2023 in Review
Health Research Study + Innovation: A Juncture
Palantir Factory has long contributed in accelerating the research study findings of our wellness and life science partners, aiding attain unmatched understandings, streamline data access, enhance data usability, and assist in innovative visualization and evaluation of information sources– all while shielding the personal privacy and safety of the support information
In 2023, Foundry supported over 50 peer-reviewed publications in well-regarded journals, covering a varied number of topics– from medical facility procedures, to oncological medicines, to learning techniques. The year prior, our software application supported a record number of peer-reviewed magazines, which we highlighted in a previous blog post
Our partners’ fundamental investments in technological infrastructure during the top of the COVID- 19 pandemic has actually made the excellent amount of magazines feasible.
Public and commercial health care companions have proactively scaled their investments in information sharing and research software program beyond COVID response to construct an extra thorough data foundation for biomedical research. As an example, the N 3 C Enclave — which houses the data of 21 5 M patients from across almost 100 organizations– is being used daily by hundreds of scientists across firms and organizations. Offered the complexity of accessing, organizing, and using ever-expanding biomedical information, the need for comparable study resources continues to rise.
In this post, we take a closer take a look at some significant publications from 2023 and examine what lies ahead for software-backed research study.
Arising Technology and the Velocity of Scientific Research
The impact of new modern technologies on the clinical business is accelerating research-based results at a formerly impossible range. Emerging modern technologies and advanced software are helping create much more accurate, arranged, and obtainable data possessions, which consequently are enabling researchers to take on progressively intricate clinical obstacles. In particular, as a modular, interoperable, and adaptable system, Shop has actually been utilized to sustain a diverse range of clinical research studies with special study features, including AI-assisted therapeutics recognition, real-world proof generation, and much more.
In 2023, the market has actually likewise seen an exponential growth in passion around utilizing Artificial Intelligence (AI)– and in particular, generative AI and huge language models (LLM)– in the health and wellness and life science domain names. Together with various other core technical innovations (e.g., around data quality and functionality), the potential for AI-enabled software application to increase clinical study is much more encouraging than ever. As an industrial leader in AI-enabled software, Palantir has gone to the center of searching for responsible, protected, and efficient means to use AI-enabled capacities to sustain our partners across markets in accomplishing their most important goals.
Over the previous year, Palantir software assisted drive vital parts of our partners’ study and we stand ready to proceed collaborating with our companions in federal government, market, and civil society to take on one of the most important difficulties in health and wellness and scientific research in advance. In the next area, we offer concrete examples of exactly how the power of software application can aid breakthrough clinical research, highlighting some vital biomedical magazines powered by Factory in 2023
2023 Publications Powered by Palantir Shop
Along with a number of essential cancer and COVID therapy research studies, Palantir Foundry likewise enabled new searchings for in the broader field of study approach. Below, we highlight a sample of a few of one of the most impactful peer-reviewed write-ups published in 2023 that utilized Palantir Shop to assist drive their research.
Recognizing brand-new reliable medication mixes for several myeloma
- Magazine : Cancer 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.
- Summary : Numerous myeloma (MM) is regularly immune to medication therapy, needing ongoing exploration to identify new, reliable therapeutic combinations. In this study, researchers utilized high-throughput drug screening to determine over 1900 substances with task versus a minimum of 25 of the 47 MM cell lines examined. From these 1900 compounds, 3 61 million mixes were reviewed in silico, and sets of compounds with highly correlated activity across the 47 cell lines and different systems of action were selected for further evaluation. Especially, six (6 medication mixes were effective at 1 minimizing over-expression of a key healthy protein (MYC) that is commonly linked to the manufacturing of deadly cells and 2 increased expression of the p 16 healthy protein, which can assist the body reduce tumor growth. In addition, three (3 recognized medication mixes raised opportunities of survival and decreased the development of cancer cells, partly by reducing task of paths associated with TGFβ/ SMAD signaling, which manage the cell life cycle. These preclinical searchings for identify potentially helpful novel drug mixes for difficult to treat numerous myeloma.
New rank-based protein classification method to enhance glioblastoma therapy
- Magazine : Cancers cells
- 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 usual sort of cancerous mind growths, differ greatly, limiting the capability to examine the organic aspects that drive whether glioblastomas will certainly respond to therapy. Nevertheless, data evaluation of the proteome– the entire collection of proteins that can be expressed by the tumor– can 1 deal non-invasive techniques of classifying glioblastomas to assist inform therapy and 2 determine protein biomarkers related to interventions to review reaction to treatment. In this study, scientists created and tested an unique rank-based weighting technique (“RadWise”) for healthy protein includes to help ML formulas focus on the the most appropriate aspects that indicate post-therapy end results. RadWise supplies a more effective pathway to identify the proteins and attributes that can be key targets for treatment of these aggressive, deadly lumps.
