2023 in Evaluation
Health Research + Innovation: A Pivotal Moment
Palantir Factory has long been instrumental in increasing the research study findings of our wellness and life scientific research companions, aiding accomplish unmatched understandings, streamline data gain access to, boost information functionality, and promote sophisticated visualization and evaluation of information sources– all while protecting the personal privacy and security of the support information
In 2023, Foundry sustained over 50 peer-reviewed magazines in renowned journals, covering a varied number of subjects– from health center operations, to oncological medicines, to learning techniques. The year prior, our software application sustained a record variety of peer-reviewed magazines, which we highlighted in a previous blog post
Our partners’ foundational investments in technological framework throughout the top of the COVID- 19 pandemic has actually made the impressive amount of magazines feasible.
Public and commercial healthcare companions have proactively scaled their investments in information sharing and study software application beyond COVID response to build an extra detailed information structure for biomedical study. For instance, the N 3 C Enclave — which houses the data of 21 5 M clients from throughout almost 100 organizations– is being used daily by hundreds of scientists across agencies and organizations. Given the complexity of accessing, arranging, and using ever-expanding biomedical information, the need for similar study sources remains to climb.
In this blog post, we take a closer take a look at some noteworthy publications from 2023 and examine what exists in advance for software-backed research.
Arising Modern Technology and the Acceleration of Scientific Study
The impact of brand-new modern technologies on the scientific venture is accelerating research-based outcomes at a previously difficult scale. Arising technologies and advanced software program are helping develop extra specific, organized, and available information assets, which subsequently are enabling researchers to take on increasingly complex clinical obstacles. In particular, as a modular, interoperable, and versatile system, Foundry has actually been utilized to support a diverse range of scientific researches with one-of-a-kind research study functions, consisting of AI-assisted therapies recognition, real-world evidence generation, and extra.
In 2023, the market has also seen a rapid development in interest around utilizing Artificial Intelligence (AI)– and in particular, generative AI and big language models (LLM)– in the health and wellness and life science domain names. Together with other core technological developments (e.g., around data quality and use), the capacity for AI-enabled software program to accelerate scientific study is a lot more appealing than ever before. As a business leader in AI-enabled software, Palantir has been at the leading edge of finding liable, safe, and effective methods to use AI-enabled capabilities to support our companions throughout markets in achieving their crucial objectives.
Over the previous year, Palantir software program helped drive key parts of our partners’ research study and we stand prepared to continue collaborating with our partners in federal government, industry, and civil society to tackle one of the most pressing difficulties in health and wellness and scientific research ahead. In the next section, we supply concrete instances of how the power of software application can assist advance scientific research study, highlighting some vital biomedical publications powered by Foundry in 2023
2023 Publications Powered by Palantir Shop
Along with a number of essential cancer cells and COVID therapy researches, Palantir Shop likewise enabled brand-new searchings for in the more comprehensive field of study method. Listed below, we highlight an example of some of one of the most impactful peer-reviewed write-ups published in 2023 that made use of Palantir Foundry to assist drive their research.
Identifying brand-new reliable drug combinations for multiple 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 : Several myeloma (MM) is frequently resistant to drug treatment, requiring ongoing exploration to identify brand-new, efficient restorative combinations. In this study, researchers utilized high-throughput medicine screening to determine over 1900 compounds with task against a minimum of 25 of the 47 MM cell lines tested. From these 1900 substances, 3 61 million combinations were assessed in silico, and sets of compounds with extremely associated task across the 47 cell lines and various devices of activity were picked for further evaluation. Especially, 6 (6 drug mixes were effective at 1 minimizing over-expression of a vital protein (MYC) that is commonly connected to the manufacturing of deadly cells and 2 enhanced expression of the p 16 protein, which can aid the body reduce lump growth. In addition, three (3 determined medicine combinations increased opportunities of survival and decreased the growth of cancer cells, partially by reducing activity of paths involved in TGFβ/ SMAD signaling, which regulate the cell life process. These preclinical findings recognize potentially valuable novel medicine combinations for hard to treat numerous myeloma.
New rank-based protein category method to boost glioblastoma therapy
- Publication : Cancers
- Authors : Tasci, E., Jagasia, S., Zhuge, Y., Sproull, M., Cooley Zgela, T., Mackey, M., Camphausen, K., Krauze, A.V.
- Summary : Glioblastomas, the most typical type of cancerous mind lumps, vary substantially, limiting the capacity to examine the organic elements that drive whether glioblastomas will reply to therapy. Nevertheless, information analysis of the proteome– the whole collection of healthy proteins that can be shared by the growth– can 1 deal non-invasive approaches of categorizing glioblastomas to aid inform treatment and 2 determine protein biomarkers connected with interventions to review response to therapy. In this study, researchers developed and tested a novel rank-based weighting technique (“RadWise”) for healthy protein features to aid ML algorithms concentrate on the the most appropriate factors that show post-therapy results. RadWise supplies an extra effective pathway to determine the healthy proteins and functions that can be essential targets for therapy of these aggressive, fatal growths.
