Journal of Clinical Monitoring and Computing最新文献

{"title":"Predicting short-term outcomes in brain-injured patients: a comprehensive approach with transcranial Doppler and intracranial compliance assessment.","authors":"Sérgio Brasil, Danilo Cardim, Juliana Caldas, Chiara Robba, Fabio Silvio Taccone, Marcelo de-Lima-Oliveira, Márcia Harumy Yoshikawa, Luiz Marcelo Sá Malbouisson, Wellingson S Paiva","doi":"10.1007/s10877-024-01181-y","DOIUrl":"10.1007/s10877-024-01181-y","url":null,"abstract":"<p><p>Neurocritical patients frequently exhibit abnormalities in cerebral hemodynamics (CH) and/or intracranial compliance (ICC), all of which significantly impact their clinical outcomes. Transcranial Doppler (TCD) and the cranial micro-deformation sensor (B4C) are valuable techniques for assessing CH and ICC, respectively. However, there is a scarcity of data regarding the predictive value of these techniques in determining patient outcomes. We prospectively included neurocritical patients undergoing intracranial pressure (ICP) monitoring within the first 5 days of hospital admission for TCD and B4C assessments. Comprehensive clinical data were collected alongside parameters obtained from TCD (including the estimated ICP [eICP] and estimated cerebral perfusion pressure [eCPP]) and B4C (measured as the P2/P1 ratio). These parameters were evaluated individually as well as in combination. The short-term outcomes (STO) of interest were the therapy intensity levels (TIL) for ICP management recommended by the Seattle International Brain Injury Consensus Conference, as TIL 0 (STO 1), TIL 1-3 (STO 2) and death (STO 3), at the seventh day after last data collection. The dataset was randomly separated in test and training samples, area under the curve (AUC) was used to represent the noninvasive techniques ability on the STO prediction and association with ICP. A total of 98 patients were included, with 67% having experienced severe traumatic brain injury and 15% subarachnoid hemorrhage, whilst the remaining patients had ischemic or hemorrhagic stroke. ICP, P2/P1, and eCPP demonstrated the highest ability to predict early mortality (p = 0.02, p = 0.02, and p = 0.006, respectively). P2/P1 was the only parameter significant for the prediction of STO 1 (p = 0.03). Combining B4C and TCD parameters, the highest AUC was 0.85 to predict death (STO 3), using P2/P1 + eCPP, whereas AUC was 0.72 to identify ICP > 20 mmHg using P2/P1 + eICP. The combined noninvasive neuromonitoring approach using eCPP and P2/P1 ratio demonstrated improved performance in predicting outcomes during the early phase after acute brain injury. The correlation with intracranial hypertension was moderate, by means of eICP and P2/P1 ratio. These results support the need for interpretation of this information in the ICU and warrant further investigations for the definition of therapy strategies using ancillary tests.</p>","PeriodicalId":15513,"journal":{"name":"Journal of Clinical Monitoring and Computing","volume":" ","pages":"1237-1247"},"PeriodicalIF":2.0,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11604736/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141283870","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Heart rate variability as a predictor of intraoperative autonomic nervous system homeostasis.","authors":"Ole C Keim, Lennart Bolwin, Robert E Feldmann, Manfred Thiel, Justus Benrath","doi":"10.1007/s10877-024-01190-x","DOIUrl":"10.1007/s10877-024-01190-x","url":null,"abstract":"<p><p>The aim of the proof-of-concept study is to investigate the level of concordance between the heart rate variability (HRV), the EEG-based Narcotrend Index as a surrogate marker for the depth of hypnosis, and the minimal alveolar concentration (MAC) of the inhalation anesthetic sevoflurane across the entire course of a surgical procedure. This non-blinded cross-sectional study recorded intraoperative HRV, Narcotrend Index, and MAC in 31 male patients during radical prostatectomy using the Da-Vinci robotic-assisted surgical system at Mannheim University Medical Center. The degree of concordance was calculated using repeated measures correlation