways for children.&nbsp;

In the recent past, an Active Case Finding (ACF) initiative in rural India, screened over 1,100 children across 10 villages, with Qure.ai’s qXR identifying 33 presumptive TB cases. Despite logistical challenges, including villages up to 100 kilometers away, the initiative demonstrated the importance of community-based healthcare and the role of AI in addressing gaps for key and vulnerable populations.&nbsp;

Even so, the fact remains that the disparity in TB diagnosis rates is not just a healthcare challenge. It is a social justice issue. The WHO <a href="https://www.who.int/news/item/20-11-2024-inclusion-for-every-child--reaching-every-child-affected-by-tuberculosis" target="_blank">reported</a> that only 42% of eligible household contacts aged under five received TB preventive care, reflecting inequities in service delivery. AI-powered solutions like qXR and qTrack offer scalable, cost-effective solutions that aligns with global priorities:&nbsp;

•	Strengthening Health Systems: By supporting healthcare workers with AI-driven insights, even non-specialists in remote areas can diagnose TB with confidence.&nbsp;

•	Focusing on Key and Vulnerable Populations: AI identifies high-risk groups, such as children under five or those living in TB-affected households, enabling targeted interventions.&nbsp;

•	Bridging Policy-Practice Gaps: AI complements WHO’s updated Roadmap toward ending TB in children, offering practical solutions to address persistent inequities.&nbsp;

Ending TB in children requires a unified effort, including policy support to secure funding for AI driven solutions, training healthcare workers to effectively use AI technologies, and scaling innovations to ensure that no region or community is left behind.&nbsp;

The effort against pediatric TB is as much about inclusion as innovation. AI has the power to bridge care gaps, strengthen health systems, and ensure every child can receive timely, effective TB care. The question remains: are we ready to harness this potential and create a world where no child’s future is stolen by TB?&nbsp;

large_Harnessing AI to Combat Pediatric TB-02.png

medium_Harnessing AI to Combat Pediatric TB-02.png

small_Harnessing AI to Combat Pediatric TB-02.png

thumbnail_Harnessing AI to Combat Pediatric TB-02.png

Harnessing AI to Combat Pediatric TB-02.png

Fighting Child Mortality: Is AI the Missing Link?

Stroke care has always been both my passion and my purpose. Over decades of refining my expertise in neurosurgery, ranging from conventional to advanced microneurosurgery and interventional techniques, I’ve witnessed the evolution of treatments and technologies firsthand. From performing over 10,000 neurosurgeries and 2,000 endovascular procedures to mentoring younger stroke teams, the journey has been as challenging as it has been fulfilling.&nbsp;

Despite advancements, the reality of stroke care in India remains sobering. Stroke affects approximately 1.8 million people in India annually, with an incidence rate of 105–152 per 100,000 individuals per year. The burden is even heavier in rural and underserved regions, where access to timely, specialized care is limited. Neurology itself is a challenging field, with fewer than one neurologist available per 100,000 people across the country (<a href="https://stroke-india.org/" target="_blank">Indian Stroke Association</a>, <a href="https://journals.sagepub.com/" target="_blank">SAGE Journals</a>). This gap highlights the pressing need for innovative solutions to bridge the disparity in stroke care.

Connecting the Dots: The Hub-and-Spoke Model &nbsp;

Zydus Hospitals became the first to adopt Qure.ai’s AI-powered patient management platform, the Qure app, for a hub-and-spoke model of stroke treatment, thanks to the collaboration with Medtronic. I was eager to help integrate the platform, train stroke teams, and witness its impact across our network. Before this deployment, guiding teams in peripheral hospitals was a logistical challenge. Physicians would share videos of scans – NCCTs, MRIs – manually, which led to delays, low-quality images, and limited real-time feedback. Discussions about treatment plans often required phone calls or occasional site visits, making collaborative decision-making cumbersome. &nbsp;

The Qure App changed everything. Today, I’m seamlessly connected to stroke teams in our peripheral hospitals, regardless of where I am, whether at my office, at home, or even between surgeries. Through the app, I can review high-resolution scans in real time on my phone, discuss treatment plans instantly, and declare emergencies like “code stroke” at the push of a button. This streamlined workflow ensures that every second counts, giving patients the best chance at recovery. &nbsp;

Empowering Stroke Teams with Confidence &nbsp;

Over the past year, the transformation has been extraordinary. Six months after adopting the Qure platform, our spoke teams began performing thrombolysis independently, often initiating treatment right at the CT scan table. Real-time guidance through the Qure App has given them the confidence to diagnose strokes and prepare treatment protocols with minimal intervention from our central hub. &nbsp;

