Caris Life Sciences Announces Another Breakthrough Study for GPSai in Identifying and Correcting Misdiagnosis of Cancer Patients

Rhea-AI Summary

Caris Life Sciences (NASDAQ: CAI) published a JAMA Network Open study (March 20, 2026) showing its GPSai algorithm reclassified cancer diagnoses among lung squamous cell carcinoma submissions. Of 3,958 cases, GPSai identified 123 as metastases from other primaries; 88 patients (71.5%) had guideline-preferred first-line therapy changes. Caris reports GPSai has overturned 3,857 diagnoses since January 2024. The GPSai capability is included in MI Cancer Seek and MI Tumor Seek; MI Cancer Seek received FDA approval November 2024.

Positive

• 123 cases reclassified out of 3,958 lung SCC submissions (3.1%)
• 88 patients (71.5%) had guideline-preferred first-line therapy change recommendations
• Caris reports 3,857 overturned diagnoses since January 2024
• FDA approval for MI Cancer Seek in November 2024 (WES/WTS CDx)

Negative

• Observed reclassification rate (3.1%) highlights diagnostic gaps in standard pathology
• Estimate of ~1,000 potential US misdiagnoses annually is an extrapolation, not a reported count

Key Figures

Lung cancer SCC cases: 3,958 cases Reclassified metastases: 123 cases Therapy change patients: 88 patients +5 more

8 metrics

Lung cancer SCC cases 3,958 cases Lung cancer cases with SCC diagnosis submitted to Caris

Reclassified metastases 123 cases Cases identified by GPSai as metastases from other primary sites

Therapy change patients 88 patients Patients with guideline-preferred first-line systemic therapy change recommendations

Therapy change rate 71.5% Share of reclassified patients with changed first-line therapy recommendations

Lung SCC share 21% Lung SCC as share of all lung cancer cases in the United States

Potential misdiagnoses 1,000 cases per year Estimated annual lung cancer misdiagnoses applying study stats to CDC data

Overturned diagnoses 3,857 diagnoses Diagnoses overturned by Caris GPSai since January 2024

MI Cancer Seek FDA approval November 2024 FDA approval timing for MI Cancer Seek tissue-based assay

Market Reality Check

Price: $18.80 Vol: Volume 3,256,465 is 1.28x...

normal vol

$18.80 Last Close

Volume Volume 3,256,465 is 1.28x the 20-day average of 2,542,380, indicating elevated interest into this AI diagnostics update. normal

Technical Shares at $18.80 are trading below the 200-day MA of $29.31 and remain far under the 52-week high of $56.22.

Peers on Argus

CAI gained 1.84% while key biotech peers like MRNA (+2.67%) and MDGL (+2.62%) we...

1 Up

CAI gained 1.84% while key biotech peers like MRNA (+2.67%) and MDGL (+2.62%) were also up, but momentum scanner only flagged CORT, suggesting today’s move in CAI is more stock-specific than a broad sector rotation.

Historical Context

5 past events · Latest: Mar 16 (Positive)

Pattern 5 events

Date	Event	Sentiment	Move	Catalyst
Mar 16	AI ovarian signature	Positive	+3.5%	Launch of AI signature to predict platinum resistance in ovarian cancer.
Mar 11	Conference studies	Positive	+0.4%	Announcement of five Caris studies to be showcased at USCAP.
Mar 09	AI pancreatic tool	Positive	+2.2%	Launch of AI signature guiding first-line therapy and de-escalation in PDAC.
Feb 26	Achieve 1 interim data	Positive	+4.7%	Reported early detection sensitivity and specificity metrics for Caris Detect.
Feb 26	Achieve 1 correction	Positive	+4.7%	Clarified interim Achieve 1 data and validation plans for Caris Detect.

Pattern Detected

Recent AI and clinical data announcements have consistently coincided with positive next-day price reactions.

Recent Company History

Over the last month, CAI has repeatedly highlighted advances in AI-driven oncology and early detection. On Feb 26, interim Achieve 1 data for Caris Detect, including Stage I–II sensitivity of 61.3% and specificity up to 99.1%, preceded gains of about 4.7%. Subsequent AI signature launches for pancreatic and ovarian cancer also saw positive reactions. Today’s lung SCC misdiagnosis study in JAMA Network Open fits this pattern of leveraging large clinico-genomic datasets and AI to refine diagnosis and treatment selection.

Market Pulse Summary

This announcement highlights a peer-reviewed JAMA Network Open study showing GPSai can reclassify 12...

Analysis

This announcement highlights a peer-reviewed JAMA Network Open study showing GPSai can reclassify 123 of 3,958 lung SCC cases as metastases, leading to therapy changes for 88 patients. It builds on Caris’ broader AI and sequencing platform and follows FDA approval of MI Cancer Seek in November 2024. Investors may watch for adoption trends, additional publications, and integration into clinical guidelines as key next steps.