with the R package (rmcorr) and presented using the rmcorr coefficient (rrm). The Narcotrend Index correlates significantly across all measures with the time-dependent parameter of HRV, the standard deviation of the means of RR intervals (SDNN) (rrm = 0.2; p < 0.001), the frequency-dependent parameters low frequency (LF) (rrm = 0.09; p = 0.04) and the low frequency/high frequency ratio (LF/HF ratio) (rrm = 0.11; p = 0.002). MAC correlated significantly negatively with the time-dependent parameter of heart rate variability, SDNN (rrm = -0.28; p < 0.001), the frequency-dependent parameter LF (rrm = -0.06; p < 0.001) and the LF/HF ratio (rrm = -0.18; p < 0.001) and the Narcotrend Index (rrm = -0.49; p < 0.001) across all measures. HRV mirrors the trend of the Narcotrend Index used to monitor depth of hypnosis and the inhibitory influence of the anesthetic sevoflurane on the autonomic nervous system. Therefore, HRV can provide essential information about the homeostasis of the autonomic nervous system during general anesthesia. DRKS00024696, March 9th, 2021.</p>","PeriodicalId":15513,"journal":{"name":"Journal of Clinical Monitoring and Computing","volume":" ","pages":"1305-1313"},"PeriodicalIF":2.0,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11604806/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141603726","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Characterization of intracranial compliance in healthy subjects using a noninvasive method - results from a multicenter prospective observational study.","authors":"Gabriela Nagai Ocamoto, Lucas Normando da Silva, Camila da Silva Rocha Tomaz, Matheus Toshio Hisatugu, Gustavo Frigieri, Danilo Cardim, Roberta Lins Gonçalves, Thiago Luiz Russo, Robson Luis Oliveira de Amorim","doi":"10.1007/s10877-024-01191-w","DOIUrl":"10.1007/s10877-024-01191-w","url":null,"abstract":"<p><strong>Purpose: </strong>An FDA-approved non-invasive intracranial pressure (ICP) monitoring system enables the assessment of ICP waveforms by revealing and analyzing their morphological variations and parameters associated with intracranial compliance, such as the P2/P1 ratio and time-to-peak (TTP). The aim of this study is to characterize intracranial compliance in healthy volunteers across different age groups.</p><p><strong>Methods: </strong>Healthy participants, both sexes, aged from 9 to 74 years old were monitored for 5 min in the supine position at 0º. Age was stratified into 4 groups: children (≤ 7 years); young adults (18 ≤ age ≤ 44 years); middle-aged adults (45 ≤ age ≤ 64 years); older adults (≥ 65 years). The data obtained was the non-invasive ICP waveform, P2/P1 ratio and TTP.</p><p><strong>Results: </strong>From December 2020 to February 2023, 188 volunteers were assessed, of whom 104 were male, with a median (interquartile range) age of 41 (29-51), and a median (interquartile range) body mass index of 25.09 (22.57-28.04). Men exhibited lower values compared to women for both the P2/P1 ratio and TTP (p < 0.001). There was a relative rise in both P2/P1 and TTP as age increased (p < 0.001).</p><p><strong>Conclusions: </strong>The study revealed that the P2/P1 ratio and TTP are influenced by age and sex in healthy individuals, with men displaying lower values than women, and both ratios increasing with age. These findings suggest potential avenues for further research with larger and more diverse samples to establish reference values for comparison in various health conditions.</p><p><strong>Trial registration: </strong>Brazilian Registry of Clinical Trials (RBR-9nv2h42), retrospectively registered 05/24/2022. UTN: U1111-1266-8006.