Predictive Oncology Announces Positive Results from Ovarian Cancer Study with UPMC Magee-Womens Hospital to be Presented at the 2024 American Society of Clinical Oncology (ASCO) Annual Meeting
Predictive Oncology (NASDAQ: POAI) has announced positive outcomes from a retrospective study in partnership with UPMC Magee-Womens Hospital.
The study, which will be presented at the 2024 ASCO Annual Meeting, demonstrated AI-driven multi-omic machine learning models that predict survival outcomes in ovarian cancer patients more accurately than clinical data alone.
Key findings include the use of patient data and sequencing to train 160 models, with seven models showing high prediction accuracy at the two-year threshold and 13 at the five-year threshold.
This advancement offers potential improvements in clinical management and personalized treatment plans.
Presentation details: June 3rd, 9:00am-12:00pm CDT, by Dr. Brian Christopher Orr.
- Study demonstrated AI-driven ML models that outperform clinical data in predicting ovarian cancer survival outcomes.
- Seven ML models achieved high prediction accuracy at the two-year threshold.
- Thirteen ML models achieved high prediction accuracy at the five-year threshold.
- ML models used multi-omic feature sets for superior prediction performance.
- Potential for ML models to improve clinical management and personalized treatment plans.
- Opportunity to discover unique biomarkers for novel cancer therapeutics.
- Predictive Oncology has a biobank with over 150,000 tumor samples and 200,000 pathology slides.
- CLIA-certified wet lab and decades of longitudinal patient data differentiate Predictive Oncology from peers.
- Study was retrospective, which may limit the applicability of findings to prospective clinical settings.
- The majority of ovarian cancer patients relapse within one to two years despite frontline chemotherapy.
- Only 20% of ovarian cancer patients are long-term survivors.
- Model performance estimated using AUROC metric, which may not fully capture clinical utility.
- Further research required to validate ML models in diverse patient populations.
- Potential risks associated with integrating AI models into routine clinical practice.
Insights
This announcement highlights a significant stride in oncology research, particularly in the realm of ovarian cancer. The application of AI and machine learning to predict survival outcomes represents an evolution in personalized medicine. The study's results suggest that predictive models utilizing multi-omic data sets—such as whole exome sequencing (WES), whole transcriptome sequencing (WTS), drug response profiles and digital pathology profiles—can markedly improve prognostic accuracy over traditional clinical data alone.
The Area Under the Receiver Operating Characteristic (AUROC) scores are critical here. An AUROC score greater than 0.5 indicates a model better than random chance and this study achieved high prediction accuracy with seven models at the two-year threshold and thirteen at the five-year threshold. This demonstrates the robustness of the predictive models and their potential utility in clinical settings.
From a clinical standpoint, this can transform patient management by identifying patients at higher risk of relapse and enabling tailored treatment plans. While traditional methods offer a broad-stroke approach, AI-driven insights allow for more nuanced, patient-specific treatment strategies.
Rating: 1
These findings could have substantial financial implications for Predictive Oncology Inc. The effectiveness of their AI-driven models in a critical area such as oncology could elevate their market position and attract significant investment. This progress enhances their value proposition, potentially leading to partnerships or acquisitions, given their unique data assets like the biobank and pathology slides.
Short-term effects might include a bump in stock value as investors react to the positive study results and upcoming presentation at the ASCO meeting. Long-term impacts could be more profound as the technology is validated and possibly adopted in clinical settings, leading to revenue generation from licensing, partnerships, or direct application in cancer treatment protocols.
It's essential to monitor how these developments translate into financial performance and whether Predictive Oncology can sustain this momentum in advancing their AI capabilities.
Rating: 1
Study successfully demonstrated Predictive’s ability to build AI multi-omic machine learning models to predict survival outcomes among ovarian cancer patients better than clinical data alone
PITTSBURGH, May 28, 2024 (GLOBE NEWSWIRE) -- Predictive Oncology Inc. (NASDAQ: POAI), a leader in AI-driven drug discovery and biologics, today announced that positive results from a retrospective study that the company recently completed in collaboration with UPMC Magee-Womens Hospital will be presented at the 2024 American Society of Clinical Oncology (ASCO) Annual Meeting, which is being held May 31-June 4, 2024, in Chicago, Il.
The purpose of the study was to determine if Predictive Oncology could leverage its artificial intelligence and other capabilities to develop machine learning (ML) models that could more accurately predict both short-term (two-year) and long-term (five-year) survival outcomes among ovarian cancer patients.
