{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T19:48:13Z","timestamp":1792180093413,"version":"4.4.0"},"reference-count":33,"publisher":"Journal of Neurosurgery Publishing Group (JNSPG)","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,8,1]]},"abstract":"<jats:sec>\n<jats:title>OBJECTIVE<\/jats:title>\n<jats:p>Avoiding intracranial hypertension after traumatic brain injury (TBI) is a foundation of neurocritical care, to minimize secondary brain injury related to elevated intracranial pressure (ICP). However, this approach at best is reactive to episodes of intracranial hypertension, allowing for periods of elevated ICP before therapies can be initiated. Accurate prediction of ICP crises before they occur would permit clinicians to implement preventive strategies, minimize total time with ICP above threshold, and potentially avoid secondary injury. The objective of this study was to develop an algorithm capable of predicting the onset of ICP crises with sufficient lead time to enable application of preventative therapies.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title>METHODS<\/jats:title>\n<jats:p>Thirty-six patients admitted to a level I trauma center with severe TBI (Glasgow Coma Scale score &lt; 8) between April 2015 and January 2019 who underwent continuous intraparenchymal ICP monitor placement were retrospectively identified. Continuous ICP data were extracted from each monitoring period (range 4\u201396 hours of monitoring). An ICP crisis was treated as a binary outcome, defined as ICP &gt; 22 mm Hg for at least 75% of the data within a 5-minute interval. ICP data preceding each ICP crisis were grouped into four total data sets of 1- and 2-hour epochs, each with 10- to 20-minute lead-time intervals before an ICP crisis. Crisis and noncrisis events were identified from continuous time-series data and randomly split into 70% for training and 30% for testing, from a subset of 30 patients. Machine learning algorithms were trained to predict ICP crises, including light gradient boosting, extreme gradient boosting, and random forest. Accuracy and area under the receiver operating characteristic curve (AUC) were measured to compare performance. The most predictive algorithm was optimized using feature selection and hyperparameter tuning to avoid overfitting, and then tested on a validation subset of 5 patients. Precision, recall, F1 score, and accuracy were measured.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title>RESULTS<\/jats:title>\n<jats:p>The random forest model demonstrated the highest accuracy (range 0.82\u20130.88) and AUC (range 0.86\u20130.88) across all four data sets. Further validation testing revealed high precision (0.76), relatively low recall (0.46), and overall strong predictive performance (F1 score 0.57, accuracy 0.86) for ICP crises. Decision curve analysis showed that the model provided net benefit at probability thresholds above 0.1 and below 0.9.<\/jats:p>\n<\/jats:sec>\n<jats:sec>\n<jats:title>CONCLUSIONS<\/jats:title>\n<jats:p>The presented model can provide accurate and timely forecasts of ICP crises in patients with severe TBI 10\u201320 minutes prior to their occurrence. If validated and implemented in clinical workflows, this algorithm can enable earlier intervention for ICP crises, more effective treatment of intracranial hypertension, and potentially improved outcomes following severe TBI.<\/jats:p>\n<\/jats:sec>","DOI":"10.3171\/2022.12.jns221860","type":"journal-article","created":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T15:39:31Z","timestamp":1674833971000},"page":"528-535","source":"Crossref","is-referenced-by-count":30,"title":["Prediction of intracranial pressure crises after severe traumatic brain injury using machine learning algorithms"],"prefix":"10.3171","volume":"139","author":[{"given":"Dmitriy","family":"Petrov","sequence":"first","affiliation":[{"name":"Departments of Neurosurgery and"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephen P.","family":"Miranda","sequence":"additional","affiliation":[{"name":"Departments of Neurosurgery and"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ramani","family":"Balu","sequence":"additional","affiliation":[{"name":"Neurology, University of Pennsylvania, Philadelphia, Pennsylvania; and"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Connor","family":"Wathen","sequence":"additional","affiliation":[{"name":"Departments