</p>","PeriodicalId":15513,"journal":{"name":"Journal of Clinical Monitoring and Computing","volume":" ","pages":"1249-1261"},"PeriodicalIF":2.0,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11604689/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141731117","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Regional cerebral oxygen saturation in the healthy population of western Sichuan: a multicenter cross-sectional study.","authors":"Gangfeng Gu, Junyao Jiang, Bo Zheng, Yan Li, Yuding Luo, Yunhai Pu, Jian Wang","doi":"10.1007/s10877-024-01244-0","DOIUrl":"https://doi.org/10.1007/s10877-024-01244-0","url":null,"abstract":"<p><p>Regional cerebral oxygen saturation (rSO₂) may vary in healthy individuals with different characteristics. Therefore, this study aimed to explore rSO₂ in a healthy population of western Sichuan. This cross-sectional study enrolled healthy volunteers from the Health Management Center and Inpatient Department of Ya'an People's Hospital, Ya'an Vocational and Technical College, Ya'an Geriatric University, and Liziping Yi Township in Shimian County, Ya'an City, Sichuan Province. Brain rSO₂ was measured by near-infrared spectroscopy (NIRS) between January 2020 and December 2022. A total of 661 volunteers were enrolled, with a mean age of 28.3 ± 23.1 years old and 276 males. There was significantly higher rSO₂ of the left brain in females (63.46 ± 3.01 vs. 63.17 ± 2.90, P = 0.015), males (63.91 ± 3.54 vs. 63.42 ± 3.32, P = 0.002), Han (65.10 ± 3.67 vs. 64.38 ± 3.43, P < 0.001), and volunteers aged 14-59 years (P < 0.05) compared with the right brain. Volunteers with Han ethnicity had significantly higher rSO₂ than those with Yi ethnicity (64.65 ± 3.29 vs. 62.68 ± 3.66, P < 0.001). Volunteers with past illness had significantly lower rSO₂ than those without past illness (62.41 ± 3.06 vs. 62.68 ± 3.66, P = 0.021). Pearson correlation analysis showed a significantly negative correlation of rSO₂ with age, ethics, past illness, and body mass index (BMI) but a significantly positive correlation with head circumference and height (all P < 0.05). The rSO₂ values in the left brain are significantly higher than in the right brain. Sex, ethnicity, age, BMI, and past illness are closely related to rSO₂ values in the healthy population.</p>","PeriodicalId":15513,"journal":{"name":"Journal of Clinical Monitoring and Computing","volume":" ","pages":""},"PeriodicalIF":2.0,"publicationDate":"2024-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142710186","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":"Association of early perioperative stroke after cardiothoracic surgery with intraoperative regional cerebral oxygenation using near-infrared spectroscopy: an observational cohort study comparing affected versus non-affected hemispheres.","authors":"Ramon Pierik, Thomas W L Scheeren, Michiel E Erasmus, Walter M van den Bergh","doi":"10.1007/s10877-024-01241-3","DOIUrl":"https://doi.org/10.1007/s10877-024-01241-3","url":null,"abstract":"<p><strong>Purpose: </strong>Patients undergoing cardiothoracic surgery are at risk of developing perioperative stroke, but residual effects of anesthesia may hamper timely detection. This study aims to determine if there is an association between intraoperative regional cerebral oxygenation (ScO₂) monitoring using near-infrared spectroscopy (NIRS) and the occurrence of early perioperative stroke within three days after cardiothoracic surgery.</p><p><strong>Methods: </strong>We performed a single-center retrospective observational cohort study including all consecutive cardiothoracic surgery patients with routinely perioperative ScO₂ monitoring admitted postoperatively to the Intensive Care Unit (ICU) between 2008 and 2017. Patients with a confirmed stroke in the anterior cerebral circulation on brain imaging were included in the analysis. Intraoperative area under the curve (AUC), duration, and total ScO₂ excursions below predefined thresholds (< 50% ScO₂ or > 20% reduction below baseline) were calculated for each hemisphere. Stroke-affected and non-affected hemispheres were compared using logistic regression analyses to investigate a potential association between ScO₂ values and stroke.</p><p><strong>Results: </strong>Of the 2454 cardiothoracic surgery patients with perioperative ScO₂ monitoring, 39 had a anterior stroke on brain imaging. ScO₂ readings of 44 affected hemispheres were compared to 34 non-affected hemispheres. Only the duration of ScO₂ < 50% or a > 20% drop from baseline were significantly associated with global ischemia (OR 1.30 (0.95%CI; 1.09-2.30)) when comparing affected (72 [5 to 33] min.) versus non-affected (28 [4 to 44] min.) hemispheres.