In one instance, I remember receiving a scan on the app late at night. The team at the spoke center had already prepared the patient for thrombolysis and simply needed my go-ahead. Within minutes, they administered the treatment, saving precious time and significantly improving the patient’s prognosis. &nbsp; &nbsp;The numbers speak for themselves. In just a year, we’ve performed over 100 thrombolysis procedures in peripheral hospitals, a remarkable 100% increase, while facilitating more than 45 mechanical thrombectomies, reflecting a 43% rise. Additionally, the door-to-needle time has been reduced to under 4 hours, a critical milestone in improving stroke care outcomes. These achievements underscore the exponential increase in the efficiency and effectiveness of stroke care within our network, demonstrating the transformative potential of AI-powered coordination and support. &nbsp;

A Vision for the Future of Stroke Care &nbsp;

For me, this journey is not just about treating individual cases—it’s about shaping the future of stroke care in India. Neurology is inherently a demanding branch, and mentorship opportunities are scarce. The Qure App has not only enabled better patient outcomes but has also bridged a crucial gap in training. &nbsp;

By fostering collaborative decision-making, the platform has empowered stroke teams to act swiftly and confidently, ensuring that more patients receive timely, high-quality care. With AI providing advanced insights, healthcare providers can make faster, more informed decisions while improving coordination between hub and spoke hospitals. This seamless care coordination minimizes delays in diagnosis and treatment, which is critical in addressing the devastating consequences of stroke. &nbsp;

What excites me most is witnessing the shift in mindset among our spoke teams. They now approach stroke care with the assurance that comes from real-time support, advanced AI-driven guidance, and the ability to make life-saving decisions independently. It is this blend of AI-powered precision and human expertise that is paving the way for transformative changes in stroke care across India.&nbsp;

Transforming Stroke Care Nationwide &nbsp;

The hub-and-spoke model integrated with AI technology has proven to be a game-changer in addressing India’s stroke burden. Studies have shown that similar models, when combined with telemedicine, lead to increased thrombolysis rates and reduced morbidity (<a href="https://karger.com/" target="_blank">Karger</a>). By replicating this approach across India, we can ensure that no stroke patient is left without timely and effective care. &nbsp;

As I continue to mentor the next generation of stroke teams, my hope is to see this model adopted nationwide, creating a legacy of impact that ensures equitable access to high-quality stroke care for all. &nbsp;

Other References: &nbsp; &nbsp;

large_Banner 2.jpg

medium_Banner 2.jpg

small_Banner 2.jpg

thumbnail_Banner 2.jpg

Banner 2.jpg

Guiding the Next Generation of Stroke Teams with Qure.ai’s AI-Powered Solutions

Each year approximately 2 billion chest X-rays are performed globally. They are fast, noninvasive, and relatively inexpensive radiological examinations for front-line diagnostics in outpatient, emergency, or community settings.&nbsp;

Be it serendipitous screening, opportunistic detection, or incidental identification, there is potential for AI incorporated into CXR to screen patients for disease when they are getting an unrelated medical examination.&nbsp;

AI can find these&nbsp;abnormalities and flag them to clinicians as a suspicious finding for further investigation.&nbsp;

Indeed, only 5.8%&nbsp;of eligible ex-smoking Americans undergo CT-based lung cancer screening.&nbsp;

Early global studies&nbsp;into the power of AI for incidental pulmonary nodules (IPNs) shows exciting promise.

The&nbsp;<a href="https://www.qure.ai/product/lung-nodule-management" target="_blank">qXR-LN</a>&nbsp;chest X-ray AI algorithm&nbsp;from Qure.ai is raising the bar for incidental pulmonary nodule detection. In a retrospective study performed on missed or mislabelled US CXR data, qXR-LN achieved an impressive negative predictive value of 96% and an AUC score of 0.99 for detection of pulmonary nodules.&nbsp;

The FDA-cleared solution&nbsp;serves as a crucial second reader, assisting in the review of chest radiographs on the frontal projection.&nbsp;

By harnessing the power of AI for opportunistic lung cancer surveillance, healthcare providers can adopt a proactive approach to early detection, without significant new investment, and ultimately improving patient survival rates.