of Neurosurgery and"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alex","family":"Vaz","sequence":"additional","affiliation":[{"name":"Departments of Neurosurgery and"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vinodh","family":"Mohan","sequence":"additional","affiliation":[{"name":"IBM Corp., Armonk, New York"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Colon","sequence":"additional","affiliation":[{"name":"IBM Corp., Armonk, New York"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ramon","family":"Diaz-Arrastia","sequence":"additional","affiliation":[{"name":"Neurology, University of Pennsylvania, Philadelphia, Pennsylvania; and"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1754","reference":[{"issue":"2 Suppl","key":"b1","series-title":"Neurocrit Care","first-page":"S282","article-title":"The International Multidisciplinary Consensus Conference on Multimodality Monitoring in Neurocritical Care: a list of recommendations and additional conclusions: a statement for healthcare professionals from the Neurocritical Care Society and the European Society of Intensive Care Medicine","volume":"21","author":"Le Roux P","year":"2014","unstructured":"Le Roux P, Menon DK, Citerio G,  The International Multidisciplinary Consensus Conference on Multimodality Monitoring in Neurocritical Care: a list of recommendations and additional conclusions: a statement for healthcare professionals from the Neurocritical Care Society and the European Society of Intensive Care Medicine. Neurocrit Care. 2014;21(2 Suppl):S282\u2013S29.25501689"},{"issue":"2","key":"b2","series-title":"Anesthesiol Clin North Am","first-page":"441","article-title":"Current concepts in neurocritical care","volume":"20","author":"Fahy BG","year":"2002","unstructured":"Fahy BG, Sivaraman V. Current concepts in neurocritical care. Anesthesiol Clin North Am. 2002;20(2):441\u2013462.12166004"},{"issue":"8","key":"b3","series-title":"Nat Rev Neurol","first-page":"451","article-title":"Multimodal monitoring and neurocritical care bioinformatics","volume":"7","author":"Hemphill JC","year":"2011","unstructured":"Hemphill JC, Andrews P, De Georgia M. Multimodal monitoring and neurocritical care bioinformatics. Nat Rev Neurol. 2011;7(8):451\u2013460.21750522"},{"key":"b4","series-title":"Translational Research in Traumatic Brain Injury","article-title":"Intracranial pressure monitoring and management","author":"Le Roux P","year":"2016","unstructured":"Le Roux P. Intracranial pressure monitoring and management. In: Laskowitz D, Grant G, eds. Translational Research in Traumatic Brain Injury. CRC Press; 2016."},{"issue":"11","key":"b5","series-title":"Cochrane Database Syst Rev","first-page":"CD002043","article-title":"Routine intracranial pressure monitoring in acute coma","volume":"2015","author":"Forsyth RJ","year":"2015","unstructured":"Forsyth RJ, Raper J, Todhunter E. Routine intracranial pressure monitoring in acute coma. Cochrane Database Syst Rev. 2015;2015(11):CD002043.26522651"},{"issue":"8","key":"b6","series-title":"Acta Neurochir (Wien)","first-page":"1615","article-title":"Clinical applications of intracranial pressure monitoring in traumatic brain injury: report of the Milan consensus conference","volume":"156","author":"Stocchetti N","year":"2014","unstructured":"Stocchetti N, Picetti E, Berardino M,  Clinical applications of intracranial pressure monitoring in traumatic brain injury: report of the Milan consensus conference. Acta Neurochir (Wien). 2014;156(8):1615\u20131622.24849391"},{"issue":"2","key":"b7","series-title":"Curr Opin Anaesthesiol","first-page":"117","article-title":"Intracranial pressure: why we monitor it, how to monitor it, what to do with the number and what\u2019s the future?","volume":"24","author":"Lavinio A","year":"2011","unstructured":"Lavinio A, Menon DK. Intracranial pressure: why we monitor it, how to monitor it, what to do with the number and what\u2019s the future? Curr Opin Anaesthesiol. 2011;24(2):117\u2013123."},{"issue":"12","key":"b8","series-title":"PLoS One","first-page":"e0243427","article-title":"Impact of duration and magnitude of raised intracranial pressure on outcome after severe traumatic brain injury: a CENTER-TBI high-resolution group study","volume":"15","author":"\u00c5kerlund CA","year":"2020","unstructured":"\u00c5kerlund CA, Donnelly J, Zeiler FA,  Impact of duration and magnitude of raised intracranial pressure on outcome after severe traumatic brain injury: a CENTER-TBI high-resolution group study. PLoS One. 2020;15(12):e0243427."