2023 in Review
Wellness Research + Innovation: A Juncture
Palantir Factory has long contributed in speeding up the research study findings of our health and wellness and life scientific research partners, helping achieve extraordinary insights, streamline information gain access to, boost data functionality, and assist in innovative visualization and analysis of information resources– all while shielding the privacy and safety of the support information
In 2023, Factory supported over 50 peer-reviewed publications in renowned journals, covering a diverse variety of subjects– from medical facility procedures, to oncological drugs, to finding out techniques. The year prior, our software application supported a record number of peer-reviewed magazines, which we highlighted in a previous article
Our partners’ fundamental investments in technological framework during the peak of the COVID- 19 pandemic has actually made the impressive amount of publications feasible.
Public and commercial healthcare companions have actually proactively scaled their investments in data sharing and study software beyond COVID reaction to build an extra extensive data structure for biomedical study. For example, the N 3 C Enclave — which houses the data of 21 5 M people from across almost 100 organizations– is being utilized everyday by countless scientists across companies and organizations. Given the complexity of accessing, organizing, and utilizing ever-expanding biomedical information, the need for similar study sources remains to climb.
In this article, we take a closer check out some noteworthy publications from 2023 and analyze what exists ahead for software-backed research.
Arising Innovation and the Velocity of Scientific Research Study
The influence of new innovations on the scientific enterprise is accelerating research-based outputs at a formerly impossible scale. Arising technologies and advanced software are helping produce more exact, arranged, and accessible information assets, which consequently are allowing researchers to take on progressively complex clinical difficulties. In particular, as a modular, interoperable, and versatile system, Foundry has actually been used to sustain a diverse series of clinical research studies with one-of-a-kind research features, consisting of AI-assisted therapeutics identification, real-world evidence generation, and much more.
In 2023, the sector has additionally seen a rapid growth in passion around making use of Expert system (AI)– and in particular, generative AI and big language versions (LLM)– in the health and life science domains. Along with other core technical developments (e.g., around data top quality and functionality), the capacity for AI-enabled software application to increase scientific research is extra appealing than ever before. As an industrial leader in AI-enabled software, Palantir has actually gone to the leading edge of finding responsible, secure, and efficient ways to apply AI-enabled capacities to support our companions across sectors in accomplishing their crucial missions.
Over the past year, Palantir software program helped drive vital elements of our partners’ research study and we stand ready to proceed interacting with our companions in federal government, market, and civil society to take on one of the most pressing obstacles in wellness and science in advance. In the next section, we provide concrete examples of exactly how the power of software application can aid advance scientific study, highlighting some key biomedical publications powered by Shop in 2023
2023 Publications Powered by Palantir Shop
In addition to a variety of important cancer and COVID treatment researches, Palantir Foundry also enabled new findings in the broader area of study technique. Below, we highlight a sample of several of the most impactful peer-reviewed short articles released in 2023 that made use of Palantir Factory to assist drive their study.
Determining brand-new effective medication mixes for multiple myeloma
- Magazine : 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 drug treatment, requiring continued exploration to identify brand-new, effective healing combinations. In this study, researchers used high-throughput medication testing to identify over 1900 compounds with task against at the very least 25 of the 47 MM cell lines evaluated. From these 1900 substances, 3 61 million mixes were reviewed in silico, and pairs of compounds with highly associated task throughout the 47 cell lines and different devices of activity were chosen for further evaluation. Particularly, 6 (6 medicine combinations worked at 1 decreasing over-expression of an essential healthy protein (MYC) that is typically connected to the production of malignant cells and 2 increased expression of the p 16 protein, which can assist the body reduce lump growth. In addition, 3 (3 identified medicine combinations enhanced possibilities of survival and decreased the growth of cancer cells, partially by minimizing task of pathways involved in TGFβ/ SMAD signaling, which manage the cell life cycle. These preclinical searchings for determine potentially beneficial novel medication combinations for difficult to treat multiple myeloma.
New rank-based healthy protein classification method to improve glioblastoma treatment
- Publication : Cancers cells
- Authors : Tasci, E., Jagasia, S., Zhuge, Y., Sproull, M., Cooley Zgela, T., Mackey, M., Camphausen, K., Krauze, A.V.
- Recap : Glioblastomas, the most typical sort of malignant brain tumors, differ considerably, restricting the capability to analyze the biological variables that drive whether glioblastomas will certainly react to therapy. However, information evaluation of the proteome– the whole set of healthy proteins that can be revealed by the tumor– can 1 deal non-invasive approaches of classifying glioblastomas to help notify treatment and 2 determine healthy protein biomarkers associated with interventions to evaluate reaction to treatment. In this research, scientists developed and examined an unique rank-based weighting technique (“RadWise”) for protein features to aid ML algorithms focus on the the most pertinent factors that suggest post-therapy outcomes. RadWise offers a more efficient pathway to recognize the healthy proteins and functions that can be essential targets for therapy of these aggressive, fatal lumps.
