Regulatory Milestone Designed to Expedite Path to FDA Clearance and CMS Coverage.
Sunnyvale, Calif., November 28, 2023 — Inflammatix, Inc., a pioneering molecular diagnostics company, announced today that the US Food and Drug Administration (FDA) has granted Breakthrough Device Designation to the company’s lead product, the TriVerity™ Acute Infection and Sepsis Test System. The TriVerity Test System, currently under development, includes the Myrna™ Instrument and the TriVerity Test and is intended to be used in emergency departments in adult patients with suspected acute infection or suspected sepsis. The TriVerity Test is designed to provide three independent readouts that reflect the likelihood of a bacterial infection, the likelihood of a viral infection, and the risk of severe illness (based on the need for critical organ support* within seven days of presentation to the emergency department).
“We are pleased that the FDA has granted its Breakthrough Device Designation to TriVerity, as it reflects that this novel test system has the potential to help physicians improve on the current standard of care,” said Dr. Timothy Sweeney, CEO and co-founder of Inflammatix. “By reaching this important regulatory milestone, we hope to place TriVerity on an accelerated pathway to FDA clearance, which would allow us to fill an unmet need for rapid, accurate tests for the diagnosis and prognosis of patients with suspected sepsis.”
The FDA established the Breakthrough Devices Program as a voluntary mechanism for certain medical devices and device-led combination products that provide for more effective treatment or diagnosis of life-threatening or irreversibly debilitating diseases or conditions. The program is intended to provide patients and health care providers with timely access to medical devices by speeding up development, assessment, and review for premarket approval and marketing authorization.
As a Breakthrough Device, TriVerity is expected to be eligible for the Centers for Medicare & Medicaid Services (CMS) New Technology Add-On Payment (NTAP) program, which will enable future Inflammatix hospital customers to receive a partial subsidy for purchases of TriVerity Acute Infection and Sepsis Tests performed on admitted patients for up to three years. In addition, assuming CMS finalizes its proposed Temporary Coverage for Emerging Technologies (TCET) rule, the TriVerity Test may be eligible for temporary coverage for tests run on discharged Medicare patients for up to four years. CMS is expected to issue its final ruling on TCET in December 2023.
“The potential Medicare reimbursement benefits associated with Breakthrough Designation may expedite implementation of TriVerity in our partner hospitals,” commented Dr. Sweeney. “We continue to engage with payers, hospitals, and other stakeholders on our path to commercial launch.”
* Defined as the need for mechanical ventilation, vasopressors, or renal replacement therapy.
About the TriVerity Acute Infection and Sepsis Test System
The TriVerity™ Acute Infection and Sepsis Test System, the lead product for Inflammatix, includes the Myrna™ Instrument and the TriVerity Test. The TriVerity Test incorporates a panel of 29 messenger RNAs (mRNAs) to “read” the body’s immune response, providing three readouts to facilitate diagnosis and prognosis of adult patients with suspected acute infection or sepsis that present in US emergency departments. Based on internal analysis of the Agency for Healthcare Research and Quality (AHRQ) Healthcare Cost and Utilization Project (HCUP) database, Inflammatix estimates roughly 20 million patients per year visit emergency departments with symptoms consistent with suspected acute infection.
The Myrna Instrument is capable of sample-to-answer quantitation of up to 64 mRNAs from whole blood or other sample types in about 30 minutes. While the first version of the Myrna Instrument will require standard laboratory operation, the company’s roadmap includes the development of a Clinical Laboratory Improvement Amendments (CLIA)-waivable version to enable point-of-care deployments.
The company recently announced the completion of technical development for the TriVerity Test System and has resumed its clinical studies, including its SEPSIS-SHIELD study (NCT04094818) required for 510(k) clearance of the TriVerity Test System by the FDA. The multi-center study has already enrolled 955 of the estimated 1,500 patients targeted. The company estimates study completion and FDA submission to occur in 2024.
The TriVerity Acute Infection and Sepsis Test System is a product in development, is not for sale, and does not have marketing approval or clearance from regulatory authorities in any jurisdiction.
About Inflammatix
Inflammatix, Inc., a pioneering molecular diagnostics company headquartered in Sunnyvale, California, USA, is developing novel diagnostics that rapidly read a patient’s immune system to improve patient care and reduce major public health burdens. The Inflammatix tests will be developed to run on the company’s sample-to-answer isothermal instrument platform, enabling the power of precision medicine at the point of care. The company’s funders include Khosla Ventures, Northpond Ventures, Think.Health Ventures, D1 Capital, and the Stanford-StartX Fund. For more information, please visit www.inflammatix.com and follow the company on LinkedIn and X (formerly Twitter) at @Inflammatix_Inc).
