Journal of Clinical Monitoring and Computing最新文献

{"title":"High frequency variability index in predicting postoperative pain in video/robotic-assisted thoracoscopic surgery under combined general anesthesia and peripheral nerve block: an observational study.","authors":"Keisuke Yoshida, Takayuki Hasegawa, Takahiro Hakozaki, Tatsumi Yakushiji, Yuzo Iseki, Yuya Itakura, Shinju Obara, Satoki Inoue","doi":"10.1007/s10877-024-01205-7","DOIUrl":"10.1007/s10877-024-01205-7","url":null,"abstract":"<p><p>The high frequency variability index (HFVI)/analgesia nociception index (ANI) is purported to assess the balance between nociception and analgesia in patients under general anesthesia. This observational study investigated whether intraoperative HFVI/ANI correlates with postoperative pain in patients performed with nerve block under general anesthesia in video/robotic-assisted thoracoscopic surgery (VATS/RATS). We investigated whether maximum postoperative pain at rest and postoperative morphine consumption are associated with HFVI/ANI just before extubation, mean HFVI/ANI during anesthesia, the difference in HFVI/ANI between before and 5 min after the start of surgery, and the difference in HFVI/ANI between before and 5 min after the nerve block. Data obtained from 48 patients were analyzed. We found no significant association between HFVI/ANI just before extubation and postoperative Numerical Rating Scale (NRS) score. Receiver operating characteristic curve analysis revealed that moderate (NRS > 3) or severe (NRS > 7) postoperative pain could not be predicted by HFVI/ANI just before extubation. In addition, there were no associations between postoperative morphine consumption and HFVI/ANI at any time points. The present study demonstrated that it is difficult to predict the degree of postoperative pain in patients undergoing VATS/RATS under general anesthesia combined with peripheral nerve block, by using HFVI/ANI obtained at multiple time points during general anesthesia.</p>","PeriodicalId":15513,"journal":{"name":"Journal of Clinical Monitoring and Computing","volume":" ","pages":"35-43"},"PeriodicalIF":2.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142004349","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Nociception level index-directed superficial parasternal intercostal plane block vs erector spinae plane block in open-heart surgery: a propensity matched non-inferiority clinical trial.","authors":"Cosmin Bălan, Cristian Boroş, Bianca Moroşanu, Antonia Coman, Iulia Stănculea, Liana Văleanu, Mihai Şefan, Bogdan Pavel, Ana-Maria Ioan, Adrian Wong, Şerban-Ion Bubenek-Turconi","doi":"10.1007/s10877-024-01236-0","DOIUrl":"10.1007/s10877-024-01236-0","url":null,"abstract":"<p><p>This single-center study explored the efficacy of superficial parasternal intercostal plane block (SPIPB) versus erector spinae plane block (ESPB) in opioid-sparing within Nociception Level (NOL) index-directed anesthesia for elective open-heart surgery. After targeted propensity matching, 19 adult patients given general anesthesia with preincisional SPIPB were compared to 33 with preincisional ESPB. We hypothesized that SPIPB is non-inferior to ESPB in reducing total intraoperative fentanyl consumption, with a non-inferiority margin (δ) set at 0.1 mg. Intraoperative fentanyl dosing targeted a NOL index ≤ 25. Postoperatively, paracetamol 1 g 6-hourly and morphine for numeric rating scale (NRS) ≥ 4 were administered. This study could not demonstrate that SPIPB was inferior to ESPB for total intraoperative fentanyl consumption, as the confidence interval for the median difference of 0.1 mg (95% CI 0.05-0.15) crossed the predefined δ, with the lower bound falling below and the upper bound exceeding δ, p = 0.558. SPIPB led to higher postoperative morphine use at 24 and 48 h: 0 (0-40.6) vs. 59.5 (28.5-96.1) µg kg^-1, p < 0.001 and 22.2 (0-42.6) vs. 63.5 (28.5-96.1) µg kg^-1, p = 0.001. Four times fewer SPIPB patients remained morphine-free at 48 h, p < 0.001, and their time to first morphine dose was three times shorter compared to ESPB patients, p = 0.001. SPIPB led to higher time-weighted average NRS scores at rest, 1 (0-1) vs. 1 (1-2), p = 0.004, and with movement, 2 (1-2) vs. 3 (2-3), p = 0.002, calculated over the 48-h period post-extubation. The SPIPB group had a significantly higher average NOL index, p = 0.003, and greater NOL index variability, p = 0.027. This study could not demonstrate that SPIPB was inferior to ESPB for intraoperative fentanyl consumption. Significant differences were observed in secondary outcomes, with SPIPB leading to higher postoperative morphine use, higher pain scores, and reduced nociception control.