</p><p><strong>Conclusion: </strong>The duration of ScO₂ values < 50% or a drop > 20% from baseline were associated with the occurrence of early perioperative global cerebral ischemia within three days after cardiothoracic surgery.</p>","PeriodicalId":15513,"journal":{"name":"Journal of Clinical Monitoring and Computing","volume":" ","pages":""},"PeriodicalIF":2.0,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142675983","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":"Characterization of the temporal profile of the antinociceptive effects of an intravenous bolus of ketamine using the analgesia nociception index in no-anesthetized adult patients.","authors":"Víctor Navarrete, Mauricio Ibacache, Víctor Contreras, Ignacio Cortínez","doi":"10.1007/s10877-024-01240-4","DOIUrl":"https://doi.org/10.1007/s10877-024-01240-4","url":null,"abstract":"<p><p>An effect-site target-controlled infusion (TCI) would allow a more precise titration of intravenous analgesics effect. The analgesia nociception index (ANI) continuously monitors the analgesia/nociception balance during general anesthesia. This study aims to derive a PKPD model of ketamine antinociceptive effect using the Domino PK parameter set and the ANI response data in awake patients without other drugs affecting the ANI response. Twenty awake adult patients were prospectively studied before general anesthesia. Patients received a single intravenous bolus of ketamine 0.1 mg·kg^- 1, and the subsequent ANI values were recorded. An effect compartment model incorporating the Domino PK parameter set was used to characterize the time lag between ketamine plasma concentrations and the ANI response. The model was parameterized with a single parameter Ke0. An Emax pharmacodynamic model was used to fit the ANI response data. Model parameters were estimated with NONMEM^® 7.5. The minimum objective function value guided the model construction. After the ketamine administration, basal ANI values increased from 38.5 ± 4.95 to a maximum of 53.5 ± 4.95 with an observed time-to-peak effect of 1.83 ± 0.74 min. Modeling analysis revealed hysteresis between predicted plasma concentrations from the Domino model and observed ANI data. Hysteresis was characterized, incorporating an estimated Keo of 0.238 (CI95% 0.20-0.28) min-1 to the described PK parameters set. The developed PKPD model, using Domino's PK parameters and the ANI response data, adequately characterized the temporal profile of ketamine's antinociceptive effect. The current estimated model parameters can be used to perform an effect-site TCI of ketamine for analgesic purposes.</p>","PeriodicalId":15513,"journal":{"name":"Journal of Clinical Monitoring and Computing","volume":" ","pages":""},"PeriodicalIF":2.0,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142638984","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":"New sensors for the early detection of clinical deterioration on general wards and beyond - a clinician's perspective.","authors":"Frederic Michard, Bernd Saugel","doi":"10.1007/s10877-024-01235-1","DOIUrl":"https://doi.org/10.1007/s10877-024-01235-1","url":null,"abstract":"<p><p>The early detection of clinical deterioration could be the next significant step in enhancing patient safety in general hospital wards. Most patients do not deteriorate suddenly; instead, their vital signs are often abnormal or trending towards an abnormal range hours before severe adverse events requiring rescue intervention and/or ICU transfer. To date, at least 10 large clinical studies have demonstrated a significant reduction in severe adverse events when heart rate, blood pressure, oxygen saturation and/or respiratory rate are continuously monitored on medical and surgical wards. Continuous, silent, and automatic monitoring of vital signs also presents the opportunity to eliminate unnecessary spot-checks for stable patients. This could lead to a reduction in nurse workload, while significantly improving patient comfort, sleep quality, and overall satisfaction. Wireless and wearable sensors are particularly valuable, as they make continuous monitoring feasible even for ambulatory patients, raising questions about the future relevance of \"stay-in-bed\" solutions like capnography, bed sensors, and video-monitoring systems. While the number of wearable sensors and mobile monitoring solutions is rapidly growing, independent validation studies on their sensitivity and specificity in detecting abnormal vital signs in actual patients, rather than healthy volunteers, remain limited. Additionally, further research is needed to evaluate the cost-effectiveness of using wireless wearables for vital sign monitoring both within hospital wards and at home.