Automated real-world data integration improves cancer outcome prediction

• Published in: Nature (London) Vol. 636; no. 8043; pp. 728 - 736
• Main Authors: Jee, Justin, Fong, Christopher, Pichotta, Karl, Tran, Thinh Ngoc, Luthra, Anisha, Waters, Michele, Fu, Chenlian, Altoe, Mirella, Liu, Si-Yang, Maron, Steven B., Ahmed, Mehnaj, Kim, Susie, Pirun, Mono, Chatila, Walid K., de Bruijn, Ino, Pasha, Arfath, Kundra, Ritika, Gross, Benjamin, Mastrogiacomo, Brooke, Aprati, Tyler J., Liu, David, Gao, JianJiong, Capelletti, Marzia, Pekala, Kelly, Loudon, Lisa, Perry, Maria, Bandlamudi, Chaitanya, Donoghue, Mark, Satravada, Baby Anusha, Martin, Axel, Shen, Ronglai, Chen, Yuan, Brannon, A. Rose, Chang, Jason, Braunstein, Lior, Li, Anyi, Safonov, Anton, Stonestrom, Aaron, Sanchez-Vela, Pablo, Wilhelm, Clare, Robson, Mark, Scher, Howard, Ladanyi, Marc, Reis-Filho, Jorge S., Solit, David B., Jones, David R., Gomez, Daniel, Yu, Helena, Chakravarty, Debyani, Yaeger, Rona, Abida, Wassim, Park, Wungki, O’Reilly, Eileen M., Garcia-Aguilar, Julio, Socci, Nicholas, Sanchez-Vega, Francisco, Carrot-Zhang, Jian, Stetson, Peter D., Levine, Ross, Rudin, Charles M., Berger, Michael F., Shah, Sohrab P., Schrag, Deborah, Razavi, Pedram, Kehl, Kenneth L., Li, Bob T., Riely, Gregory J., Schultz, Nikolaus
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 19.12.2024; Nature Publishing Group
• Subjects: 45/23; 692/308/575; 692/699/67; Accuracy; Adenocarcinoma; Annotations; Automation; Cancer; Cancer therapies; Data integration; Datasets; Datasets as Topic; DNA sequencing; Electronic Health Records; Female; Gene sequencing; Genomics; Histopathology; Humanities and Social Sciences; Humans; Immunotherapy; Lung cancer; Lungs; Machine Learning; Male; Medical research; Metastases; Metastasis; Models, Biological; multidisciplinary; Natural Language Processing; Neoplasm Metastasis - diagnosis; Neoplasms - drug therapy; Neoplasms - genetics; Neoplasms - pathology; Oncology; Patients; Prognosis; Prostate; Radiation; Radiology; Registries; Science; Science (multidisciplinary); Tumors; Unstructured data

The digitization of health records and growing availability of tumour DNA sequencing provide an opportunity to study the determinants of cancer outcomes with unprecedented richness. Patient data are often stored in unstructured text and siloed datasets. Here we combine natural language processing an...