Key Terms

squamous cell carcinoma, metastases, comprehensive molecular profiling, systemic therapy, +1 more

5 terms

squamous cell carcinoma medical

"An AI Approach to Differentiating Lung Squamous Cell Carcinoma From Metastases"

Squamous cell carcinoma is a type of skin cancer that develops when the cells in the outer layer of the skin grow abnormally and uncontrollably. It can also occur in other parts of the body, such as the mouth or throat. For investors, understanding diseases like this is important because they can impact healthcare companies, influence medical research funding, and affect overall public health trends.

metastases medical

"Differentiating Lung Squamous Cell Carcinoma From Metastases of Other Origins."

Metastases are secondary tumors that form when cancer cells break away from the original tumor and establish new growths in other organs or tissues, like seeds scattering from a plant and taking root elsewhere. For investors, metastases matter because they usually make a disease harder and more expensive to treat, influence patient outcomes and survival, and can affect the size and urgency of the market for therapies, clinical trial design, regulatory review, and reimbursement decisions.

comprehensive molecular profiling medical

"including AI algorithms as part of routine comprehensive molecular profiling, clinicians can uncover"

Comprehensive molecular profiling is a detailed laboratory analysis of a patient’s tissue or blood to identify genes, mutations, proteins and other biological markers that drive a disease. Think of it as creating a high-resolution blueprint or fingerprint of a condition so doctors and drug developers can match treatments to the underlying cause. For investors, it signals opportunities for targeted therapies, diagnostic tests and more precise drug development, which can concentrate benefit and reduce wasted spending.

systemic therapy medical

"patients who had guideline-preferred first-line systemic therapy change recommendations"

Treatments that travel through the bloodstream or throughout the body to reach disease sites rather than targeting a single spot—think of a citywide water main delivering resources rather than a local hose. They include drugs given orally, by injection, or infusion and are commonly used for cancers, infections, and autoimmune diseases. Investors care because systemic therapies often address large patient populations, drive long-term drug sales, carry regulatory and safety risks, and shape competitive positioning and pricing in healthcare markets.

companion diagnostic (CDx) regulatory

"first and only simultaneous WES and WTS-based assay with FDA-approved companion diagnostic (CDx)"

A companion diagnostic (CDx) is a medical test designed to identify which patients are likely to benefit from, or be harmed by, a specific drug or therapy—think of it as a key that shows which locks a particular medicine can open. For investors, a CDx matters because it shapes how many patients can use the drug, affects regulatory approval and reimbursement odds, and reduces commercial and clinical risk by targeting treatment to the right people.

AI-generated analysis. Not financial advice.

Highlighting the critical role of Caris GPSai in improving cancer care

IRVING, Texas, March 20, 2026 /PRNewswire/ -- Caris Life Sciences® (NASDAQ: CAI), a leading, patient-centric, next-generation AI TechBio company and precision medicine pioneer, published a study in JAMA Network Open, titled "An AI Approach to Differentiating Lung Squamous Cell Carcinoma From Metastases of Other Origins." This study builds on the body of evidence showing the superiority of Caris' proprietary and world-leading GPSai® algorithm over traditional diagnostic procedures in correctly diagnosing cancer types. 

This paper demonstrates that by including AI algorithms as part of routine comprehensive molecular profiling, clinicians can uncover clinically significant misdiagnoses in cases labeled as lung squamous cell carcinoma (SCC), influencing treatment decisions and patient outcomes. The study comprised 3,958 lung cancer cases submitted to Caris with a diagnosis of SCC. Caris GPSai® identified 123 of the 3,958 cases were metastases from other primary sites, including cutaneous, urothelial, head and neck and thymic cancers.

The clinical impact of reclassification underscores the power of precision medicine. The study identified 88 patients (71.5%) who had guideline-preferred first-line systemic therapy change recommendations, alerting clinicians that a change in their patients' treatments would achieve better outcomes. According to the CDC website, lung SCC accounts for roughly 21% of all lung cancer cases in the United States. Applying study-specific stats to the wider CDC data for lung cancer in the United States suggests that approximately 1,000 cases each year may be potential misdiagnoses.

"Caris GPSai has overturned 3,857 diagnoses across the spectrum of cancer since January of 2024," said Matthew Oberley, MD, PhD, Senior Vice President, Chief Clinical Officer and Pathologist-in-Chief at Caris. "By integrating AI-driven tissue‑of‑origin predictions with comprehensive molecular profiling and pathology, we can give clinicians greater diagnostic confidence and ensure patients receive the most appropriate care."

These misdiagnoses carry direct and life-altering clinical consequences, as treatment recommendations and prognostic expectations differ significantly across cancer types. By embedding Caris GPSai into Caris' comprehensive molecular profiling, providers gain an additional layer of insight that can help patients get the healthcare they deserve.

The GPSai algorithm is included as part of MI Cancer Seek® and MI Tumor Seek® at no additional cost. Caris received FDA approval in November 2024 for MI Cancer Seek. This tissue-based assay is the first and only simultaneous WES and WTS-based assay with FDA-approved companion diagnostic (CDx) indications for molecular profiling of solid tumors.