},{"issue":"suppl 1","key":"b9","series-title":"VIII. Intracranial pressure thresholds. J Neurotrauma","first-page":"S55","article-title":"Guidelines for the management of severe traumatic brain injury","volume":"24","author":"Bratton SL","year":"2007","unstructured":"Bratton SL, Chestnut RM, Ghajar J,  Guidelines for the management of severe traumatic brain injury. VIII. Intracranial pressure thresholds. J Neurotrauma. 2007;24(suppl 1):S55-S58.17511546"},{"issue":"5","key":"b10","series-title":"Intensive Care Med","first-page":"919","article-title":"A management algorithm for adult patients with both brain oxygen and intracranial pressure monitoring: the Seattle International Severe Traumatic Brain Injury Consensus Conference (SIBICC)","volume":"46","author":"Chesnut R","year":"2020","unstructured":"Chesnut R, Aguilera S, Buki A,  A management algorithm for adult patients with both brain oxygen and intracranial pressure monitoring: the Seattle International Severe Traumatic Brain Injury Consensus Conference (SIBICC). Intensive Care Med. 2020;46(5):919\u2013929.31965267"},{"issue":"12","key":"b11","series-title":"Intensive Care Med","first-page":"1783","article-title":"A management algorithm for patients with intracranial pressure monitoring: the Seattle International Severe Traumatic Brain Injury Consensus Conference (SIBICC)","volume":"45","author":"Hawryluk GWJ","year":"2019","unstructured":"Hawryluk GWJ, Aguilera S, Buki A,  A management algorithm for patients with intracranial pressure monitoring: the Seattle International Severe Traumatic Brain Injury Consensus Conference (SIBICC). Intensive Care Med. 2019;45(12):1783\u20131794.31659383"},{"issue":"suppl 1","key":"b12","series-title":"Neurocrit Care","first-page":"S60","article-title":"Emergency neurological life support: intracranial hypertension and herniation","volume":"17","author":"Stevens RD","year":"2012","unstructured":"Stevens RD, Huff JS, Duckworth J, Papangelou A, Weingart SD, Smith WS. Emergency neurological life support: intracranial hypertension and herniation. Neurocrit Care. 2012;17(suppl 1):S60-S65.22936079"},{"issue":"22","key":"b13","series-title":"N Engl J Med","first-page":"2121","article-title":"Traumatic intracranial hypertension","volume":"370","author":"Stocchetti N","year":"2014","unstructured":"Stocchetti N, Maas AI. Traumatic intracranial hypertension. N Engl J Med. 2014;370(22):2121\u20132130.24869722"},{"issue":"1","key":"b14","series-title":"Intensive Care Med","first-page":"124","article-title":"Prediction model for intracranial hypertension demonstrates robust performance during external validation on the CENTER-TBI dataset","volume":"47","author":"Carra G","year":"2021","unstructured":"Carra G, G\u00fciza F, Depreitere B, Meyfroidt G. Prediction model for intracranial hypertension demonstrates robust performance during external validation on the CENTER-TBI dataset. Intensive Care Med. 2021;47(1):124\u2013126.33001234"},{"issue":"3","key":"b15","series-title":"Crit Care Med","first-page":"e316","article-title":"Early detection of increased intracranial pressure episodes in traumatic brain injury: external validation in an adult and in a pediatric cohort","volume":"45","author":"G\u00fciza F","year":"2017","unstructured":"G\u00fciza F, Depreitere B, Piper I,  Early detection of increased intracranial pressure episodes in traumatic brain injury: external validation in an adult and in a pediatric cohort. Crit Care Med. 2017;45(3):e316\u2013e320."},{"issue":"2","key":"b16","series-title":"Crit Care Med","first-page":"554","article-title":"Novel methods to predict increased intracranial pressure during intensive care and long-term neurologic outcome after traumatic brain injury: development and validation in a multicenter dataset","volume":"41","author":"G\u00fciza F","year":"2013","unstructured":"G\u00fciza F, Depreitere B, Piper I, Van den Berghe G, Meyfroidt G. Novel methods to predict increased intracranial pressure during intensive care and long-term neurologic outcome after traumatic brain injury: development and validation in a multicenter dataset. Crit Care Med. 2013;41(2):554\u2013564."