1. Topological network analysis of patient similarity for precision management of acute blood pressure in spinal cord injury
- Author
-
Torres-Espín, Abel, Haefeli, Jenny, Ehsanian, Reza, Torres, Dolores, Almeida, Carlos A, Huie, J Russell, Chou, Austin, Morozov, Dmitriy, Sanderson, Nicole, Dirlikov, Benjamin, Suen, Catherine G, Nielson, Jessica L, Kyritsis, Nikos, Hemmerle, Debra D, Talbott, Jason F, Manley, Geoffrey T, Dhall, Sanjay S, Whetstone, William D, Bresnahan, Jacqueline C, Beattie, Michael S, McKenna, Stephen L, Pan, Jonathan Z, Ferguson, Adam R, Beattie, Bresnahan, JC, Burke, JF, Chou, A, de Almeida, CA, Dhall, SS, DiGiorgio, AM, Doung-Fernandez, X, Ferguson, AR, Haefeli, J, Hemmerle, DD, Huie, Kyritsis, N, Manley, GT, Moncivais, S, Omondi, C, Pan, JZ, Pascual, LU, Singh, V, Talbott, JF, Thomas, LH, Torres-Espin, A, Weinstein, P, and Whetstone, WD
- Subjects
Biomedical and Clinical Sciences ,Clinical Sciences ,Neurosciences ,Physical Injury - Accidents and Adverse Effects ,Traumatic Head and Spine Injury ,Spinal Cord Injury ,Neurological ,Adult ,Aged ,Aged ,80 and over ,Arterial Pressure ,Blood Pressure ,Humans ,Middle Aged ,Monitoring ,Intraoperative ,Recovery of Function ,Retrospective Studies ,Spinal Cord Injuries ,topological networks analysis ,spinal cord injury ,blood pressure ,machine learning ,surgery ,Human ,TRACK-SCI Investigators ,computational biology ,human ,medicine ,systems biology ,Biochemistry and Cell Biology ,Biological sciences ,Biomedical and clinical sciences ,Health sciences - Abstract
BackgroundPredicting neurological recovery after spinal cord injury (SCI) is challenging. Using topological data analysis, we have previously shown that mean arterial pressure (MAP) during SCI surgery predicts long-term functional recovery in rodent models, motivating the present multicenter study in patients.MethodsIntra-operative monitoring records and neurological outcome data were extracted (n = 118 patients). We built a similarity network of patients from a low-dimensional space embedded using a non-linear algorithm, Isomap, and ensured topological extraction using persistent homology metrics. Confirmatory analysis was conducted through regression methods.ResultsNetwork analysis suggested that time outside of an optimum MAP range (hypotension or hypertension) during surgery was associated with lower likelihood of neurological recovery at hospital discharge. Logistic and LASSO (least absolute shrinkage and selection operator) regression confirmed these findings, revealing an optimal MAP range of 76-[104-117] mmHg associated with neurological recovery.ConclusionsWe show that deviation from this optimal MAP range during SCI surgery predicts lower probability of neurological recovery and suggest new targets for therapeutic intervention.FundingNIH/NINDS: R01NS088475 (ARF); R01NS122888 (ARF); UH3NS106899 (ARF); Department of Veterans Affairs: 1I01RX002245 (ARF), I01RX002787 (ARF); Wings for Life Foundation (ATE, ARF); Craig H. Neilsen Foundation (ARF); and DOD: SC150198 (MSB); SC190233 (MSB).
- Published
- 2021