“High grade serous ovarian cancer is a notoriously challenging cancer to treat, due in large part to the lack of symptoms in the early stages of disease,” stated Robert Edwards, MD, Professor and Chair, Department of Obstetrics, Gynecology & Reproductive Sciences, Co-Director, Gynecologic Oncology Research, Magee-Womens Hospital of UPMC. “While surgery and frontline chemotherapy are effective in the near-term, nearly
“We would like to thank Brian Orr, MD, lead investigator of the study, Robert Edwards, MD, the other investigators, and our collaborators at Magee-Womens Hospital who executed on this study so successfully,” stated Arlette Uihlein, MD, Senior Vice President, Translational Medicine and Drug Discovery, and Medical Director, Predictive Oncology. “We believe these results highlight the potential of AI and machine learning to not only accelerate early oncology drug discovery, but to assist with the clinical management of cancer patients in real-time, thereby improving survival outcomes. We also see an opportunity to leverage these findings to discover unique biomarkers that can be used by us or a partner to develop novel cancer therapeutics. With a unique set of assets and capabilities, including our biobank of more than 150,000 tumor samples, 200,000 pathology slides, CLIA-certified wet lab, and decades of longitudinal patient data that clearly differentiate us from peers, Predictive Oncology is proud to be a leader in this emerging field.”
Presentation details:
| Title: | Using Artificial Intelligence-Powered Evidence-Based Molecular Decision-Making for Improved Outcomes in Ovarian Cancer |
| Abstract #: | 448976 |
| Session: | Gynecologic Cancer |
| Date/time: | Monday, June 3rd, 9:00am-12:00pm CDT (10:00am-1:00pm EDT) |
| Presenter: | Dr. Brian Christopher Orr, MD, MS, Gynecologic Oncologist at the Hollings Cancer Center, Assistant Professor, Medical University of South Carolina |
Summary:
The study analyzed clinical data and tumor specimens from 2010-2016. Patient data, whole exome sequencing (WES), whole transcriptome sequencing (WTS), drug response profile, and digital pathology profile were used as input feature sets for training the 160 multi-omic machine learning (ML) models that were built as part of the study. Hypothesis-free training of the ML models was utilized to classify patient survival at two-year and five-year threshold. Model performance was estimated using AUROC (area under the receiver operating characteristic curve) metric, with scores greater than 0.5 having higher prediction potential.
Results:
Of the 160 ML models built, seven were found to achieve high prediction accuracy at the two-year threshold, and 13 at the five-year threshold. Multi-omic feature set inputs led to superior prediction and improved performance over clinical data alone, and top performing models predicted better than any feature set in isolation.
Conclusion:
Utilizing multi-omic machine learning models, superior prediction of short- and long-term survival was achieved as compared to clinical data alone. The specific drivers of the top performing models were different for the short- and long-term cohorts, identifying future research opportunities as well as development potential of a clinical decision tool.
The full 2024 ASCO Program Guide can be found here.
About Predictive Oncology
Predictive Oncology is on the cutting edge of the rapidly growing use of artificial intelligence and machine learning to expedite early drug discovery and enable drug development for the benefit of cancer patients worldwide. The company’s scientifically validated AI platform, PEDAL, is able to predict with
Investor Relations Contact
Tim McCarthy
LifeSci Advisors, LLC
tim@lifesciadvisors.com
Forward-Looking Statements:
Certain matters discussed in this release contain forward-looking statements. These forward- looking statements reflect our current expectations and projections about future events and are subject to substantial risks, uncertainties and assumptions about our operations and the investments we make. All statements, other than statements of historical facts, included in this press release regarding our strategy, future operations, future financial position, future revenue and financial performance, projected costs, prospects, changes in management, plans and objectives of management are forward-looking statements. The words “anticipate,” “believe,” “estimate,” “expect,” “intend,” “may,” “plan,” “would,” “target” and similar expressions are intended to identify forward-looking statements, although not all forward-looking statements contain these identifying words. Our actual future performance may materially differ from that contemplated by the forward-looking statements as a result of a variety of factors including, among other things, factors discussed under the heading “Risk Factors” in our filings with the SEC. Except as expressly required by law, the Company disclaims any intent or obligation to update these forward-looking statements.
FAQ
What did Predictive Oncology's study on ovarian cancer achieve?
When will Predictive Oncology present their ovarian cancer study results?
What is the significance of Predictive Oncology's AI models in ovarian cancer?
How many AI models showed high prediction accuracy in Predictive Oncology's study?
What data did Predictive Oncology use to train their AI models?
What are the potential applications of Predictive Oncology's study findings?
What differentiates Predictive Oncology from its peers?