},{"issue":"9","key":"b17","series-title":"Crit Care Med","first-page":"1754","article-title":"Predicting intracranial pressure and brain tissue oxygen crises in patients with severe traumatic brain injury","volume":"44","author":"Myers RB","year":"2016","unstructured":"Myers RB, Lazaridis C, Jermaine CM, Robertson CS, Rusin CG. Predicting intracranial pressure and brain tissue oxygen crises in patients with severe traumatic brain injury. Crit Care Med. 2016;44(9):1754\u20131761.27315192"},{"issue":"5","key":"b18","series-title":"IEEE Trans Biomed Eng","first-page":"1070","article-title":"Forecasting ICP elevation based on prescient changes of intracranial pressure waveform morphology","volume":"57","author":"Hu X","year":"2010","unstructured":"Hu X, Xu P, Asgari S, Vespa P, Bergsneider M. Forecasting ICP elevation based on prescient changes of intracranial pressure waveform morphology. IEEE Trans Biomed Eng. 2010;57(5):1070\u20131078.20659820"},{"issue":"10","key":"b19","series-title":"IEEE J Biomed Health Inform","first-page":"3967","article-title":"Prediction of life-threatening intracranial hypertension during the acute phase of traumatic brain injury using machine learning","volume":"25","author":"Lee HJ","year":"2021","unstructured":"Lee HJ, Kim H, Kim YT, Won K, Czosnyka M, Kim DJ. Prediction of life-threatening intracranial hypertension during the acute phase of traumatic brain injury using machine learning. IEEE J Biomed Health Inform. 2021;25(10):3967\u20133976.34061756"},{"issue":"8","key":"b20","series-title":"Med Eng Phys","first-page":"1058","article-title":"Intracranial hypertension prediction using extremely randomized decision trees","volume":"34","author":"Scalzo F","year":"2012","unstructured":"Scalzo F, Hamilton R, Asgari S, Kim S, Hu X. Intracranial hypertension prediction using extremely randomized decision trees. Med Eng Phys. 2012;34(8):1058\u20131065.22401795"},{"issue":"4","key":"b21","series-title":"Acta Neurochir (Wien)","first-page":"401","article-title":"Intracranial pressure processing with artificial neural networks: prediction of ICP trends","volume":"142","author":"Swiercz M","year":"2000","unstructured":"Swiercz M, Mariak Z, Krejza J, Lewko J, Szydlik P. Intracranial pressure processing with artificial neural networks: prediction of ICP trends. Acta Neurochir (Wien). 2000;142(4):401\u2013406.10883336"},{"key":"b22","series-title":"Proceedings of 17th International Conference of the Engineering in Medicine and Biology Society.","first-page":"1045","article-title":"A wavelet based neural network for prediction of ICP signal","author":"Tsui FC","year":"1995","unstructured":"Tsui FC, Sun M, Li CC, Sclabassi RJ. A wavelet based neural network for prediction of ICP signal. In: Proceedings of 17th International Conference of the Engineering in Medicine and Biology Society.IEEE;1995:1045-1046."},{"key":"b23","series-title":"Annu Int Conf IEEE Eng Med Biol Soc","first-page":"7111","article-title":"Artificial neural network based intracranial pressure mean forecast algorithm for medical decision support","volume":"2011","author":"Zhang F","year":"2011","unstructured":"Zhang F, Feng M, Pan SJ,  Artificial neural network based intracranial pressure mean forecast algorithm for medical decision support. Annu Int Conf IEEE Eng Med Biol Soc. 2011;2011:7111\u20137114.22255977"},{"issue":"24","key":"b24","series-title":"Neural Comput Appl","first-page":"18069","article-title":"The importance of interpretability and visualization in machine learning for applications in medicine and health care","volume":"32","author":"Vellido A","year":"2020","unstructured":"Vellido A. The importance of interpretability and visualization in machine learning for applications in medicine and health care. Neural Comput Appl. 2020;32(24):18069\u201318083."},{"issue":"1","key":"b25","series-title":"Neurosurgery","first-page":"6","article-title":"Guidelines for the management of severe traumatic brain injury,","volume":"80","author":"Carney N","year":"2017","unstructured":"Carney N, Totten AM, O\u2019Reilly C,  Guidelines for the management of severe traumatic brain injury,. fourth edition. Neurosurgery. 