2023 in Evaluation
Wellness Research + Innovation: A Juncture
Palantir Foundry has long contributed in increasing the study findings of our health and life science companions, helping attain unprecedented understandings, simplify data access, enhance information functionality, and assist in innovative visualization and evaluation of information sources– all while securing the personal privacy and security of the support data
In 2023, Factory supported over 50 peer-reviewed publications in prestigious journals, covering a varied number of subjects– from hospital procedures, to oncological medicines, to discovering methods. The year prior, our software program supported a document number of peer-reviewed publications, which we highlighted in a prior article
Our partners’ foundational financial investments in technological infrastructure during the peak of the COVID- 19 pandemic has actually made the excellent quantity of publications possible.
Public and commercial health care partners have actually proactively scaled their financial investments in information sharing and research study software program beyond COVID feedback to construct a more comprehensive data structure for biomedical research study. For instance, the N 3 C Enclave — which houses the data of 21 5 M people from throughout virtually 100 institutions– is being used everyday by hundreds of scientists across agencies and organizations. Provided the intricacy of accessing, arranging, and utilizing ever-expanding biomedical data, the need for similar research study resources remains to climb.
In this blog post, we take a closer look at some noteworthy magazines from 2023 and analyze what lies in advance for software-backed research.
Emerging Technology and the Acceleration of Scientific Research Study
The influence of new innovations on the clinical enterprise is accelerating research-based outcomes at a previously difficult scale. Emerging innovations and advanced software program are aiding produce a lot more accurate, organized, and easily accessible information assets, which in turn are enabling researchers to deal with significantly complicated scientific obstacles. In particular, as a modular, interoperable, and flexible platform, Factory has actually been utilized to sustain a diverse variety of clinical research studies with unique study functions, including AI-assisted therapeutics identification, real-world evidence generation, and more.
In 2023, the industry has likewise seen a rapid growth in interest around making use of Artificial Intelligence (AI)– and specifically, generative AI and large language versions (LLM)– in the wellness and life scientific research domain names. Together with various other core technical improvements (e.g., around data high quality and functionality), the possibility for AI-enabled software program to speed up scientific study is more encouraging than ever before. As a business leader in AI-enabled software application, Palantir has actually been at the forefront of finding responsible, safe and secure, and reliable methods to apply AI-enabled abilities to sustain our companions throughout industries in achieving their most important goals.
Over the previous year, Palantir software aided drive essential elements of our companions’ study and we stand ready to continue working together with our companions in federal government, industry, and civil culture to deal with the most important difficulties in wellness and science in advance. In the next section, we offer concrete examples of how the power of software program can aid breakthrough scientific research study, highlighting some crucial biomedical publications powered by Factory in 2023
2023 Publications Powered by Palantir Foundry
Along with a variety of vital cancer and COVID treatment researches, Palantir Foundry likewise made it possible for brand-new findings in the more comprehensive area of study approach. Below, we highlight a sample of some of one of the most impactful peer-reviewed write-ups released in 2023 that utilized Palantir Foundry to aid drive their research.
Determining new efficient medicine mixes for several myeloma
- Publication : Cancer cells Letters
- Authors : 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.
- Recap : Numerous myeloma (MM) is frequently immune to medication therapy, requiring ongoing exploration to identify new, reliable therapeutic mixes. In this research, researchers utilized high-throughput drug testing to recognize over 1900 compounds with activity versus at least 25 of the 47 MM cell lines evaluated. From these 1900 substances, 3 61 million mixes were evaluated in silico, and sets of compounds with very associated activity throughout the 47 cell lines and various devices of activity were picked for additional evaluation. Especially, six (6 drug mixes were effective at 1 reducing over-expression of an essential protein (MYC) that is usually connected to the manufacturing of deadly cells and 2 raised expression of the p 16 protein, which can aid the body suppress lump growth. In addition, 3 (3 identified medication combinations boosted possibilities of survival and decreased the growth of cancer cells, partially by reducing task of pathways involved in TGFβ/ SMAD signaling, which manage the cell life process. These preclinical findings recognize possibly valuable novel medicine mixes for challenging to treat multiple myeloma.
New rank-based protein category technique to boost glioblastoma treatment
- Publication : Cancers
- Writers : Tasci, E., Jagasia, S., Zhuge, Y., Sproull, M., Cooley Zgela, T., Mackey, M., Camphausen, K., Krauze, A.V.
- Summary : Glioblastomas, one of the most typical kind of malignant brain tumors, vary considerably, limiting the capability to evaluate the biological variables that drive whether glioblastomas will reply to therapy. However, data analysis of the proteome– the whole collection of healthy proteins that can be expressed by the growth– can 1 deal non-invasive approaches of identifying glioblastomas to assist notify treatment and 2 determine healthy protein biomarkers associated with treatments to review response to therapy. In this research study, researchers established and checked a novel rank-based weighting technique (“RadWise”) for protein features to assist ML formulas focus on the one of the most appropriate variables that suggest post-therapy end results. RadWise supplies a more reliable path to determine the healthy proteins and attributes that can be vital targets for treatment of these aggressive, deadly lumps.
