2023 in Review
Health And Wellness Study + Technology: A Juncture
Palantir Foundry has long been instrumental in increasing the research study searchings for of our health and life science partners, helping accomplish extraordinary understandings, simplify data gain access to, boost information usability, and facilitate innovative visualization and evaluation of information resources– all while protecting the personal privacy and security of the backing information
In 2023, Factory sustained over 50 peer-reviewed publications in well-regarded journals, covering a varied number of topics– from medical facility procedures, to oncological medicines, to discovering modalities. The year prior, our software program sustained a document variety of peer-reviewed magazines, which we highlighted in a prior blog post
Our partners’ foundational investments in technical framework throughout the height of the COVID- 19 pandemic has actually made the remarkable quantity of publications possible.
Public and commercial healthcare companions have actually proactively scaled their financial investments in information sharing and study software program past COVID reaction to develop a more detailed information structure for biomedical study. For example, the N 3 C Enclave — which houses the data of 21 5 M patients from throughout almost 100 establishments– is being utilized everyday by countless researchers across agencies and organizations. Given the intricacy of accessing, organizing, and using ever-expanding biomedical information, the need for comparable research resources continues to increase.
In this blog post, we take a closer look at some significant magazines from 2023 and analyze what exists ahead for software-backed study.
Emerging Innovation and the Velocity of Scientific Research
The influence of new modern technologies on the scientific venture is increasing research-based results at a formerly impossible scale. Arising technologies and advanced software application are aiding produce a lot more specific, arranged, and easily accessible data possessions, which in turn are enabling scientists to deal with significantly intricate clinical obstacles. Specifically, as a modular, interoperable, and adaptable platform, Foundry has actually been utilized to sustain a varied series of scientific studies with special research functions, consisting of AI-assisted therapeutics recognition, real-world evidence generation, and more.
In 2023, the sector has likewise seen an exponential growth in interest around making use of Expert system (AI)– and in particular, generative AI and large language models (LLM)– in the wellness and life science domain names. Alongside various other core technical innovations (e.g., around information top quality and functionality), the potential for AI-enabled software application to speed up clinical research is much more appealing than ever before. As a commercial leader in AI-enabled software, Palantir has actually gone to the forefront of searching for accountable, safe, and effective methods to apply AI-enabled abilities to sustain our partners across markets in attaining their crucial objectives.
Over the past year, Palantir software application aided drive vital components of our partners’ research and we stand all set to proceed working together with our companions in government, market, and civil society to take on one of the most important obstacles in health and wellness and scientific research in advance. In the next section, we supply concrete instances of just how the power of software program can help advance clinical research study, highlighting some crucial biomedical publications powered by Foundry in 2023
2023 Publications Powered by Palantir Factory
Along with a number of important cancer and COVID therapy research studies, Palantir Foundry additionally enabled brand-new searchings for in the broader field of research study method. Listed below, we highlight a sample of several of one of the most impactful peer-reviewed articles published in 2023 that utilized Palantir Shop to assist drive their study.
Recognizing new effective drug mixes for several myeloma
- Magazine : Cancer Letters
- Writers : Peat, T.J., Gaikwad, S.M., Dubois, W., Gyabaah-Kessie, N., Zhang, S., Gorjifard, S., Phyo, Z., Andres, M., Hughitt, V.K., Simpson, R.M., Miller, M.A., Girvin, A.T., Taylor, A., Williams, D., D’Antonio, N., Zhang, Y., Rajagopalan, A., Flietner, E., Wilson, K., Zhang, X., Shinn, P., Klumpp-Thomas, C., McKnight, C., Itkin, Z., Chen, L., Kazandijian, D., Zhang, J., Michalowski, A.M., Simmons, J.K., Keats, J., Thomas, C.J., Mock, B.A.