Inflammatix product development has been funded in part with Federal funds from the Department of Health and Human Services; Office of the Assistant Secretary for Preparedness and Response; Biomedical Advanced Research and Development Authority, under Contract Nos. 75A50119C00034 and 75A50119C00044.
TriVerity, Myrna, and Inflammatix are trademarks of Inflammatix, Inc. in the US and other countries and regions.
The TriVerity™ Acute Infection and Sepsis Test System, which includes the Myrna™ Instrument and TriVerity Cartridge, has reached an important milestone with completion of technical development.
Company Reaches Important Product Development Milestone with its Myrna™ Instrument and TriVerity Cartridge.
Sunnyvale, Calif., November 15, 2023 — Inflammatix, Inc., a pioneering molecular diagnostics company, announced today that the company has completed technical development for its TriVerity™ Acute Infection and Sepsis Test System, which includes the Myrna™ Instrument, and for the TriVerity™ Cartridge. TriVerity is intended to be used in emergency department settings in patients with suspected acute infection and sepsis to assess the likelihood of a bacterial infection, a viral infection, and risk of acute decompensation (the need for ICU-level care).
“Myrna will be the world’s highest-multiplex point-of-care system capable of quantitating RNA, allowing us to bring ‘precision medicine’ into acute care settings,” said Dr. Timothy Sweeney, CEO and co-founder of Inflammatix. “Completing technical development brings TriVerity a step closer to FDA submission and launch, and enables us to execute key clinical studies.”
The Myrna Instrument is capable of sample-to-answer quantitation of up to 64 messenger RNAs (mRNAs) from whole blood or other sample types in about 30 minutes. It is designed to be Clinical Laboratory Improvement Amendments (CLIA)-waivable to enable point-of-care deployments. The disposable cartridges are expected to be room-temperature stable for up to 12 months.
“With the completion of the test system, we look forward to further exploring partnerships that bring existing RNA signatures onto the Myrna ecosystem,” Dr. Sweeney commented. “This may be an especially viable pathway given expected changes to the regulation of lab-developed tests and the increased reliance on a biomarker-driven approach to immunotherapy development.”
The TriVerity Acute Infection and Sepsis Test, Inflammatix’s lead product, incorporates a panel of 29 mRNAs to ”read” the body’s immune response and thus aid in the diagnosis of patients with suspected acute infection and sepsis. It is designed to potentially facilitate diagnosis of patients with suspected infection that present in US emergency departments. Based on internal analysis of the Agency for Healthcare Research and Quality (AHRQ) Healthcare Cost and Utilization Project (HCUP) database, Inflammatix estimates roughly 20 million patients per year visit emergency departments with symptoms consistent with suspected infection.
The company has resumed completion of its clinical studies, including its SEPSIS-SHIELD study (NCT04094818) required for submission of the TriVerity Test system to the U.S. Food and Drug Administration (FDA). The multi-center study has already enrolled 955 of the estimated 1,500 patients needed. Inflammatix estimates study completion and FDA submission to occur by spring 2024.
The TriVerity Acute Infection and Sepsis Test System is a product in development, is not for sale, and does not have marketing approval or clearance from regulatory authorities in any jurisdiction.
About Inflammatix
Inflammatix, Inc., is an innovative molecular diagnostics company based in Sunnyvale, California, USA, that is developing novel diagnostics that rapidly read a patient’s immune system to improve patient care and reduce major public health burdens. Inflammatix’s tests will be developed to run on the company’s sample-to-answer isothermal instrument platform, enabling the power of precision medicine at the point of care. The company’s funders include Khosla Ventures, Northpond Ventures, Think.Health Ventures, D1 Capital, and the Stanford-StartX Fund. For more information, please visit www.inflammatix.com and follow the company on LinkedIn and X (formerly Twitter) at @Inflammatix_Inc).
Inflammatix product development has been funded in part with Federal funds from the Department of Health and Human Services; Office of the Assistant Secretary for Preparedness and Response; Biomedical Advanced Research and Development Authority, under Contract Nos. 75A50119C00034 and 75A50119C00044.
Myrna, TriVerity, and Inflammatix are trademarks of Inflammatix, Inc. in the US and other countries and regions.
The TriVerity™ Acute Infection and Sepsis Test System, which includes the Myrna™ Instrument and TriVerity Cartridge, has reached an important milestone with completion of technical development.