Note:&nbsp;<a href="https://theimagingwire.com/2024/11/07/chest-x-ray-an-important-tool-for-early-lung-cancer-detection/">First published in Imaging Wire, November 14 2024</a>

large_Early Lung Cancer Detection-01.jpg

medium_Early Lung Cancer Detection-01.jpg

small_Early Lung Cancer Detection-01.jpg

thumbnail_Early Lung Cancer Detection-01.jpg

Early Lung Cancer Detection-01.jpg

Future of AI-Powered Incidental Pulmonary Nodule Detection

From Ancient Times to Activating AI: How scientific discoveries and inventions have shaped the field of respiratory medicine and pulmonology&nbsp;&nbsp;

From the earliest discoveries of respiratory diseases to the modern-day AI-driven innovations, the journey of lung health has been marked by significant discoveries, inventions and milestones.&nbsp;&nbsp;

Lung cancer, once considered a rare medical curiosity, has become a global health challenge. While tobacco use remains a significant risk factor, other elements such as second-hand smoking, radon, occupational hazards, pollution, and genetics also contribute to the development of lung cancer.&nbsp;&nbsp;

Innovations to understand &amp; fight against Lung Cancer&nbsp;

The first historical observation of Lung Cancer was in the 1800s by Dr Laennec, a French physician, who described lesions in the lungs that were different to tuberculosis (TB). By 1823 the Lancet Journal is launched, promoting postmortems or autopsies to identify lung cancer as a separate diagnosis to TB.&nbsp;

In 1895, Wilhelm Roentgen pioneered the production and detection of electromagnetic radiation in a wavelength, x-radiation, to be known as X-rays. It was an achievement that earned him the inaugural Nobel Prize for Physics in 1901 and its use in medical applications soon followed shortly.&nbsp;

Fast forward to today, nearly 130 years since the invention of X-ray, plain film radiography is the mainstay of frontline medical imaging, with an estimated 2 billion chest X-rays alone performed per year globally.&nbsp;&nbsp;

The popularity and versatility of X-ray has stood the test of time with a number of innovations expanding its use and application to serve a wider range of patient communities across health boundaries. This includes the move from analogue to filmless and chemical free digital radiography; portability of detector plates to refashion the traditionally fixed systems onto wheels to take directly to patient bedsides or outpatient clinics; and the shrinking of X-ray solutions into easy-to-carry systems that fit into backpacks or flight cases to reach remote and rural communities.&nbsp;&nbsp;

The invention of Computed Tomography (CT) in the the late 1960s and its application into medicine in the early 1970s revolutionized medical imaging. Unlike traditional X-rays, which provide limited two-dimensional views, CT scans offered detailed cross-sectional slice images of the lungs, allowing for more precise visualization. This positioned CT as the gold standard for lung cancer screening in many developed nations, as it can detect small nodules or abnormalities, leading to earlier diagnoses and better survival rates.&nbsp;

Low-Dose CT is still central to proactive lung cancer screening programs in place across the world for high-risk groups such as ex or current smokers. These programs have reduced lung cancer mortality by enabling earlier identifications leading to interventions.&nbsp;

The timeline of testing for and tackling rates of TB

AI powering the future of early identification of disease&nbsp;

Today, AI is transforming the landscape of lung health identification and management using medical imaging.&nbsp;&nbsp;

AI solutions, like <a href="https://www.qure.ai/product/lung-nodule-management" target="_blank">qXR from Qure.ai</a>, analyze chest X-rays, detecting the risk of even the smallest nodules that could indicate early-stage cancer. X-ray-based surveillance as part of Incidental Pulmonary Nodule initiatives, also known as incidental nodule detection, are growing in strength.&nbsp;&nbsp;

AI's applications also extend beyond detection, with solutions like <a href="https://www.qure.ai/product/lung-nodule-management" target="_blank">qCT</a> that helps with precise qualification, comprehensive characterization and 3D visualization. Recently <a href="https://www.qure.ai/news_press_coverages/qure.ai-launches-FDA-cleared-AI-solution-for-advanced-lung-nodule-quantification-on-CT-scans-at-AABIP-2024" target="_blank">qCT LN Quant gained US FDA clearence</a> to support radiologists and pulmonologists in analyzing lung nodules on non-contrast CT scans and tracking volumetric growth as part of progression monitoring.&nbsp;&nbsp;

AI is also playing a crucial role in the fight against TB. <a href="https://www.qure.ai/global-health" target="_blank">Qure.ai's qXR can detect TB</a> on chest X-rays with high accuracy, helping to identify cases early and initiate timely treatment. AI also aids in contact tracing, predicting disease spread, and optimizing resource allocation in TB control programs.&nbsp;

The future of AI in TB care includes possibilities such as AI-guided personalized treatment regimens, AI-powered adherence monitoring, and AI-driven drug discovery for novel TB therapies. As we continue to battle this antiquated disease, AI offers hope for a future where TB is effectively controlled and ultimately eliminated.&nbsp;