- Summary : Multiple myeloma (MM) is regularly resistant to drug treatment, needing ongoing expedition to identify new, reliable restorative combinations. In this research, researchers made use of high-throughput drug screening to determine over 1900 substances with task versus at least 25 of the 47 MM cell lines tested. From these 1900 compounds, 3 61 million mixes were evaluated in silico, and pairs of substances with highly correlated task throughout the 47 cell lines and various systems of activity were chosen for more analysis. Particularly, six (6 medicine mixes worked at 1 decreasing over-expression of a vital protein (MYC) that is commonly linked to the manufacturing of malignant cells and 2 increased expression of the p 16 healthy protein, which can assist the body subdue tumor growth. In addition, three (3 recognized drug mixes boosted opportunities of survival and decreased the development of cancer cells, partly by minimizing task of paths associated with TGFβ/ SMAD signaling, which regulate the cell life process. These preclinical searchings for determine possibly beneficial unique medication combinations for tough to treat multiple myeloma.
New rank-based protein classification method to enhance glioblastoma treatment
- Publication : Cancers
- Authors : Tasci, E., Jagasia, S., Zhuge, Y., Sproull, M., Cooley Zgela, T., Mackey, M., Camphausen, K., Krauze, A.V.
- Recap : Glioblastomas, one of the most usual kind of cancerous brain growths, differ substantially, restricting the ability to assess the organic aspects that drive whether glioblastomas will certainly react to therapy. Nevertheless, data analysis of the proteome– the whole collection of proteins that can be revealed by the lump– can 1 deal non-invasive techniques of identifying glioblastomas to aid educate treatment and 2 recognize healthy protein biomarkers associated with treatments to review response to treatment. In this research, researchers established and evaluated an unique rank-based weighting approach (“RadWise”) for healthy protein features to help ML algorithms focus on the the most relevant aspects that show post-therapy results. RadWise provides an extra efficient pathway to identify the healthy proteins and functions that can be essential targets for therapy of these hostile, fatal tumors.
Identifying liver cancer subtypes most likely to respond to immunotherapy
- Publication : Cell Reports Medicine
- Authors : Budhu, A., Pehrsson, E.C., He, A., Goyal, L., Kelley, R.K., Dang, H., Xie, C., Monge, C., Tandon, M., Ma, L., Revsine, M., Kuhlman, L., Zhang, K., Baiev, I., Lamm, R., Patel, K., Kleiner, D.E., Hewitt, S.M., Tran, B., Shetty, J., Wu, X., Zhao, Y., Shen, T.W., Choudhari, S., Kriga, Y., Ylaya, K., Warner, A.C., Edmondson, E.F., Forgues, M., Greten, T.F., Wang, X.W.
- Recap : Liver cancer is an increasing source of cancer fatalities in the US. This research investigated variant in individual results for a type of immunotherapy making use of immune checkpoint inhibitors. Researchers noted that certain molecular subtypes of cancer cells, specified by 1 the aggressiveness of cancer and 2 the microenvironment of the cancer cells, were connected to higher survival prices with immune checkpoint prevention treatment. Determining these molecular subtypes can assist medical professionals identify whether a client’s distinct cancer cells is likely to reply to this kind of intervention, implying they can use a lot more targeted use immunotherapy and enhance probability of success.
Using formulas to EHR information to presume pregnancy timing for even more precise maternal health study
- Publication : JAMIA, Female’s Health Special Edition
- Authors : Jones, S., Bradwell, K.R. *, Chan, L.E., McMurry, J.A., Olson-Chen, C., Tarleton, J., Wilkins, K.J., Qin, Q., Faherty, E.G., Lau, Y.K., Xie, C., Kao, Y.H., Liebman, M.N., Ljazouli, S. *, Mariona, F., Challa, A., Li, L., Ratcliffe, S.J., Haendel, M.A., Patel, R.C., Hill, E.L.
- Summary : There are indications that COVID- 19 can cause pregnancy difficulties, and pregnant individuals appear to be at greater risk for much more severe COVID- 19 infection. Evaluation of health document (EHR) information can aid supply even more understanding, yet because of information incongruities, it is commonly hard to ascertain 1 pregnancy start and end dates and 2 gestational age of the baby at birth. To aid, scientists adjusted an existing formula for determining gestational age and maternity size that depends on diagnostic codes and shipment dates. To boost the precision of this formula, the researchers layered by themselves data-driven formulas to specifically infer pregnancy start, maternity end, and landmark period throughout a pregnancy’s progression while additionally addressing EHR information disparity. This method can be dependably made use of to make the fundamental inference of pregnancy timing and can be applied to future maternity and maternal research on subjects such as negative maternity end results and maternal mortality.