Data-biobank Acutelines and Inflammatix, an innovative molecular diagnostics company, are joining forces to improve the early detection of sepsis: a potentially fatal syndrome caused by a dysregulated immune response to infection.
Sunnyvale, Calif., September 13, 2023 — Acutelines and Inflammatix are developing a smart tool to facilitate recognition of sepsis and support clinical decisions in the early phase of the disease. Early recognition of sepsis is hard but can make a significant impact on patient outcomes.
The importance of early recognition Before the COVID-19 pandemic, annually, 50 million patients were diagnosed with sepsis. The pandemic has led to a steep increase in these numbers. Early recognition of infections and accurate differentiation between viral and bacterial etiology is vital to select effective therapy. On the one hand, each hour of delayed antibiotic treatment introduces additional risk for bacterial infection patients. On the other hand, rampant overuse of antibiotics drives the development of antimicrobial-resistant (AMR) bacteria, risking the effectiveness of current antibiotics.
Recent estimates indicate nearly 5 million deaths associated with AMR. Novel precision diagnostic approaches can support balancing the tightrope between overtreating the uninfected and missing the infected patients, thereby impacting society by improving patient outcomes and reducing the socioeconomic burden of sepsis and AMR.
Improving the future of sepsis The project will approach this diagnostic dilemma by combining health records and biological information with the goal to deliver better clinical decision support for patients with suspected sepsis visiting the emergency department. Blood samples will be collected, and the expressions of genes associated with the immune response to infection will be measured. These biological signals along with clinical record data collected during the patient encounter will be used to derive diagnostic algorithms that can better inform on the presence, type and severity of infection. These signatures will be validated in prospective studies and are planned to be used by physicians to better recognize early sepsis, decide whom to admit and when to administer antibiotics.
Data-biobank Acutelines ensures availability and standardized processing of data and biomaterials from more than five thousand samples from over one thousandpatients. Inflammatix brings expertise in developing machine learning-based algorithms and building rapid point-of-care-based gene expression diagnostics into the collaboration.
Integrating health data in a clinically actionable manner “Our collaboration will allow us to leverage our expertise in data-banking and research to better understand the dynamics of sepsis. Inflammatix’s proficiency in machine learning and rapid gene expression diagnostics will greatly enhance our efforts to develop a smart, early diagnosis system,” says Dr. Hjalmar Bouma, project leader of Acutelines. Dr. Timothy Sweeney, CEO and co-founder of Inflammatix, added, “Our joint efforts with Acutelines accelerates our mission to further improve sepsis diagnosis by integrating health record data with our biological signature in a clinically actionable manner. ”
Support The project is supported by Health Holland through a public-private partnership allowance. This support underscores a shared commitment to advancing healthcare and improving patient outcomes. The Acutelines-Inflammatix partnership marks a significant step forward in early sepsis diagnosis, ultimately paving the way towards precision medicine and saving lives.
About Acutelines and Inflammatix
About Acutelines Acutelines is a leading data-biobank based in the Acute and Emergency Department at University Medical College Groningen (UMCG). Acutelines is committed to improving acute care by developing smart diagnostics and personalized medicine.
About Inflammatix Inflammatix, Inc., is an innovative molecular diagnostics company based in Sunnyvale, California, USA, developing novel diagnostics that rapidly read a patient’s immune system to improve care and reduce major public health burdens. Inflammatix tests will be developed to run on the company’s sample-to-answer isothermal instrument platform, enabling the power of precision medicine at the point of care.
By Kirindi Choi, Ljubomir Buturovic, Roland Luethy, Inflammatix, Inc.
Introduction
Recently, generative artificial intelligence (AI) models for text, images, and video have made major progress and achieved worldwide attention among experts and the public, including initial applications in medicine [1]. The application of generative AI to problems in genomics (the study of genes and their functions) has, understandably, been less visible, but has nevertheless important applications. In this blog, we assess several open-source and commercial tools which can be used to generate high-quality genomic data and discuss potential applications. We focus on transcriptomic applications (a subfield of genomics), with tabular data representing gene expression (the measurements of abundance of gene products in cells). Transcriptomics has significant applications in bioinformatics research and increasingly in clinical care as a new class of diagnostics and prognostics [2-5].
One of the main use cases for synthetic genomic and transcriptomic data is sharing data while preserving privacy. Some ideas include the following: an organization may wish to organize a Kaggle competition for its transcriptomic problem by using synthetic data based on patient data, thereby preserving the privacy of the patient data; or an organization may send synthetic data to a software vendor to report and reproduce a bug, again without sending sensitive data.