The Future of AI in Lung Health Care&nbsp;

The developmental trajectory of lung health, from ancient times to the AI-driven present, is a testament to human resilience and innovation. As we observe the International Day of Radiology and Lung Cancer Awareness Month, we must celebrate the progress made in lung cancer care and TB detection, while recognizing the critical role of AI in shaping the future of lung health.&nbsp;

By harnessing the power of AI, we can accelerate early detection, improve treatment outcomes, and ultimately save lives. As we stand on the brink of a new era in lung health, let us embrace AI's potential to transform the way we prevent, identify, and treat respiratory diseases, paving the way for a healthier future for all.

large_Past_Present_Future-02.webp

medium_Past_Present_Future-02.webp

small_Past_Present_Future-02.webp

thumbnail_Past_Present_Future-02.webp

Past_Present_Future-02.webp

The Past, Present & Future of Lung Cancer

A discussion of how innovations in assistive medical device technology such as robotic bronchoscopy and novel medical imaging AI can be game changers for the early detection of lung cancer and early-stage treatment planning.&nbsp;

In pulmonary medicine, early Incidental Pulmonary Nodules (IPN) detection and subsequent characterization is critical to improve patient outcomes. IPNs, often the first indicators of potential lung cancer, have traditionally been identified by a manual or keyword search facilitated review of chest X-ray and CT reports (CXRs) by radiologists or pulmonologists.&nbsp;&nbsp;

However, to err is human, and radiologists can overlook subtle nodules, leading to delayed diagnosis and treatment. This is where Artificial Intelligence (AI) is poised to revolutionize the current paradigm of lung cancer treatment, offering a powerful tool for early IPN detection and transforming the landscape of thoracic medicine.&nbsp;

AI algorithms, trained on extensive datasets of CXRs, can detect clinically relevant IPNs with unparalleled accuracy and consistency, with high sensitivity and specificity. These sophisticated algorithms can identify suspicious nodules that may be missed by human observers, in some cases in up to 70% of radiographs, significantly increasing the overall detection rate and thus casting a wider net for early lung cancer detection. The early identification of IPNs through AI augments the pulmonology funnel, thus enabling interventional pulmonologists to initiate diagnostic bronchoscopies earlier, expediting the path to definitive diagnosis and treatment.&nbsp;

The implications of AI-assisted early IPN detection are far-reaching. By putting patients into investigation pathways more quickly, surgeons, radiologists and pulmonologists can collect tissue samples for cancer cell testing at an earlier stage. This accelerated process facilitates a prompter conclusive diagnosis, allowing patients to enter the appropriate treatment pathway more swiftly, potentially even for cure. AI is no doubt a game-changer in the quest for early intervention and improved survival from the world’s deadliest cancer.&nbsp;

Maximizing medical device innovations in tune with AI&nbsp;&nbsp;&nbsp;&nbsp;

The field of pulmonology has witnessed a remarkable transformation with the advent of robotic bronchoscopy. This innovative technology combines the precision of robotics with the flexibility of traditional bronchoscopy, enabling pulmonologists to conclusively diagnose lung cancer at earlier stages. By utilizing thin, maneuverable catheters guided by advanced robotics, physicians can now access peripheral lung nodules inaccessible to CT guided biopsy with unparalleled accuracy and stability.&nbsp;&nbsp;

This minimally invasive approach not only improves diagnostic yields but also significantly reduces the time from initial nodule detection via X-ray and/or CT to biopsy, allowing patients to receive timely treatment. The technical aspects and clinical implications of groundbreaking robotic bronchoscopy is poised to revolutionize the early detection and management of lung cancer.&nbsp;

AI to enhance clinical confidence and efficiency&nbsp;

Beyond its role in early detection, AI offers many benefits that bolster clinical confidence and streamlines workflow in pulmonology. One such benefit is the standardization of nodule assessment. AI ensures consistent evaluation of CXRs, mitigating inter-observer variability amongst radiologists and pulmonologists and upholding high diagnostic accuracy. This standardization enhances the reliability and reproducibility of IPN detection across different healthcare settings.&nbsp;

Moreover, AI's rapid ability to identify IPNs accelerates subsequent diagnostic tests and interventions, expediting patient access to care. This efficiency optimizes clinical paradigms and enables pulmonologists to make informed treatment decisions more rapidly. The seamless integration of AI into the diagnostic process saves time and allows for a more streamlined approach to patient management.&nbsp;