An unique approach for dealing with EHR information quality issues for professional encounters
- Publication : JAMIA
- Authors : Leese, P., Anand, A., Girvin, A. *, Manna, A. *, Patel, S., Yoo, Y.J., Wong, R., Haendel, M., Chute, C.G., Bennett, T., Hajagos, J., Pfaff, E., Moffitt, R.
- Recap : Clinical encounter data can be a rich resource for study, yet it often differs considerably across suppliers, facilities, and institutions, making it challenging to consistently evaluate. This inconsistency is magnified when multisite digital health and wellness document (EHR) data is networked with each other in a main database. In this study, researchers established an unique, generalizable method for solving professional encounter information for analysis by combining related experiences right into composite “macrovisits.” This method helps adjust and settle EHR experience data concerns in a generalizable, repeatable method, permitting scientists to extra conveniently open the potential of this abundant data for large studies.
Improving transparency in phenotyping for Long COVID study and past
- Magazine : Journal of the American Medical Informatics Association
- Writers : Pfaff, E.R., Girvin, A.T. *, Crosskey, M., Gangireddy, S., Master, H., Wei, W.Q., Kerchberger, V.E., Weiner, M., Harris, P.A., Basford, M., Lunt, C., Chute, C.G., Moffitt, R.A., Haendel, M.; N 3 C and Recuperate Consortia
- Recap : Phenotyping, the process of reviewing and categorizing an organism’s characteristics, can help scientists better comprehend the distinctions in between individuals and groups of individuals, and to recognize particular characteristics that may be linked to specific conditions or problems. Artificial intelligence (ML) can help obtain phenotypes from information, yet these are challenging to share and replicate due to their complexity. Scientists in this study designed and educated an ML-based phenotype to determine patients highly possible to have Long COVID, an increasingly urgent public wellness factor to consider, and showed applicability of this approach for other atmospheres. This is a success tale of just how transparent innovation and collaboration can make phenotyping algorithms extra easily accessible to a wide audience of scientists in informatics, decreasing copied work and supplying them with a device to get to insights quicker, consisting of for various other conditions.
Navigating obstacles for multisite real life data (RWD) data sources
- Publication : BMC Medical Research Study Approach
- Writers : Sidky, H., Youthful, J.C., Girvin, A.T. *, Lee, E., Shao, Y.R., Hotaling, N., Michael, S., Wilkins, K.J., Setoguchi, S., Funk, M.J.; N 3 C Consortium
- Summary : Working with big scale streamlined EHR databases such as N 3 C for research study needs specialized expertise and cautious examination of data quality and efficiency. This research examines the process of assessing data top quality in preparation for research, focusing on medicine efficiency studies. Scientist recognized several approaches and finest techniques to better define crucial study elements consisting of exposure to therapy, standard wellness comorbidities, and essential end results of rate of interest. As big range, systematized real world data sources end up being a lot more prevalent, this is a helpful advance in assisting researchers more effectively navigate their unique data obstacles while opening essential applications for medication development.
What’s Next for Wellness Research Study at Palantir
While 2023 saw essential progress, the new year brings with it brand-new possibilities, along with a seriousness to use the latest technical improvements to one of the most vital wellness problems encountering individuals, areas, and the public at large. For instance, in 2023, the U.S. Government declared its commitment to combating systemic conditions such as cancer cells, and also launched a brand-new wellness company, the Advanced Research Study Projects Firm for Health ( ARPA-H
Furthermore, in 2024, Palantir is pleased to be a market partner in the innovative National AI Research Study Source (NAIRR) pilot program , produced under the auspices of the National Science Foundation (NSF) and with funding from the NIH. As part of the NAIRR pilot– whose launch was routed by the Biden Administration’s Executive Order on Artificial Intelligence — Palantir will certainly be working with its long-time partners at the National Institutes of Health And Wellness (NIH) and N 3 C to support research ahead of time secure, secure, and reliable AI, along with the application of AI to challenges in health care.
In 2024, we’re thrilled to work with partners, brand-new and old, on concerns of vital importance, applying our learnings on data, devices, and research to aid allow purposeful improvements in health and wellness results for all.
To get more information about our continuing work throughout wellness and life scientific researches, go to https://www.palantir.com/offerings/federal-health/
* Authors affiliated with Palantir Technologies