</p>","PeriodicalId":15513,"journal":{"name":"Journal of Clinical Monitoring and Computing","volume":" ","pages":"59-72"},"PeriodicalIF":2.0,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142545768","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Accuracy of remote, video-based supraventricular tachycardia detection in patients undergoing elective electrical cardioversion: a prospective cohort.","authors":"Iris Cramer, Rik van Esch, Cindy Verstappen, Carla Kloeze, Bas van Bussel, Sander Stuijk, Jan Bergmans, Marcel van 't Veer, Svitlana Zinger, Leon Montenij, R Arthur Bouwman, Lukas Dekker","doi":"10.1007/s10877-025-01263-5","DOIUrl":"https://doi.org/10.1007/s10877-025-01263-5","url":null,"abstract":"<p><p>Unobtrusive pulse rate monitoring by continuous video recording, based on remote photoplethysmography (rPPG), might enable early detection of perioperative arrhythmias in general ward patients. However, the accuracy of an rPPG-based machine learning model to monitor the pulse rate during sinus rhythm and arrhythmias is unknown. We conducted a prospective, observational diagnostic study in a cohort with a high prevalence of arrhythmias (patients undergoing elective electrical cardioversion). Pulse rate was assessed with rPPG via a visible light camera and ECG as reference, before and after cardioversion. A cardiologist categorized ECGs into normal sinus rhythm or arrhythmias requiring further investigation. A supervised machine learning model (support vector machine with Gaussian kernel) was trained using rPPG signal features from 60-s intervals and validated via leave-one-subject-out. Pulse rate measurement performance was evaluated with Bland-Altman analysis. Of 72 patients screened, 51 patients were included in the analyses, including 444 60-s intervals with normal sinus rhythm and 1130 60-s intervals of clinically relevant arrhythmias. The model showed robust discrimination (AUC 0.95 [0.93-0.96]) and good calibration. For pulse rate measurement, the bias and limits of agreement for sinus rhythm were 1.21 [- 8.60 to 11.02], while for arrhythmia, they were - 7.45 [- 35.75 to 20.86]. The machine learning model accurately identified sinus rhythm and arrhythmias using rPPG in real-world conditions. Heart rate underestimation during arrhythmias highlights the need for optimization.</p>","PeriodicalId":15513,"journal":{"name":"Journal of Clinical Monitoring and Computing","volume":" ","pages":""},"PeriodicalIF":2.0,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143065953","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effect of postoperative peripheral nerve blocks on the analgesia nociception index under propofol anesthesia: an observational study.","authors":"Motoi Kumagai, Naoto Yamada, Masahiro Wakimoto, Shohei Ogawa, Sho Watanabe, Kotaro Sato, Kenji S Suzuki","doi":"10.1007/s10877-025-01264-4","DOIUrl":"https://doi.org/10.1007/s10877-025-01264-4","url":null,"abstract":"<p><strong>Purpose: </strong>The analgesia nociception index (ANI), also referred to as the high frequency variability index (HFVI), is reported to be an objective measure of nociception. This study investigated changes in ANI after peripheral nerve blocks (PNB) under general anesthesia. Understanding these changes could enhance assessment of PNB efficacy before emergence from general anesthesia.</p><p><strong>Methods: </strong>This study enrolled 30 patients undergoing elective upper limb surgery. After surgery, median and maximum ANI values were recorded during two periods: a 5-minute period before PNB and a 20-minute period after PNB. The numeric rating scale (NRS) for pain was assessed twice: immediately after emergence from general anesthesia (N1) and the maximum pain experienced by the following morning after PNB effects subsided (N2). The difference in ANI before and after PNB was tested using the Wilcoxon signed-rank test. Statistical significance was set at P < 0.05.</p><p><strong>Results: </strong>The ANI significantly increased after PNB in both the median (pre vs. post PNB value: 53.5 [44.0-68.0] vs. 59.0 [47.0-78.3], median [interquartile range]; P < 0.05) and maximum values (64.0 [56.3-79.5] vs. 74.5 [61.5-85.3]; P < 0.01). Secondary analysis revealed that significant ANI increases in both median (48.0 [42.3-66.5] vs. 61.0 [50.0-76.5]; P < 0.01) and maximum values (58.5 [50.3-75.3] vs. 76.0 [71.8-83.5]; P < 0.01) in the 18 cases with N2 ≥ 4 whereas no statistical differences were observed in the 12 cases with N2 < 4.</p><p><strong>Conclusion: </strong>The increased ANI value after PNB under propofol anesthesia may be a valuable indicator for assessing PNB efficacy.</p><p><strong>Trial registration number: </strong>UMIN000050334.</p><p><strong>Date of registration: </strong>February 28, 2023.