Another crucial aspect of AI's impact on clinical confidence lies in its advanced nodule analysis capabilities. AI can generate Lung Nodule Malignancy Risk Scores, aiding in the differentiation and distinction between benign and malignant nodules. This sophisticated analysis reduces false positives and unnecessary procedures while providing invaluable clinical decision support. The risk scores incorporate nodule characteristics, such as texture and composition, and calculating doubling time of volume.&nbsp;&nbsp;&nbsp;

AI can alleviate patient anxiety by accurately and expeditiously identifying nodules requiring further intervention, and more importantly those that do not warrant biopsy. Integrating AI-powered nodule analysis empowers pulmonologists to make more accurate and informed decisions, ensuring patients receive the most appropriate care based on their needs.&nbsp;

Furthermore, AI-generated reports offer detailed insights and visual aids that facilitate effective communication between pulmonologists and patients. These detailed and organized reports improve patient understanding and engagement in their care plan, fostering a patient-centric approach. The synergy of technology and human expertise creates a collaborative environment where the best possible outcomes can be achieved.&nbsp;

The integration of AI into pulmonology pathways holds immense promise for optimizing patient care. Early lung cancer detection through AI-assisted IPN identification can significantly improve survival rates. Moreover, AI's ability to enhance clinical decision-making, guide interventions, and optimize workflows has the power to transform the practice of pulmonology.&nbsp;

As the field of AI continues to evolve, innovative solutions like Qure.ai's <a href="https://www.qure.ai/product/lung-nodule-management" target="_blank">qXR-LN</a> are at the forefront of harnessing the potential of artificial intelligence to transform pulmonary medicine. By embracing these cutting-edge technologies, pulmonologists can usher in a new era of precision, efficiency, and patient-centric care.&nbsp;

The digital future of pulmonology is here, and AI is poised to impact the fight against lung cancer. With its ability to detect IPNs earlier, enhance clinical confidence, guide bronchoscopy interventions, and improve patient outcomes. As we stand on the precipice of this transformative era, it is an exciting time where innovation and dedication converge to shape a brighter, healthier tomorrow.&nbsp;

Fill out the form to connect with us! 

large_1000122754.webp

medium_1000122754.webp

small_1000122754.webp

thumbnail_1000122754.webp

1000122754.webp

How AI can ‘Pack a Punch’ in Pulmonology 

Silicosis is a debilitating and often fatal lung disease caused by inhaling fine particles of crystalline silica, commonly found in industries such as mining, construction, and manufacturing. According to the World Health Organization (WHO), around 38 million workers worldwide are exposed to silica dust, and approximately 230,000 new cases of silicosis are diagnosed each year globally. This disease is particularly prevalent in countries with significant industrial activities, such as China, India, South Africa, and the United States.&nbsp;

Silicosis is a severe occupational health hazard that poses significant risks to workers. The inhalation of silica dust leads to inflammation and scarring of lung tissue, resulting in impaired lung function and reduced quality of life. The disease can progress to severe respiratory failure and increases the risk of other lung infections, including tuberculosis (TB). The International Labour Organization (ILO) estimates that silicosis causes more than 10,000 deaths annually worldwide. Additionally, the economic burden of silicosis is substantial, with healthcare costs and lost productivity amounting to billions of dollars each year.&nbsp;

Incurability and the Need for Early Diagnosis&nbsp;

Silicosis is currently incurable, making early detection and intervention critical. The disease progresses in stages, which may include acute silicosis, which can develop within a few months of high exposure to silica dust, accelerated silicosis and chronic silicosis, which is the most commonly encountered stage. Early diagnosis allows for timely medical intervention, such as removing the worker from exposure and providing supportive treatments to slow disease progression. Without early diagnosis, workers are at risk of rapid deterioration and severe health complications.&nbsp;

Lung Health Disease and the Radiologist Shortage&nbsp;

AI Solutions: The Role of AI-Powered Screening Tools&nbsp;

Given the shortage of radiologists and the complexity of diagnosing silicosis, AI solutions have emerged as vital tools in healthcare. AI-powered chest X-ray screening tools can analyse medical images with remarkable accuracy and speed, identifying patterns and anomalies that may be indicative of various lung conditions, including silicosis. These tools are designed to detect signs of lung diseases such as tuberculosis and lung cancer, but they can also incidentally identify features suggestive of silicosis, such as nodules, fibrosis, and other abnormalities.&nbsp;

AI algorithms are trained on vast datasets of annotated medical images, enabling them to recognize subtle signs of disease that might be missed by human eyes, especially in the early stages. These tools can provide preliminary diagnoses or flag suspicious cases for further review by radiologists, thus enhancing the diagnostic process and reducing the workload on healthcare professionals.&nbsp;

