{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T09:53:54Z","timestamp":1782208434121,"version":"3.54.5"},"reference-count":26,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T00:00:00Z","timestamp":1781740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Physiol."],"abstract":"<jats:p>Decompression sickness (DCS) is a low-incidence but potentially severe consequence of hyperbaric exposure. Probabilistic decompression models offer a framework to quantify this risk, yet their calibration is challenged by the scarcity of empirical outcome data. In this study, we propose a gradient-based optimization model to predict DCS probability, trained on 924 dive profiles from the US Navy Experimental Diving Unit XVal-He-9 tables, representing predefined DCS probabilities (2.3% and 4%), and optimized based on actual body tissues grouped in five compartments. The model achieved high predictive accuracy (MAE: 0.535%; RMSE: 0.694%) with consistent performance across training and test sets, indicating limited overfitting. Reduced accuracy was observed in intermediate depth ranges (100\u2013130fsw or 30\u201339msw). Out-of-sample evaluation on 31 high-risk dives (three DCS cases) showed general agreement between predicted and observed incidence while suggesting a potential contribution of repetitive exposures not accounted for in the model. These results demonstrate that gradient-based optimization, trained based on existing probabilistic tables, seems to be capable of satisfactorily predicting decompression sickness risk for a given dive profile. Additionally, future studies can further adjust the loss function to account for individual or dive-related indicators, leading to a more individualized risk function.<\/jats:p>","DOI":"10.3389\/fphys.2026.1852640","type":"journal-article","created":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T04:38:28Z","timestamp":1781757508000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A gradient-based optimization model for predicting decompression sickness risk"],"prefix":"10.3389","volume":"17","author":[{"given":"Sergio Rhein","family":"Schirato","sequence":"first","affiliation":[{"name":"Department of Physiology, Biosciences Institute, University of S\u00e3o Paulo","place":["S\u00e3o Paulo, Brazil"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Massimo","family":"Pieri","sequence":"additional","affiliation":[{"name":"Divers Alert Network (DAN) Europe Research Division","place":["Roseto degli Abruzzi, Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Riccardo","family":"Pelliccia","sequence":"additional","affiliation":[{"name":"Divers Alert Network (DAN) Europe Research Division","place":["Roseto degli Abruzzi, Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessandro","family":"Marroni","sequence":"additional","affiliation":[{"name":"Divers Alert Network (DAN) Europe Research Division","place":["Roseto degli Abruzzi, Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Costantino","family":"Balestra","sequence":"additional","affiliation":[{"name":"Divers Alert Network (DAN) Europe Research Division","place":["Roseto degli Abruzzi, Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jos\u00e9 Guilherme","family":"Chaui-Berlinck","sequence":"additional","affiliation":[{"name":"Department of Physiology, Biosciences Institute, University of S\u00e3o Paulo","place":["S\u00e3o Paulo, Brazil"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,18]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2024.1395846","article-title":"Physiology of deep closed circuit rebreather mixed gas diving: vascular gas emboli and biological changes during a week-long liveaboard safari","volume":"15","author":"Balestra","year":"2024","journal-title":"Front. Physiol."},{"key":"B2","doi-asserted-by":"publisher","first-page":"103518","DOI":"10.1016\/j.compbiomed.2019.103518","article-title":"A new form of admissible pressure for Haldanian decompression models","volume":"115","author":"Blasselle","year":"2019","journal-title":"Comput. Biol. Med."},{"key":"B3","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1017\/s0022172400003399","article-title":"The prevention of compressed-air illness","volume":"8","author":"Boycott","year":"1908","journal-title":"Jornal. Hygiene."},{"key":"B4","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-662-02409-6","volume-title":"Decompression, decompression sickness","author":"B\u00fchlman","year":"1984"},{"key":"B5","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1016\/j.compbiomed.2014.10.012","article-title":"A ternary model of decompression sickness in rats","volume":"55","author":"Buzzacott","year":"2014","journal-title":"Comput. Biol. Med."},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2017.01587","article-title":"Dive risk factors, Gas Bubble formation, and decompression illness in recreational SCUBA diving: Analysis of DAN Europe DSL data base","volume":"8","author":"Cialoni","year":"2017","journal-title":"Front. Psychol."