Identifying liver cancer subtypes most likely to react to immunotherapy
- Magazine : Cell Records Medicine
- 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., Warner, A.C., Edmondson, E.F., Forgues, M., Greten, T.F., Wang, X.W.
- Summary : Liver cancer cells is an increasing reason for cancer cells fatalities in the US. This study checked out variant in individual results for a type of immunotherapy using immune checkpoint inhibitors. Scientist noted that particular molecular subtypes of cancer, defined by 1 the aggression of cancer and 2 the microenvironment of the cancer cells, were connected to higher survival prices with immune checkpoint inhibitor therapy. Determining these molecular subtypes can help physicians determine whether an individual’s special cancer cells is most likely to respond to this type of treatment, meaning they can apply extra targeted use immunotherapy and enhance probability of success.
Using formulas to EHR data to infer pregnancy timing for even more exact maternal wellness research
- Magazine : JAMIA, Women’s Wellness 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.
- Recap : There are indications that COVID- 19 can trigger pregnancy issues, and expecting individuals appear to be at greater danger for extra extreme COVID- 19 infection. Analysis of wellness document (EHR) information can aid provide even more understanding, however as a result of data disparities, it is usually difficult to establish 1 pregnancy beginning and end dates and 2 gestational age of the baby at birth. To aid, scientists adjusted an existing algorithm for determining gestational age and pregnancy size that relies upon analysis codes and distribution days. To increase the precision of this algorithm, the researchers layered on their own data-driven formulas to specifically presume pregnancy start, pregnancy end, and landmark amount of time throughout a pregnancy’s development while also resolving EHR information variance. This approach can be reliably used to make the foundational inference of pregnancy timing and can be applied to future maternity and maternal research on subjects such as damaging maternity end results and maternal death.
An unique approach for settling EHR information high quality issues for scientific encounters
- 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.
- Summary : Medical experience data can be a rich resource for research study, however it usually varies substantially across companies, centers, and organizations, making it challenging to consistently evaluate. This disparity is magnified when multisite digital health and wellness record (EHR) data is networked with each other in a central database. In this study, scientists developed an unique, generalizable method for settling scientific encounter information for analysis by integrating relevant encounters into composite “macrovisits.” This method aids manipulate and solve EHR encounter data issues in a generalizable, repeatable means, allowing researchers to a lot more easily open the possibility of this abundant information for massive researches.
Improving transparency in phenotyping for Long COVID study and beyond
- 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 process of evaluating and categorizing an organism’s features, can assist researchers much better recognize the distinctions in between individuals and teams of people, and to identify particular attributes that might be connected to particular diseases or problems. Machine learning (ML) can aid obtain phenotypes from data, but these are challenging to share and reproduce due to their intricacy. Researchers in this study designed and educated an ML-based phenotype to identify patients very probable to have Long COVID, a significantly immediate public health and wellness factor to consider, and revealed applicability of this technique for various other settings. This is a success tale of how clear technology and cooperation can make phenotyping formulas more easily accessible to a broad target market of researchers in informatics, reducing copied work and giving them with a tool to get to insights quicker, consisting of for other illness.
Navigating difficulties for multisite real world information (RWD) data sources
- Magazine : BMC Medical Study Method
- 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 huge range systematized EHR data sources such as N 3 C for research study requires specialized expertise and mindful analysis of information high quality and efficiency. This research study takes a look at the procedure of evaluating information quality to prepare for research, concentrating on medicine efficacy studies. Scientist recognized numerous approaches and finest methods to better identify important research aspects including exposure to therapy, baseline wellness comorbidities, and essential results of interest. As large scale, centralized real life databases become more common, this is a practical step forward in aiding scientists more effectively browse their distinct information difficulties while unlocking critical applications for medicine growth.
What’s Following for Wellness Research Study at Palantir
While 2023 saw vital development, the brand-new year brings with it brand-new possibilities, in addition to an urgency to use the most recent technological innovations to one of the most vital wellness problems facing people, communities, and the general public at big. For example, in 2023, the U.S. Government declared its commitment to combating systemic conditions such as cancer cells, and even launched a new health firm, the Advanced Research Projects Company for Wellness ( ARPA-H
Furthermore, in 2024, Palantir is happy to be an industry companion in the innovative 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 component of the NAIRR pilot– whose launch was directed by the Biden Management’s Executive Order on Expert System — Palantir will be working with its veteran companions at the National Institutes of Wellness (NIH) and N 3 C to support study beforehand secure, safe, and credible AI, as well as the application of AI to challenges in healthcare.
In 2024, we’re excited to collaborate with companions, new and old, on concerns of essential significance, applying our learnings on information, tools, and study to aid make it possible for meaningful improvements in health and wellness outcomes for all.
To get more information about our proceeding job across health and wellness and life sciences, visit https://www.palantir.com/offerings/federal-health/
* Authors associated with Palantir Technologies