For instance, in occupational health screenings where workers are regularly tested for lung diseases, AI-powered tools can serve as a first line of defence, ensuring that potential cases of silicosis are not overlooked. By integrating these AI solutions into routine healthcare practices, it is possible to achieve more timely and accurate diagnoses, which is crucial for early intervention and better health outcomes for workers at risk.&nbsp;

Addressing the challenge of silicosis requires a multifaceted approach. Governments and industries must enforce stringent occupational safety regulations to minimize silica dust exposure. At present, several mining companies do take precautionary measures to prevent silicosis among their workers:&nbsp;

However, challenges remain in fully implementing these preventive measures, such as the high cost, lack of awareness, and underreporting of silicosis cases. Continued efforts by mining companies, regulators, and workers are needed to eliminate this preventable occupational disease.&nbsp;

Increasing investment in healthcare infrastructure and training more radiologists are essential steps to address the current shortage. Furthermore, integrating AI solutions into routine diagnostic practices can significantly enhance early detection and improve patient outcomes. By combining these strategies, we can mitigate the impact of silicosis and protect the health of workers globally.&nbsp;

<a href="https://www.mining-technology.com/features/feature130267/" target="_blank">https://www.mining-technology.com/features/feature130267/</a>&nbsp;&nbsp;

<a href="https://occup-med.biomedcentral.com/articles/10.1186/s12995-023-00379-1" target="_blank">https://occup-med.biomedcentral.com/articles/10.1186/s12995-023-00379-1</a>&nbsp;&nbsp;

<a href="https://nhrc.nic.in/sites/default/files/NHRC_Interventions_on_Silicosis_27122016.pdf" target="_blank">https://nhrc.nic.in/sites/default/files/NHRC_Interventions_on_Silicosis_27122016.pdf</a>&nbsp;&nbsp;

<a href="https://www.msha.gov/sites/default/files/Alerts%20and%20Hazards/HH%20Cards/HH-7%20Tips%20for%20Preventing%20Silicosis.pdf" target="_blank">https://www.msha.gov/sites/default/files/Alerts%20and%20Hazards/HH%20Cards/HH-7%20Tips%20for%20Preventing%20Silicosis.pdf</a>&nbsp;&nbsp;

<a href="https://www.cdc.gov/niosh/docs/92-107/default.html" target="_blank">https://www.cdc.gov/niosh/docs/92-107/default.html</a>&nbsp;

World Health Organization (WHO). Silicosis: Global burden and epidemiology (<a href="https://www.who.int/health-topics/silicosis#tab=tab_1" target="_blank">WHO</a>)&nbsp;

International Labour Organization (ILO). Silicosis: A major occupational health issue. (<a href="https://www.ilo.org/global/topics/safety-and-health-at-work/lang--en/index.htm" target="_blank">ILO</a>)&nbsp;&nbsp;

<a href="https://www.sciencedirect.com/science/article/pii/S2666623521000325" target="_blank">https://www.sciencedirect.com/science/article/pii/S2666623521000325</a>&nbsp;

<a href="https://www.mdpi.com/2227-9032/11/16/2260" target="_blank">https://www.mdpi.com/2227-9032/11/16/2260</a>&nbsp;&nbsp;

large_image.webp

medium_image.webp

small_image.webp

thumbnail_image.webp

image.webp

Silicosis: An Urgent Occupational Health Hazard 

Lung cancer is the <a href="https://www.who.int/news-room/fact-sheets/detail/lung-cancer" target="_blank">leading cause</a> of cancer-related deaths worldwide, with <a href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5627048/" target="_blank">approximately 75% of patients</a> detected in late-stage disease. A later diagnosis means that the opportunity for therapeutic or surgical intervention is low, and survival is limited. However, early detection has the potential for improved survival, <a href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7950268/" target="_blank">over 90%</a> if treatment starts at cancer stage 1.&nbsp;

Traditional lung cancer screening initiatives have helped tackle rising cancer rates since their inception, but calling specific patient cohorts for screening based on age or smoking history is only part of the lung cancer detection jigsaw.&nbsp;

Casting the net wider in lung cancer detection&nbsp;

AI can be a highly accurate tool for opportunistic lung cancer surveillance. According to a study published in the journal <a href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9689183/" target="_blank">Diagnostics</a>, Qure’s qXR chest X-ray solution achieved a high negative predictive value of 99.8% for detecting lung nodules. It also demonstrated an impressive 91.5% AUC (Area Under Curve) score for identifying lung nodules, showcasing its potential to accurately detect early signs of lung cancer from routine X-rays.&nbsp;