Another potential use case is to improve classification accuracy by adding synthetic tabular data to the training set for Machine Learning (ML) models. However, in the available literature, we have not seen convincing evidence of this approach being successful. Thus, we believe that this use case remains hypothetical.
In this blog, we compare the quality of the transcriptomic synthetic data created using different generative AI tools.
Methods
We selected and compared two open-source and two commercial synthetic data generators (available through Python API).
We selected the following open-source Python tools:
CTGAN (conditional tabular generative adversarial network) [6] from SDV (Synthetic Data Vault) [7] and
Gaussian Copula (Gaussian Multivariate) [8] in SDV Copulas library.
We selected the following commercial solutions:
LSTM and ACTGAN (an alternate implementation of CTGAN) cloud-based APIs from Gretel.ai ([9], [12], [13], [14]).
To evaluate quality of the synthesized data, we used two different metrics:
SDMetrics (synthetic data metrics) [10] from SDV.
Cross-validation AUROC (Area Under Receiver Operating Characteristic) of a binary logistic regression classifier trained on real (positive class) and corresponding synthetic (negative class) data. The idea is that high-quality synthetic data should be difficult to discriminate (classify) from real data, therefore such data should have an AUROC of approximately 0.5. This quality metric has a low false-negative rate: data which fail the metric are unlikely to be high-quality. However, data with AUROC close to 0.5 may still not be high quality
Per [11], we also applied duplicate detection steps after the data were synthesized: we detected and discarded any duplicates within the synthesized dataset, and detected and discarded any synthesized data that were replicates of the real data.
For the data synthesis, we used default values for the parameter settings of the data synthesizers except batch size and number of epochs (Table 1).
We used a real data set with 9,654 patient samples and used the expression levels of 29 genes for each sample [5]. We synthesized 6 sets of data: 4 datasets using SDV tool, and 2 datasets using Gretel tool. The synthetic datasets had 1,000 samples each. The SDV datasets were created on the same EC2 instance with four vCPUs, whereas Gretel.ai is a cloud-based service. Since ACTGAN is a variant of CTGAN, we also ran a CTGAN with the same hyper parameter settings as ACTGAN’s default parameters that use larger network than CTGAN’s default parameters.
We computed an AUROC quality metric as follows. For each set of synthesized data, we used the synthesized data and the real data as the training set (consisting of 10,654 samples in total) wherein synthetic data was considered positive class and real data was considered negative class. We then estimated a cross-validation AUROC for the said training set using scikit-learn Logistic Regression model for binary classification and Optuna [15] hyperparameter search. The AUROC reported corresponds to the highest AUROC found by the hyperparameter search. Ideally, a classifier should not be able to distinguish synthetic data from real. Thus, the corresponding cross-validation AUROC should be as close as possible to 0.5.
The second metric was computed using the SDMetrics package. It evaluates the marginal distributions and pairwise trends between columns. Its overall quality score is an average of all metric scores (i.e., KSComplement, TVComplement, CorrelationSimilarity and CategoryCoverage). The score ranges from 0 to 1 with 1 meaning the best quality.
Results
We performed the duplication check on 10,000 synthetic samples and found no duplicates within synthetic data nor copies of real data. Thus, this QC (Quality Control) step may be redundant.
Besides fine-grained and overall scores, SDMetrics offers convenient comparison visualizations including density plot per column between the synthesized data and the real data.
Figure 1: Density plot for a feature synthesized with Gretel LSTM (#6 below).
Figure 2: Density plot for the same feature as in Fig. 1 synthesized with CTGAN (#3 below).
All synthetic datasets except Gretel LSTM were easily and highly distinguishable from the real data with AUROCs >= 0.87. For example, for CTGAN with 50 epochs and batch size of 100, a linear classifier could accurately distinguish between real and synthetic data with high accuracy (AUROC = 0.963). Overall, Gretel LSTM performed best in generating data that mimics the set of real data, with an AUROC of 0.623 and the highest SDMetrics overall quality score of 0.949. A distant second was SDV’s CTGAN with 100 epochs and larger dimensions with SDMetrics quality score of 0.927 and was easily distinguishable from real data with AUROC of 0.87. Notably, between the two synthetic datasets generated using Gretel, the LSTM tool was substantially better than their ACTGAN tool.
The AUROC metric proved to be very useful. It was significantly more intuitive and familiar to users than the SDMetric Overall Quality score, yet the rankings of the methods obtained by the two metrics were virtually identical.
Table 1: Parameters and performance metrics of synthetic data tools.
We observed that turning verbose mode on for CTGAN added excessive amount of time to our data synthesis process and thus we kept verbose off for the runs as shown above.