</p>","PeriodicalId":15513,"journal":{"name":"Journal of Clinical Monitoring and Computing","volume":" ","pages":""},"PeriodicalIF":2.0,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143065992","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cost-effectiveness of data driven personalised antibiotic dosing in critically ill patients with sepsis or septic shock.","authors":"Hana M Broulikova, Jacqueline Wallage, Luca Roggeveen, Lucas Fleuren, Tingjie Guo, Paul W G Elbers, Judith E Bosmans","doi":"10.1007/s10877-024-01257-9","DOIUrl":"https://doi.org/10.1007/s10877-024-01257-9","url":null,"abstract":"<p><strong>Purpose: </strong>This study provides an economic evaluation of bedside, data-driven, and model-informed precision dosing of antibiotics in comparison with usual care among critically ill patients with sepsis or septic shock.</p><p><strong>Methods: </strong>This economic evaluation was conducted alongside an AutoKinetics randomized controlled trial. Effect measures included quality-adjusted life years (QALYs), mortality and pharmacokinetic target attainment. Costs were measured from a societal perspective. Missing data was multiply imputed, and bootstrapping was used to estimate statistical uncertainty. Differences in effects and costs were estimated using bivariate regression and used to calculate incremental cost-effectiveness ratios.</p><p><strong>Results: </strong>Patients in the intervention group had higher costs (€42,684 vs. 39,475), lower mortality (42% vs. 49%), more QALYs (0.184 vs. 0.153), and higher pharmacokinetic target attainment (69% vs. 48%). Only the difference for target attainment was found statistically significant. An additional €18,129, €55,576, and €123,493 needs to be invested to attain the targeted plasma levels for one more patient, to save one life and gain one QALY, respectively. The probability of cost-effectiveness for all effect outcomes is below 60% for most acceptable willingness-to-pay thresholds.</p><p><strong>Conclusions: </strong>Data-driven personalised antibiotic dosing in critically ill patients as implemented in the AutoKinetics trial cannot be recommended for implementation as a cost-effective intervention.</p><p><strong>Trial registration: </strong>The trial was prospectively registered at Netherlands Trial Register (NTR), NL6501/NTR6689 on 25 August 2017 and at the European Clinical Trials Database (EudraCT), 2017-002478-37 on 6 November 2017.</p>","PeriodicalId":15513,"journal":{"name":"Journal of Clinical Monitoring and Computing","volume":" ","pages":""},"PeriodicalIF":2.0,"publicationDate":"2025-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143032854","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assessing fluid responsiveness by using functional hemodynamic tests in critically ill patients: a narrative review and a profile-based clinical guide.","authors":"Antonio Messina, Domenico Luca Grieco, Valeria Alicino, Guia Margherita Matronola, Andrea Brunati, Massimo Antonelli, Michelle S Chew, Maurizio Cecconi","doi":"10.1007/s10877-024-01255-x","DOIUrl":"https://doi.org/10.1007/s10877-024-01255-x","url":null,"abstract":"<p><p>Fluids are given with the purpose of increasing cardiac output (CO), but approximately only 50% of critically ill patients are fluid responders. Since the effect of a fluid bolus is time-sensitive, it diminuish within few hours, following the initial fluid resuscitation. Several functional hemodynamic tests (FHTs), consisting of maneuvers affecting heart-lung interactions, have been conceived to discriminate fluid responders from non-responders. Three main variables affect the reliability of FHTs in predicting fluid responsiveness: (1) tidal volume; (2) spontaneous breathing activity; (3) cardiac arrythmias. Most FTHs have been validated in sedated or even paralyzed ICU patients, since, historically, controlled mechanical ventilation with high tidal volumes was the preferred mode of ventilatory support. The transition to contemporary methods of invasive mechanical ventilation with spontaneous breathing activity impacts heart-lung interactions by modifying intrathoracic pressure, tidal volumes and transvascular pressure in lung capillaries. These alterations and the heterogeneity in respiratory mechanics (that is present both in healthy and injured lungs) subsequently influence venous return and cardiac output. Cardiac arrythmias are frequently present in critically ill patients, especially atrial fibrillation, and intuitively impact on FHTs. This is due to the random CO fluctuations. Finally, the presence of continuous CO monitoring in ICU patients is not standard and the assessment of fluid responsiveness with surrogate methods is clinically useful, but also challenging. In this review we provide an algorithm for the use of FHTs in different subgroups of ICU patients, according to ventilatory setting, cardiac rhythm and the availability of continuous hemodynamic monitoring.