2017;80(1):6\u201315.27654000"},{"issue":"2","key":"b26","series-title":"Neurocrit Care","first-page":"258","article-title":"Critical thresholds for cerebrovascular reactivity after traumatic brain injury","volume":"16","author":"Sorrentino E","year":"2012","unstructured":"Sorrentino E, Diedler J, Kasprowicz M,  Critical thresholds for cerebrovascular reactivity after traumatic brain injury. Neurocrit Care. 2012;16(2):258\u2013266.21964774"},{"key":"b27","first-page":"1","article-title":"Introduction to Time Series and Forecasting","author":"Brockwell PJ","year":"2016","unstructured":"Brockwell PJ, Davis RA. Introduction to Time Series and Forecasting. 3rd ed. Springer International Publishing; 2016:1."},{"key":"b28","series-title":"Neurocomputing","first-page":"72","article-title":"Time Series FeatuRe Extraction on basis of Scalable Hypothesis tests (tsfresh\u2014a Python package)","volume":"307","author":"Christ M","year":"2018","unstructured":"Christ M, Braun N, Neuffer J, Kempa-Liehr AW. Time Series FeatuRe Extraction on basis of Scalable Hypothesis tests (tsfresh\u2014a Python package). Neurocomputing. 2018;307:72\u201377."},{"issue":"6","key":"b29","series-title":"Med Decis Making","first-page":"565","article-title":"Decision curve analysis: a novel method for evaluating prediction models","volume":"26","author":"Vickers AJ","year":"2006","unstructured":"Vickers AJ, Elkin EB. Decision curve analysis: a novel method for evaluating prediction models. Med Decis Making. 2006;26(6):565\u2013574.17099194"},{"issue":"1","key":"b30","series-title":"J Biomed Eng","first-page":"5","article-title":"Time series methods in the monitoring of intracranial pressure. Part 1: Problems, suggestions for a monitoring scheme and review of appropriate techniques","volume":"5","author":"Allen R","year":"1983","unstructured":"Allen R. Time series methods in the monitoring of intracranial pressure. Part 1: Problems, suggestions for a monitoring scheme and review of appropriate techniques. J Biomed Eng. 1983;5(1):5\u201318.6338297"},{"issue":"2","key":"b31","series-title":"Crit Care","first-page":"127","article-title":"Novel representation of physiologic states during critical illness and recovery","volume":"14","author":"Buchman TG","year":"2010","unstructured":"Buchman TG. Novel representation of physiologic states during critical illness and recovery. Crit Care. 2010;14(2):127.20236462"},{"issue":"4","key":"b32","series-title":"Anesthesiology","first-page":"663","article-title":"Machine-learning algorithm to predict hypotension based on high-fidelity arterial pressure waveform analysis","volume":"129","author":"Hatib F","year":"2018","unstructured":"Hatib F, Jian Z, Buddi S,  Machine-learning algorithm to predict hypotension based on high-fidelity arterial pressure waveform analysis. Anesthesiology. 2018;129(4):663\u2013674.29894315"},{"issue":"11","key":"b33","series-title":"JAMA","first-page":"1052","article-title":"Effect of a machine learning-derived early warning system for intraoperative hypotension vs standard care on depth and duration of intraoperative hypotension during elective noncardiac surgery: the HYPE randomized clinical trial","volume":"323","author":"Wijnberge M","year":"2020","unstructured":"Wijnberge M, Geerts BF, Hol L,  Effect of a machine learning-derived early warning system for intraoperative hypotension vs standard care on depth and duration of intraoperative hypotension during elective noncardiac surgery: the HYPE randomized clinical trial. JAMA. 2020;323(11):1052\u20131060.32065827"}],"container-title":["Journal of Neurosurgery"],"original-title":[],"link":[{"URL":"https:\/\/thejns.org\/view\/journals\/j-neurosurg\/139\/2\/article-p528.xml","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/thejns.org\/downloadpdf\/journals\/j-neurosurg\/139\/2\/article-p528.xml","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/thejns.org\/downloadpdf\/journals\/j-neurosurg\/139\/2\/article-p528.xml","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,18]],"date-time":"2024-05-18T10:46:30Z","timestamp":1716029190000},"score":1,"resource":{"primary":{"URL":"https:\/\/thejns.org\/view\/journals\/j-neurosurg\/139\/2\/article-p528.xml"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,1]]},"references-count":33,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.3171\/2022.12.jns221860","relation":{},"ISSN":["0022-3085","1933-0693"],"issn-type":[{"value":"0022-3085","type":"print"},{"value":"1933-0693","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,1]]}}}