As expected, we also observed that for the three CTGAN runs with different hyper parameter values, the performance results differed. This suggests some hyperparameter optimization for data synthesizer training can be beneficial for a given set of real data.
In the future we plan to add the Transformer-based NEMO tabular data generator from NVIDIA [11] to our evaluations.
Conclusion
We found that the LSTM synthetic data generator from Gretel.ai is the best among the six solutions that we compared by a wide margin of 0.25 AUROC points between Gretel.ai and the next best software. Interestingly, it is based on LSTM, which to our knowledge has not been widely used for generating synthetic non-temporal tabular data.
Our findings are only based on one internal transcriptomic dataset with numeric features and may not generalize to other data. Nevertheless, we think it is an important data point because the Gretel LSTM was substantially better than any other tool, meaning that it may be inherently superior. We also found the AUROC to be an especially useful and intuitive quality metric in benchmarking performance of these different techniques.
References
Shah NH, Entwistle D, Pfeffer MA. Creation and Adoption of Large Language Models in Medicine. JAMA. 2023 Aug 7.
Sparano JA, Gray RJ, Makower DF, Pritchard KI, Albain KS, Hayes DF, Geyer Jr CE, Dees EC, Goetz MP, Olson Jr JA, Lively T. Adjuvant chemotherapy guided by a 21-gene expression assay in breast cancer. New England Journal of Medicine. 2018 Jul 12;379(2):111-21.
Alexander EK, Kennedy GC, Baloch ZW, Cibas ES, Chudova D, Diggans J, Friedman L, Kloos RT, LiVolsi VA, Mandel SJ, Raab SS. Preoperative diagnosis of benign thyroid nodules with indeterminate cytology. New England Journal of Medicine. 2012 Aug 23;367(8):705-15.
Pham MX, Teuteberg JJ, Kfoury AG, Starling RC, Deng MC, Cappola TP, Kao A, Anderson AS, Cotts WG, Ewald GA, Baran DA. Gene-expression profiling for rejection surveillance after cardiac transplantation. New England Journal of Medicine. 2010 May 20;362(20):1890-900.
Brakenridge SC, Chen UI, Loftus T, Ungaro R, Dirain M, Kerr A, Zhong L, Bacher R, Starostik P, Ghita G, Midic U. Evaluation of a multivalent transcriptomic metric for diagnosing surgical sepsis and estimating mortality among critically ill patients. JAMA Network Open. 2022 Jul 1;5(7):e2221520-.
Sunnyvale, Calif., July 10, 2023 — Inflammatix, a pioneering molecular diagnostics company, announced today the appointment of Heiner Dreismann, PhD, as a member of the company’s board of directors.
Dr. Dreismann brings to Inflammatix more than 35 years of experience in the life sciences and health care industries and is regarded as a pioneer in the early adoption of polymerase chain reaction (PCR) technique, one of the most ubiquitous technologies in molecular biology and genetics research today. He was CEO of Roche Molecular Systems from 2000-2006 after various leadership roles in Roche’s global Diagnostic Division. Besides Inflammatix, Dr. Dreismann currently serves on several boards of public, private, and non-profit organizations.
“We are thrilled to welcome Dr. Dreismann to the Board. We envision host response-based diagnostics to become ubiquitous as did PCR and couldn’t think of a better person to guide us on our journey. In addition to understanding how to be launch groundbreaking technology, we plan to leverage Heiner’s executive, board and technical experiences to inform strategic decisions as we approach commercialization,” said Inflammatix CEO and Co-Founder Timothy Sweeney, MD, PhD.
Dr. Dreismann commented, “I am so impressed by the Inflammatix approach of immune-based diagnostics, and with the extensive data published to date. Host response diagnostics are poised to finally address significant unmet needs in acute infections, sepsis, and other conditions. I’m excited to help Inflammatix bring their important products to patients worldwide.”
About Inflammatix
Inflammatix, Inc., is an innovative molecular diagnostics company developing novel diagnostics that rapidly read a patient’s immune system to improve care and reduce major public health burdens. The company’s initial focus is acute infections and sepsis, where its tests combine proprietary biomarkers and advanced machine learning to help physicians quickly get the right treatments to the right patients. Each test will be developed to run on the company’s sample-to-answer isothermal instrument platform, enabling the power of precision medicine at the point of care. The Sunnyvale, California-based company is backed by top-tier investors including Khosla Ventures, Northpond Ventures, D1 Capital Partners, Think.Health Ventures, the Stanford StartX Fund, and OSF Ventures.