Determining liver cancer cells subtypes most likely to react to immunotherapy
- Publication : Cell Records 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., Detector, A.C., Edmondson, E.F., Forgues, M., Greten, T.F., Wang, X.W.
- Summary : Liver cancer is a climbing cause of cancer cells deaths in the United States. This study examined variation in person outcomes for a type of immunotherapy using immune checkpoint inhibitors. Researchers noted that specific molecular subtypes of cancer, defined by 1 the aggression of cancer cells and 2 the microenvironment of the cancer cells, were linked to greater survival prices with immune checkpoint inhibitor therapy. Recognizing these molecular subtypes can aid doctors identify whether a person’s one-of-a-kind cancer cells is likely to respond to this type of intervention, implying they can use a lot more targeted use of immunotherapy and boost possibility of success.
Using algorithms to EHR information to infer pregnancy timing for more exact mother’s health research
- Magazine : JAMIA, Female’s Health and wellness Scandal sheet
- Writers : 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 create pregnancy difficulties, and expecting persons seem at higher danger for more serious COVID- 19 infection. Analysis of wellness document (EHR) information can help give more understanding, however due to information disparities, it is frequently tough to identify 1 maternity begin and end dates and 2 gestational age of the infant at birth. To aid, scientists adapted an existing formula for establishing gestational age and pregnancy size that relies upon diagnostic codes and distribution days. To boost the precision of this algorithm, the scientists layered on their own data-driven formulas to specifically infer maternity begin, pregnancy end, and site period throughout a pregnancy’s progression while likewise dealing with EHR information variance. This approach can be dependably used to make the fundamental reasoning of pregnancy timing and can be applied to future maternity and maternity study on topics such as adverse maternity end results and maternal death.
A novel technique for dealing with EHR information high quality issues for clinical experiences
- Publication : JAMIA
- Writers : 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 : Professional experience data can be an abundant resource for research study, but it usually differs considerably across providers, facilities, and institutions, making it tough to evenly evaluate. This inconsistency is magnified when multisite electronic health record (EHR) information is networked together in a main database. In this research study, researchers established a novel, generalizable approach for fixing medical experience information for evaluation by integrating relevant experiences into composite “macrovisits.” This methodology helps manipulate and solve EHR encounter information issues in a generalizable, repeatable means, enabling researchers to more easily open the possibility of this abundant data for large research studies.
Improving openness in phenotyping for Long COVID research and past
- Magazine : Journal of the American Medical Informatics Association
- Authors : 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 RECOVER Consortia
- Recap : Phenotyping, the procedure of reviewing and classifying an organism’s attributes, can aid researchers better understand the differences in between individuals and groups of people, and to recognize certain traits that might be linked to particular diseases or conditions. Machine learning (ML) can aid obtain phenotypes from data, however these are testing to share and duplicate as a result of their intricacy. Researchers in this study created and educated an ML-based phenotype to determine people very possible to have Long COVID, an increasingly immediate public wellness consideration, and revealed applicability of this method for various other environments. This is a success story of how transparent modern technology and collaboration can make phenotyping algorithms more available to a broad target market of scientists in informatics, reducing copied work and giving them with a device to get to insights much faster, including for other diseases.
Browsing obstacles for multisite real life information (RWD) databases
- Publication : BMC Medical Study Methodology
- Writers : Sidky, H., Young, 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 large range centralized EHR databases such as N 3 C for research study calls for specialized expertise and cautious examination of information top quality and completeness. This study takes a look at the process of evaluating information quality to prepare for research, focusing on drug effectiveness research studies. Scientist determined a number of methods and finest practices to much better define crucial research components including exposure to treatment, standard health and wellness comorbidities, and essential end results of rate of interest. As large range, systematized real life databases come to be extra common, this is a useful progression in aiding researchers better browse their special data difficulties while opening important applications for medicine growth.
What’s Next for Health Study at Palantir
While 2023 saw important progression, the new year brings with it brand-new possibilities, in addition to a seriousness to apply the most recent technological advancements to the most crucial health issues facing individuals, communities, and the general public at big. For instance, in 2023, the united state Federal government reaffirmed its dedication to combating systemic illness such as cancer cells, and also introduced a brand-new wellness agency, the Advanced Study Projects Agency for Health ( ARPA-H
In addition, in 2024, Palantir is happy to be a sector partner in the ingenious National AI Research Study Resource (NAIRR) pilot program , created under the auspices of the National Science Structure (NSF) and with funding from the NIH. As part of the NAIRR pilot– whose launch was directed by the Biden Management’s Exec Order on Artificial Intelligence — Palantir will certainly be collaborating with its long-time companions at the National Institutes of Health (NIH) and N 3 C to support research study beforehand safe, secure, and reliable AI, in addition to the application of AI to obstacles in health care.
In 2024, we’re delighted to work with companions, brand-new and old, on concerns of important importance, using our learnings on information, devices, and research to aid make it possible for purposeful improvements in health and wellness outcomes for all.
To read more regarding our continuing work throughout health and life sciences, see https://www.palantir.com/offerings/federal-health/
* Authors affiliated with Palantir Technologies