About Caris Life Sciences
Caris Life Sciences® (Caris) is a leading, patient-centric, next-generation AI TechBio company and precision medicine pioneer actively developing and commercializing innovative solutions to transform healthcare. Through comprehensive molecular profiling (Whole Genome, Whole Exome and Whole Transcriptome Sequencing), advanced AI and machine learning, Caris has created the large-scale, multimodal clinico-genomic database and computing capability needed to analyze and further unravel the molecular complexity of disease. This convergence of next-generation sequencing, AI and machine learning technologies and high-performance computing provides a differentiated platform for developing the latest generation of advanced precision medicine diagnostic solutions for early detection, diagnosis, monitoring, therapy selection and drug development.

Caris was founded with a vision to realize the potential of precision medicine to improve the human condition. Headquartered in Irving, Texas, Caris has offices in Phoenix, New York, Cambridge (MA), Tokyo, Japan and Basel, Switzerland. Caris or its distributor partners provide services in the U.S. and other international markets.

Forward Looking Statements

This press release contains forward-looking statements within the meaning of the federal securities laws. All statements other than statements of historical facts contained in this press release are forward-looking statements, including statements regarding our business, solutions, plans, objectives, goals, industry trends, financial outlook and guidance. In some cases forward-looking statements can be identified by words such as "may," "will," "should," "would," "expect," "plan," "anticipate," "could," "intend," "target," "project," "potential," "contemplate," "believe," "estimate," "predict," "potential" or "continue" or similar expressions.

You should not rely upon forward-looking statements as predictions of future events. Although we believe that the expectations reflected in these forward-looking statements are reasonable based on information currently available to us, we cannot guarantee that the future results, discoveries, levels of activity, performance or events and circumstances reflected in forward-looking statements will be achieved or occur. Forward-looking statements involve known and unknown risks and uncertainties, some of which are beyond our control. Risks and uncertainties that could cause our actual results to differ materially from those indicated or implied by the forward-looking statements in this press release include, among other things: developments in the precision medicine industry; our future financial performance, results of operations or other operational results or metrics; development, analytical and clinical validation, timing and performance of future solutions by us and our competitors; commercial market acceptance for our solutions, including acceptance of preventive as well as diagnostic testing paradigms, and our ability to meet resulting demand; the rapidly evolving competitive environment in which we operate; third-party payer reimbursement and coverage decisions related to our solutions; risks related to data management, storage, and processing capabilities and our ability to integrate and deploy artificial intelligence and advanced data analytics technologies; our ability to protect and enhance our intellectual property; regulatory requirements, decisions or approvals (including the timing and conditions thereof) related to our solutions; reliance on third-party suppliers; risks related to data security, patient privacy, and compliance with healthcare data protection regulations as well as potential cybersecurity threats to our data platforms; our compliance with laws and regulations; the outcome of government investigations and litigation; risks related to our indebtedness; and our ability to hire and retain key personnel as well as risks, uncertainties, and other factors described in the section titled "Risk Factors" and elsewhere in our Annual Report on Form 10-K filed with the Securities and Exchange Commission (SEC) on March 3, 2026, and in our other filings we make with the SEC from time to time. We undertake no obligation to update any forward-looking statements to reflect changes in events, circumstances or our beliefs after the date of this press release, except as required by law. 

Caris Life Sciences Media:
Corporate Communications
CorpComm@CarisLS.com
214.294.5606

View original content to download multimedia:https://www.prnewswire.com/news-releases/caris-life-sciences-announces-another-breakthrough-study-for-gpsai-in-identifying-and-correcting-misdiagnosis-of-cancer-patients-302719396.html

SOURCE Caris Life Sciences

FAQ

What did Caris (CAI) announce in the March 20, 2026 JAMA Network Open study?

Caris announced GPSai reclassified 123 of 3,958 lung SCC submissions as metastases from other primaries. According to Caris, 88 patients (71.5%) had guideline-preferred therapy changes, showing direct clinical impact on treatment selection.

How many cases did GPSai reclassify in the Caris CAI study and what percent is that?

GPSai reclassified 123 of 3,958 lung SCC cases, about 3.1% of submissions. According to Caris, this reclassification uncovered cancers from cutaneous, urothelial, head and neck and thymic origins.

What patient treatment impact did the Caris CAI study report from GPSai reclassifications?

The study found 88 patients (71.5% of reclassified cases) had guideline-preferred first-line systemic therapy changes. According to Caris, these changes could alter treatment choice and expected outcomes for affected patients.

Does Caris include GPSai in its commercial assays and is there regulatory approval?

Yes; GPSai is included in MI Cancer Seek and MI Tumor Seek at no extra cost, and MI Cancer Seek received FDA approval in November 2024. According to Caris, MI Cancer Seek is WES/WTS-based with CDx indications.

How did Caris estimate ~1,000 potential US misdiagnoses annually from the study?

Caris applied study-specific misclassification rates to CDC lung cancer statistics to estimate ~1,000 potential misdiagnoses per year in the US. According to Caris, this is an extrapolation from study findings to national data.

What broader diagnostic claim did Caris (CAI) make about GPSai since January 2024?

Caris reported GPSai has overturned 3,857 diagnoses across cancer types since January 2024. According to Caris, integrating AI tissue‑of‑origin predictions adds diagnostic confidence alongside molecular profiling.