AI to inspire the redesign of patient pathways&nbsp;

A <a href="https://www.qure.ai/news_press_coverages/major-milestone-met-in-ai-powered-fight-against-lung-cancer" target="_blank">partnership between Qure and AstraZeneca</a>, the global biopharmaceutical company, has made considerable progress in the fight against lung cancer on a global scale. This collaboration is testament to the transformative potential of AI, innovating beyond traditional lung cancer screening profiles and improving patient outcomes on a large scale. It's a glimpse into the future of healthcare.&nbsp;&nbsp;

Nipun Jain, Head of International A.Catalyst Network at AstraZeneca states, "Our partnership with Qure.ai represents a critical step in our commitment to the EDISON Alliance's 1 billion Lives Challenge. Lung cancer remains a major global health concern, and it is through applying AI to screen for lung cancer risk in millions of routine X-rays, that it will provide a low-cost, high-impact way of ensuring at-risk patients enter the right diagnostic and care pathway. This milestone exemplifies our A.Catalyst Network approach to expanding access to digital healthcare and driving sustainable change in the communities we serve."&nbsp;&nbsp;

Initial findings of <a href="https://www.nhsggc.scot/nhsggc-trials-ai-powered-x-rays-in-fight-against-lung-cancer/" target="_blank">RADICAL, a pioneering UK AI-powered trial to diagnose lung cancer earlier</a> from GP or primary care physician referred chest X-rays in an outpatient hospital setting, have also shown much to be optimistic about. Time to treatment turnarounds have reduced from 64 days to 25 by triaging chest X-rays with AI and referring patients for a CT scan within 24 hours. This saves considerable time to potentially improve patent outcomes and quality of life.&nbsp;&nbsp;

Professor David Lowe, Professor of Health Innovation at the University of Glasgow and Emergency Consultant at NHS Greater Glasgow and Clyde in Scotland states, “Worldwide healthcare systems have a significant challenge in the detection of lung cancer. At present, nearly 50% of patients present with advanced or stage 4 cancer, leading to poorer outcomes. If we can spot cancer earlier, by speeding up the time and accuracy of the 100,000 chest X-rays performed each year with our study at NHS Greater Glasgow &amp; Clyde, we can improve time to further imaging, and subsequent treatment. AI will help orchestrate benefits for the whole patient care pathway.”&nbsp;

AI to optimize oncology clinical trials and care&nbsp;&nbsp;

There is much potential for AI to also push the boundaries in clinical oncology care, research and pharmaceutical drug development / trials.&nbsp;&nbsp;

Recently, Qure.ai and Project Data Sphere, a nonprofit initiative of the CEO Roundtable on Cancer, announced <a href="https://www.qure.ai/news_press_coverages/qure-ai-and-project-data-sphere-combine-big-pharma-insights-with-deep-ai-to-drive-cancer-care-forward" target="_blank">a partnership to augment tumor assessments using AI</a>. The collaboration aims to increase efficiency and consistency in evaluating the effectiveness of cancer treatments. The focus of the collaboration is ‘autoRECIST’. It will address the critical need for automating and standardizing tumor response assessments. Initiated in consultation with the US FDA and stakeholders from across the pharmaceutical industry and academia, it will aim to enhance cancer treatments and research.&nbsp;&nbsp;&nbsp;

AI for discussion at ASCO &amp; ESMO 2024

Qure’s end-to-end AI-powered lung cancer care portfolio includes CE and FDA certified solutions to support the early identification, precise measurement, efficient management and monitoring of lung nodules. These help to address critical gaps in healthcare plus propel developments in the pharmaceutical or life sciences industry.&nbsp;&nbsp;

For example, the AI solution <a href="https://www.qure.ai/product/lung-nodule-management" target="_blank">qXR-LN</a> (lung nodule detection) has <a href="https://appliedradiology.com/Articles/qure-ai-nets-fda-clearance-for-ai-powered-chest-x-ray-lung-nodule-solution" target="_blank">FDA clearance</a> for identifying and localizing lung nodules on chest X-rays. It also shows malignancy-risk scores and can serve as a crucial second reader for physicians, assisting in the review of frontal chest radiographs to assist with referral into CT pathways. In a study involving 40 sites across the United States, qXR-LN achieved an impressive AUC of 94% for nodule detection.&nbsp;

As the global oncology community converges on Chicago then Barcelona to share and discuss the latest clinical cancer research and innovations impacting patient care at the 2024 American Society of Clinical Oncology (ASCO) meeting, 31 May to 4 June and European Society for Medical Oncology (ESMO), 13 to 17 Sept, opportunities for AI abound. Early detection and treatment advances using digital health innovations will drive research techniques and improve patient quality of life – and this matters in the global fight against lung cancer.