</p>","PeriodicalId":15513,"journal":{"name":"Journal of Clinical Monitoring and Computing","volume":" ","pages":""},"PeriodicalIF":2.0,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143005795","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The use of the surgical pleth index to guide anaesthesia in gastroenterological surgery: a randomised controlled study.","authors":"Tommi Bergman, Maija-Liisa Kalliomäki, Mika Särkelä, Jarkko Harju","doi":"10.1007/s10877-025-01262-6","DOIUrl":"https://doi.org/10.1007/s10877-025-01262-6","url":null,"abstract":"<p><p>The measurement of nociception and the optimisation of intraoperative antinociceptive medication could potentially improve the conduct of anaesthesia, especially in the older population. The Surgical Pleth Index (SPI) is one of the monitoring methods presently used for the detection of nociceptive stimulus. Eighty patients aged 50 years and older who were scheduled to undergo major abdominal surgery were randomised and divided into a study group and a control group. In the study group, the SPI was used to guide the administration of remifentanil during surgery. In the control group, the SPI value was concealed, and remifentanil administration was based on the clinical evaluation of the attending anaesthesiologist. The primary endpoint of this study was intraoperative remifentanil consumption. In addition, we compared the durations of intraoperative hypotension and hypertension. No difference in intraoperative remifentanil consumption (4.5 µg kg^- 1h^- 1 vs. 5.6 µg kg^- 1h^- 1, p = 0.14) was found. Furthermore, there was no difference in the proportion of hypotensive time (mean arterial pressure, MAP < 65) (3.7% vs. 1.6%, p = 0.40). However, in the subgroup of patients who underwent operation with invasive blood pressure monitoring, there was less severe hypotension (MAP < 55) (0.3% vs. 0.0%, p = 0.02) and intermediate hypotension (MAP < 65) (10.2% vs. 2.6%, p = 0.07) in the treatment group, even though remifentanil consumption was higher (3.5 µg kg^- 1h^- 1 vs. 5.1 µg kg^- 1h^- 1p = 0.03). The use of SPI guidance for the administration of remifentanil during surgery did not help to reduce the remifentanil consumption. However, the results from invasively monitored study group suggest more timely administered opioid when SPI was used.</p>","PeriodicalId":15513,"journal":{"name":"Journal of Clinical Monitoring and Computing","volume":" ","pages":""},"PeriodicalIF":2.0,"publicationDate":"2025-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143006166","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Decision support guided fluid challenges and stroke volume response during high-risk surgery: a post hoc analysis of a randomized controlled trial.","authors":"Sean Coeckelenbergh, Joseph Rinehart, Olivier Desebbe, Nicolas Rogoz, Amira Dagachi Mastouri, Bryan Maghen, Maxime Cannesson, Jean-Louis Vincent, Jacques Duranteau, Alexandre Joosten","doi":"10.1007/s10877-025-01261-7","DOIUrl":"https://doi.org/10.1007/s10877-025-01261-7","url":null,"abstract":"<p><p>Intravenous fluid is administered during high-risk surgery to optimize stroke volume (SV). To assess ongoing need for fluids, the hemodynamic response to a fluid bolus is evaluated using a fluid challenge technique. The Acumen Assisted Fluid Management (AFM) system is a decision support tool designed to ease the application of fluid challenges and thus improve fluid administration during high-risk surgery. In this post hoc analysis of data from a randomized controlled trial, we compared the rates of fluid responsiveness (defined as an increase in SV of ≥ 10%) after AFM-guided or clinician-initiated (control) fluid challenges. Patients undergoing high-risk abdominal surgery were randomly allocated to AFM-guided or clinician-initiated groups for fluid challenges titration, which consisted of 250-mL boluses of crystalloid or albumin given over 5 min. The fluid responsiveness rates and the mean SV increase in the two groups were compared. The original study included 86 patients (44 in the AFM group and 42 in the clinician-initiated group) and this sub-study analysed 85 patients with a total of 448 fluid challenges. The median rate of fluid responsiveness was greater in the AFM than in the control group (50 [44-71] % vs 33 [20-40] %, p<0.001). The mean increase in SV after fluid challenge was also higher in the AFM than in the control group (12 [9-16] % vs 6 [3-10] %, p<0.001). AFM-initiated fluid challenges were more often associated with the desired increase in SV than were clinician-initiated fluid challenges, and absolute SV increases were greater.