Determining liver cancer cells subtypes likely to respond to immunotherapy
- Publication : Cell Records Medication
- Writers : 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 cells is a rising reason for cancer cells deaths in the US. This research examined variant in person outcomes for a type of immunotherapy using immune checkpoint preventions. Scientist kept in mind that particular molecular subtypes of cancer cells, specified by 1 the aggression of cancer and 2 the microenvironment of the cancer cells, were connected to higher survival rates with immune checkpoint prevention treatment. Determining these molecular subtypes can assist doctors identify whether an individual’s distinct cancer is likely to respond to this type of intervention, implying they can apply much more targeted use immunotherapy and enhance possibility of success.
Using formulas to EHR information to infer maternity timing for even more accurate mother’s health research study
- Magazine : JAMIA, Women’s Health Special Edition
- 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 trigger pregnancy complications, and expectant individuals seem at higher threat for extra extreme COVID- 19 infection. Evaluation of health and wellness document (EHR) information can aid supply even more insight, but because of data disparities, it is often hard to ascertain 1 maternity begin and end dates and 2 gestational age of the child at birth. To assist, researchers adjusted an existing formula for identifying gestational age and pregnancy size that relies upon analysis codes and delivery days. To increase the precision of this algorithm, the scientists layered by themselves data-driven algorithms to precisely presume maternity begin, maternity end, and landmark time frames throughout a pregnancy’s progression while likewise addressing EHR data inconsistency. This technique can be dependably used to make the foundational reasoning of maternity timing and can be applied to future pregnancy and maternity study on subjects such as negative pregnancy results and maternal death.
An unique approach for dealing with EHR information quality concerns for medical encounters
- Magazine : 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 : Medical experience data can be an abundant resource for research, yet it often differs substantially across companies, centers, and institutions, making it tough to evenly evaluate. This incongruity is multiplied when multisite electronic wellness document (EHR) information is networked with each other in a main data source. In this research study, scientists created an unique, generalizable method for solving clinical encounter data for analysis by incorporating relevant experiences into composite “macrovisits.” This approach aids control and deal with EHR experience information problems in a generalizable, repeatable means, allowing researchers to a lot more quickly open the possibility of this abundant data for large-scale studies.
Improving openness in phenotyping for Long COVID research and past
- Magazine : Journal of the American Medical Informatics Organization
- 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 RECOVER Consortia
- Summary : Phenotyping, the process of reviewing and categorizing an organism’s attributes, can aid researchers much better understand the distinctions in between people and teams of people, and to recognize details traits that may be connected to specific illness or conditions. Machine learning (ML) can assist derive phenotypes from data, however these are challenging to share and recreate as a result of their complexity. Scientists in this research developed and educated an ML-based phenotype to identify clients very possible to have Lengthy COVID, an increasingly immediate public wellness consideration, and revealed applicability of this method for various other settings. This is a success tale of exactly how clear innovation and collaboration can make phenotyping algorithms extra available to a broad target market of researchers in informatics, decreasing duplicated job and giving them with a tool to get to understandings faster, consisting of for various other illness.
Navigating challenges for multisite real life data (RWD) databases
- Publication : BMC Medical Study Technique
- Authors : 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
- Recap : Dealing with huge scale streamlined EHR data sources such as N 3 C for study requires specialized understanding and cautious analysis of data high quality and efficiency. This research analyzes the procedure of evaluating data quality to prepare for study, focusing on medication efficiency researches. Researchers identified numerous techniques and best practices to better define vital research components consisting of direct exposure to therapy, standard health and wellness comorbidities, and crucial end results of passion. As big scale, centralized real world data sources become extra common, this is a practical advance in assisting researchers better browse their one-of-a-kind information obstacles while opening critical applications for medicine development.
What’s Next for Health Study at Palantir
While 2023 saw essential progression, the new year brings with it new possibilities, in addition to a seriousness to use the current technological developments to the most important health concerns encountering individuals, neighborhoods, and the public at huge. As an example, in 2023, the U.S. Federal government reaffirmed its commitment to combating systemic conditions such as cancer cells, and also launched a brand-new health and wellness agency, the Advanced Study Projects Firm for Health And Wellness ( ARPA-H
In addition, in 2024, Palantir is honored to be an industry partner in the ingenious National AI Research Resource (NAIRR) pilot program , created under the auspices of the National Scientific Research Foundation (NSF) and with funding from the NIH. As component of the NAIRR pilot– whose launch was routed by the Biden Management’s Executive Order on Artificial Intelligence — Palantir will be working with its veteran companions at the National Institutes of Health (NIH) and N 3 C to sustain research beforehand secure, safe and secure, and reliable AI, in addition to the application of AI to obstacles in healthcare.
In 2024, we’re delighted to deal with companions, new and old, on problems of critical significance, using our discoverings on information, tools, and research to aid allow significant enhancements in health results for all.
To find out more about our proceeding work across health and wellness and life sciences, visit https://www.palantir.com/offerings/federal-health/
* Authors connected with Palantir Technologies