Want to meet at ESMO??

large_IMG_0414.webp

medium_IMG_0414.webp

small_IMG_0414.webp

thumbnail_IMG_0414.webp

IMG_0414.webp

Why Early Lung Cancer Detection Matters

AI to optimise lung cancer pathways&nbsp;

A recent roundtable discussion, chaired by Professor Sir Mike Richards, Chair of the UK National Screening Committee brought together experts to discuss the <a href="https://newmarket-strategy.com/wp-content/uploads/2023/12/Transformation_of_the_lung_cancer_pathway.pdf" target="_blank">transformation of the lung cancer pathway in the NHS</a>, highlighting the crucial role of AI and other digital health innovations to redesign healthcare. It suggested that new technologies should be seen as an opportunity to streamline existing processes and championed solutions that detect lung nodules from chest X-rays or determine malignancy risk or monitor growth via CT, particularly when used in partnership with Cancer Alliances and NHS Trusts. This approach improves early detection rates and streamlines the diagnostic process, reducing the burden on healthcare professionals.&nbsp;

Many high-profile UK studies are now looking into improving the diagnostic pathway for lung cancer:&nbsp;

Furthermore, a <a href="https://www.qure.ai/news_press_coverages/major-milestone-met-in-ai-powered-fight-against-lung-cancer" target="_blank">pioneering partnership between Qure and AstraZeneca</a> has made considerable progress in the fight against lung cancer on a global scale. This collaboration is testament to the transformative potential of AI, innovating beyond traditional lung cancer screening profiles and improving patient outcomes on a large scale. It's a glimpse into the future of healthcare.&nbsp;&nbsp;

The latest figures suggest 2 million people in 28 countries have been screened using Qure's AI-powered chest X-ray analysis for the incidental detection of high-risk lung nodules. This proactive lung health AI commitment casts the net wider, beyond traditional lung cancer screening based on age or smoking history profiles. The initiative has found over 220,000 lung nodules, identifying close to 3,000 potential early lung cancer cases.&nbsp;&nbsp;

AI to create triage efficiencies for neurocritical CT&nbsp;

AI can also help healthcare professionals make timely decisions and ensure that patients with Traumatic Head Injuries (TBI) or suspected Strokes receive prompt attention. This is particularly important in the context of triage in acute or frontline emergency care where high patient numbers and resource shortages can impact timely patient care.&nbsp;&nbsp;

The ACcEPT (Assess the Clinical Effectiveness in Prioritising CT Heads) study commenced during winter 2023/24 at NHS Greater Glasgow and Clyde, the first of four planned NHS sites across the UK, utilising <a href="https://www.qure.ai/product/qer" target="_blank">qER, Qure’s head CT AI</a>. In the first initial weeks, qER analysed 651 non-contrast head CTs, detecting 128 head injuries including cranial fractures, intracranial haemorrhage (ICH), mass effect and mid-line shift within the brain. The intracranial pathologies were identified and prioritised by the qER AI solution as critical findings for radiologist review, confirmation, treatment planning and / or discharge out of the Emergency Department.&nbsp;

Tackling NHS acute imaging workloads through teleradiology has also been powered by AI to redesign processes and flow. Medica, a leading UK teleradiology provider, uses qER as its <a href="https://www.qure.ai/impact_stories/medica-qure-partnership" target="_blank">24/7 emergency reporting diagnostic tool to support the delivery of acute care</a> in many NHS Trusts.&nbsp;&nbsp;

Redesigning healthcare for better patient outcomes&nbsp;

Optimising lung cancer pathways and creating triage efficiencies for neurocritical CT with the power of diagnostic AI will help redesign care and treatment pathways. The key to AI activation and deployment will be the cross collaboration of stakeholders to share the challenges, champion the successes and steer the NHS ecosystems safely and securely into the future of improved patient care.&nbsp;&nbsp;

Meet Qure.ai this summer to hear more about how AI can redesign healthcare. We’ll be at <a href="https://www.ukio.org.uk/" target="_blank">UKIO</a> in Liverpool, 10-12 June 2024, stand B8/9 and at the <a href="https://www.nhsconfedexpo.org/" target="_blank">NHS ConfedExpo</a> in Manchester, 11-12 June 2024 stand D5a.&nbsp;

Insights onArtificial Intelligence &Healthcare Technology

Insights on
Artificial Intelligence &
Healthcare Technology