</p>","PeriodicalId":15513,"journal":{"name":"Journal of Clinical Monitoring and Computing","volume":" ","pages":""},"PeriodicalIF":2.0,"publicationDate":"2025-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143006158","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated and reference methods for the calculation of left ventricular outflow tract velocity time integral or ejection fraction by non-cardiologists: a systematic review on the agreement of the two methods.","authors":"Filipe André Gonzalez, Mateusz Zawadka, Rita Varudo, Simone Messina, Alessandro Caruso, Cristina Santonocito, Michel Slama, Filippo Sanfilippo","doi":"10.1007/s10877-024-01259-7","DOIUrl":"https://doi.org/10.1007/s10877-024-01259-7","url":null,"abstract":"<p><p>Echocardiography is crucial for evaluating patients at risk of clinical deterioration. Left ventricular ejection fraction (LVEF) and velocity time integral (VTI) aid in diagnosing shock, but bedside calculations can be time-consuming and prone to variability. Artificial intelligence technology shows promise in providing assistance to clinicians performing point-of-care echocardiography. We conducted a systematic review, utilizing a comprehensive literature search on PubMed, to evaluate the interchangeability of LVEF and/or VTI measurements obtained through automated mode as compared to the echocardiographic reference methods in non-cardiology settings, e.g., Simpson´s method (LVEF) or manual trace (VTI). Eight studies were included, four studying automated-LVEF, three automated-VTI, and one both. When reported, the feasibility of automated measurements ranged from 78.4 to 93.3%. The automated-LVEF had a mean bias ranging from 0 to 2.9% for experienced operators and from 0% to -10.2% for non-experienced ones, but in both cases, with wide limits of agreement (LoA). For the automated-VTI, the mean bias ranged between - 1.7 cm and - 1.9 cm. The correlation between automated and reference methods for automated-LVEF ranged between 0.63 and 0.86 for experienced and between 0.56 and 0.81 for non-experienced operators. Only one study reported a correlation between automated-VTI and manual VTI (0.86 for experienced and 0.79 for non-experienced operators). We found limited studies reporting the interchangeability of automated LVEF or VTI measurements versus a reference approach. The accuracy and precision of these automated methods should be considered within the clinical context and decision-making. Such variability could be acceptable, especially in the hands of trained operators. PROSPERO number CRD42024564868.</p>","PeriodicalId":15513,"journal":{"name":"Journal of Clinical Monitoring and Computing","volume":" ","pages":""},"PeriodicalIF":2.0,"publicationDate":"2024-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142894840","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Noninvasive estimation of PaCO₂ from volumetric capnography in animals with injured lungs: an Artificial Intelligence approach.","authors":"Gerardo Tusman, Adriana G Scandurra, Stephan H Böhm, Noelia I Echeverría, Gustavo Meschino, P Kremeier, Fernando Suarez Sipmann","doi":"10.1007/s10877-024-01253-z","DOIUrl":"https://doi.org/10.1007/s10877-024-01253-z","url":null,"abstract":"<p><p>To investigate the feasibility of non-invasively estimating the arterial partial pressure of carbon dioxide (PaCO₂) using a computational Adaptive Neuro-Fuzzy Inference System (ANFIS) model fed by noninvasive volumetric capnography (VCap) parameters. In 14 lung-lavaged pigs, we continuously measured PaCO₂ with an optical intravascular catheter and VCap on a breath-by-breath basis. Animals were mechanically ventilated with fixed settings and subjected to 0 to 22 cmH₂O of positive end-expiratory pressure steps. The resultant 8599 pairs of data points - one PaCO₂ value matched with twelve Vcap and ventilatory parameters derived in one breath - fed the ANFIS model. The data was separated into 7370 data points for training the model (85%) and 1229 for testing (15%). The ANFIS analysis was repeated 10 independent times, randomly mixing the total data points. Bland-Altman plot (accuracy and precision), root mean square error (quality of prediction) and four-quadrant and polar plots concordance indexes (trending ability) between reference and estimated PaCO₂ were analyzed. The Bland-Altman plot performed in 10 independent tested ANFIS models showed a mean bias between reference and estimated PaCO₂ of 0.03 ± 0.03 mmHg, with limits of agreement of 2.25 ± 0.42 mmHg, and a root mean square error of 1.15 ± 0.06 mmHg. A good trending ability was confirmed by four quadrant and polar plots concordance indexes of 95.5% and 94.3%, respectively. In an animal lung injury model, the Adaptive Neuro-Fuzzy Inference System model fed by noninvasive volumetric capnography parameters can estimate PaCO₂ with high accuracy, acceptable precision, and good trending ability.</p>","PeriodicalId":15513,"journal":{"name":"Journal of Clinical Monitoring and Computing","volume":" ","pages":""},"PeriodicalIF":2.0,"publicationDate":"2024-12-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142894843","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}