},{"key":"B7","article-title":"Validation of XVAL-He-8_040 and XVAL-He-9_040 Thalmann algorithm parameter sets","author":"Doolette","year":"2019","journal-title":"(Technical Report No. NEDU TR 19-05). Navy Experimental Diving Unit"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.21236\/ad1003571","article-title":"Decompression from he-n 2 -o 2 (trimix) bounce dives is not more efficient than from he-o 2 (heliox)","author":"Doolette","year":"2015"},{"key":"B9","article-title":"Thalmann algorithm parameter sets for support of constant 1.3 atm po2 he-o2 diving TO 300 FSW navy experimental diving unit","author":"Doolette","year":"2018"},{"key":"B10","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1113\/jphysiol.2004.077842","article-title":"Perfusion-diffusion compartmental models describe cerebral helium kinetics at high and low cerebral blood flows in sheep","volume":"563","author":"Doolette","year":"2005","journal-title":"J. Physiol."},{"key":"B11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0172665","article-title":"The probability and severity of decompression sickness","volume":"12","author":"Howle","year":"2017","journal-title":"PloS One"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1117","DOI":"10.1016\/j.compbiomed.2009.09.006","article-title":"A computationally advantageous system for fitting probabilistic decompression models to empirical data","volume":"39","author":"Howle","year":"2009","journal-title":"Comput. Biol. Med."},{"key":"B13","doi-asserted-by":"publisher","first-page":"262","DOI":"10.28920\/dhm55.3.228-236","article-title":"Revised guideline for central nervous system oxygen toxicity exposure limits when using an inspired PO2 of 1.3 atmospheres","volume":"55","author":"Hoyt","year":"2025","journal-title":"Diving. Hyperbaric. Med. J."},{"key":"B14","unstructured":"Logistic regression in rare events data\n          \n          \n            \n              King\n              G.\n            \n          \n          \n          2001"},{"key":"B15","article-title":"Adam: A method for stochastic optimization","volume-title":"Presented at the International Conference on Learning Representations (ICLR)","author":"Kingma","year":"2017"},{"key":"B16","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/j.compbiomed.2017.04.014","article-title":"Probabilistic pharmacokinetic models of decompression sickness in humans, part 1: Coupled perfusion-limited compartments","volume":"86","author":"Murphy","year":"2017","journal-title":"Comput. Biol. Med."},{"key":"B17","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.compbiomed.2017.11.011","article-title":"Probabilistic pharmacokinetic models of decompression sickness in humans: Part 2, coupled perfusion-diffusion models","volume":"92","author":"Murphy","year":"2018","journal-title":"Comput. Biol. Med."},{"key":"B18","doi-asserted-by":"publisher","first-page":"207","DOI":"10.22462\/03.04.2022.6","article-title":"Post-decompression bubble and inflammation interactions: a non-extensive dynamical system model","volume":"49","author":"Schirato","year":"2022","journal-title":"Undersea. Hyperb. Med."},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.36922\/jctr.24.00021","article-title":"A broad appraisal of decompression-induced physiological stress in different simulated dive profiles","volume":"10","author":"Schirato","year":"2024","journal-title":"J. Clin. Transl. Res."},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.22462\/01.01.2023.37","article-title":"Proposed thalmann algorithm air diving decompression table for the Swedish armed forces Undersea & hyperbaric medicine","author":"Silvanius","year":"2023"},{"key":"B21","article-title":"Statistically based decompression tables X: Real-time decompression algorithm using a probabilistic model (Report No. NMRI 96-06)","author":"Survanshi","year":"1996"},{"key":"B22","first-page":"255","article-title":"Improved probabilistic decompression model risk predictions using linear-exponential kinetics","volume":"24","author":"Thalmann","year":"1997","journal-title":"Undersea. Hyperbaric. Med."},{"key":"B23","article-title":"Model of n 2 exchanges based on physiology of o 2 transport 1 research article 1 running head : model of n 2 exchanges based on physiology of o 2 transport 2 N 2 exchanges in hyperbaric environments: towards a 3 model based on physiological gas transport (O 2 and 4 CO 2) 5 6","author":"Theron","year":"2025"},{"key":"B24","doi-asserted-by":"publisher","first-page":"18831","DOI":"10.1074\/jbc.m113.543702","article-title":"Neutrophils generate microparticles during exposure to inert gases due to cytoskeletal oxidative stress","volume":"289","author":"Thom","year":"2014","journal-title":"J. Biol. Chem."},{"key":"B25","article-title":"Microparticle and interleukin IL-1\u03b2 production associated with human high-pressure exposures","author":"Thom","year":"2018"},{"key":"B26","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1152\/japplphysiol.00384.2015","article-title":"Separating the roles of nitrogen and oxygen in high pressure-induced blood-borne microparticle elevations, neutrophil activation, and vascular injury in mice","volume":"119","author":"Yang","year":"2015","journal-title":"J. Appl. Physiol."}],"container-title":["Frontiers in Physiology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2026.1852640\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T09:44:25Z","timestamp":1782207865000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2026.1852640\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,18]]},"references-count":26,"alternative-id":["10.3389\/fphys.2026.1852640"],"URL":"https:\/\/doi.org\/10.3389\/fphys.2026.1852640","relation":{},"ISSN":["1664-042X"],"issn-type":[{"value":"1664-042X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,18]]},"article-number":"1852640"}}