Determining liver cancer cells subtypes most likely to react to immunotherapy
- Magazine : Cell Reports Medication
- 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.
- Recap : Liver cancer cells is a rising root cause of cancer cells deaths in the United States. This research explored variation in person end results for a type of immunotherapy using immune checkpoint preventions. Researchers kept in mind that specific molecular subtypes of cancer cells, defined by 1 the aggressiveness of cancer and 2 the microenvironment of the cancer cells, were linked to higher survival prices with immune checkpoint inhibitor treatment. Identifying these molecular subtypes can aid doctors identify whether an individual’s unique cancer is likely to respond to this kind of intervention, implying they can apply a lot more targeted use immunotherapy and improve probability of success.
Applying formulas to EHR data to infer maternity timing for more precise mother’s health and wellness research
- Magazine : JAMIA, Women’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., Hillside, E.L.
- Summary : There are indications that COVID- 19 can create maternity difficulties, and expecting persons seem at greater risk for much more serious COVID- 19 infection. Evaluation of health and wellness document (EHR) data can aid give more insight, yet as a result of information incongruities, it is typically tough to determine 1 maternity beginning and end days and 2 gestational age of the baby at birth. To assist, scientists adjusted an existing formula for determining gestational age and pregnancy size that relies on diagnostic codes and delivery days. To enhance the precision of this algorithm, the researchers layered on their own data-driven algorithms to precisely infer maternity start, maternity end, and site timespan throughout a pregnancy’s progression while additionally dealing with EHR data disparity. This method can be accurately used to make the foundational inference of maternity timing and can be related to future maternity and maternity study on subjects such as adverse maternity end results and mother’s mortality.
A novel method for solving EHR data top quality problems for professional 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.
- Summary : Clinical encounter information can be an abundant source for research study, however it commonly varies significantly throughout providers, facilities, and organizations, making it tough to uniformly examine. This variance is amplified when multisite digital wellness record (EHR) information is networked with each other in a central data source. In this study, scientists established an unique, generalizable approach for settling clinical encounter data for evaluation by incorporating relevant experiences into composite “macrovisits.” This methodology aids adjust and resolve EHR experience data issues in a generalizable, repeatable method, permitting researchers to much more quickly unlock the capacity of this abundant data for large-scale research 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
- Recap : Phenotyping, the process of assessing and classifying a microorganism’s qualities, can help scientists better recognize the differences between people and groups of individuals, and to identify specific characteristics that may be linked to specific conditions or problems. Machine learning (ML) can aid acquire phenotypes from information, but these are challenging to share and replicate because of their intricacy. Researchers in this research devised and trained an ML-based phenotype to recognize people highly potential to have Lengthy COVID, an increasingly urgent public health factor to consider, and showed applicability of this technique for various other settings. This is a success story of just how clear innovation and partnership can make phenotyping formulas extra obtainable to a wide audience of scientists in informatics, reducing copied job and providing them with a device to reach understandings quicker, consisting of for other illness.
Browsing obstacles for multisite real world information (RWD) data sources
- Magazine : BMC Medical Research 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 : Collaborating with large scale systematized EHR data sources such as N 3 C for research calls for specialized knowledge and careful assessment of information quality and completeness. This research examines the procedure of analyzing information high quality in preparation for research, focusing on drug efficacy studies. Researchers recognized numerous techniques and best techniques to better characterize crucial study aspects including direct exposure to therapy, baseline health and wellness comorbidities, and crucial outcomes of passion. As huge scale, centralized real life databases become extra common, this is a helpful step forward in assisting researchers better navigate their special data challenges while opening important applications for medicine advancement.
What’s Following for Health Research Study at Palantir
While 2023 saw vital progress, the brand-new year brings with it brand-new possibilities, as well as a necessity to apply the most up to date technical advancements to one of the most crucial health and wellness concerns dealing with individuals, neighborhoods, and the general public at huge. For example, in 2023, the U.S. Government reaffirmed its commitment to combating systemic illness such as cancer, and also released a new wellness company, the Advanced Research Study Projects Firm for Health ( ARPA-H
Furthermore, in 2024, Palantir is happy to be a market companion in the cutting-edge National AI Research Source (NAIRR) pilot program , developed 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 Administration’s Exec Order on Artificial Intelligence — Palantir will be working with its long-time companions at the National Institutes of Health And Wellness (NIH) and N 3 C to sustain research study ahead of time safe, secure, and reliable AI, along with the application of AI to challenges in health care.
In 2024, we’re thrilled to deal with partners, new and old, on problems of critical significance, using our understandings on data, devices, and study to help allow purposeful renovations in health results for all.
For more information concerning our proceeding job across health and life scientific researches, browse through https://www.palantir.com/offerings/federal-health/
* Authors connected with Palantir Technologies