</p>","PeriodicalId":15513,"journal":{"name":"Journal of Clinical Monitoring and Computing","volume":" ","pages":""},"PeriodicalIF":2.0,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142638987","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":"Avatar-based versus conventional patient monitoring with distant vision: a computer-based simulation study.","authors":"Petar Milovanovic, Julia Braun, Cynthia Alexandra Hunn, Justyna Lunkiewicz, David Werner Tscholl, Greta Gasciauskaite","doi":"10.1007/s10877-024-01239-x","DOIUrl":"https://doi.org/10.1007/s10877-024-01239-x","url":null,"abstract":"<p><p>Patient monitoring in the perioperative setting can be challenging, especially when monitoring multiple patients simultaneously or managing dynamic situations that require movement around the operating room. We aimed to evaluate whether avatar-based patient monitoring, which presents vital signs in the form of changing colors, shapes and motion, improves remote vital sign recognition compared to conventional monitoring. We conducted a prospective, single-center, computer-based simulation study to evaluate how anesthesia providers recognize vital signs when using the Philips Visual Patient Avatar at different viewing distances (8 and 16 m) compared to conventional monitoring. The primary outcome was the total number of correctly identified vital signs which were compared for the two distances and the two devices using mixed Poisson regression. We analyzed data from 28 anesthesia providers who participated in 112 simulations. The correct recognition rate using the Visual Patient Avatar compared to conventional monitoring at 8 m was increased by 74% (rate ratio 1.74, 95% CI, 1.42 to 2.14, p < 0.001) and by 51% at 16-meter viewing distance (rate ratio 1.51, 95% CI, 1.23 to 1.87, p < 0.001). We observed scenario-specific superior performance for six vital signs at 8 m. The results provide empirical evidence that avatar-based monitoring can significantly improve the perception of vital signs when using distant vision.</p>","PeriodicalId":15513,"journal":{"name":"Journal of Clinical Monitoring and Computing","volume":" ","pages":""},"PeriodicalIF":2.0,"publicationDate":"2024-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142638981","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":"Evaluation of decision support to wean patients from mechanical ventilation in intensive care: a prospective study reporting clinical and physiological outcomes.","authors":"Marcela P Vizcaychipi, Dan S Karbing, Laura Martins, Amandeep Gupta, Jeronimo Moreno-Cuesta, Manu Naik, Ingeborg Welters, Suveer Singh, Georgina Randell, Leyla Osman, Stephen E Rees","doi":"10.1007/s10877-024-01231-5","DOIUrl":"https://doi.org/10.1007/s10877-024-01231-5","url":null,"abstract":"<p><p>This study investigated the clinical and physiological response to use of the BEACON Caresystem, a bedside open-loop decision support system providing advice to guide clinicians when weaning patients from invasive mechanical ventilation. Multicenter prospective study conducted in five adult intensive care units in the UK. Following screening and assent, intubated patients mechanically ventilated for > 24 h were randomized to intervention or usual care. Intervention consisted of application of the BEACON Caresystem's advice on tidal volume/inspiratory pressure, inspired oxygen, respiratory rate and PEEP. Usual care was defined as local clinical practice. The primary outcome was duration of mechanical ventilation. Secondary outcomes quantified prolonged intubation and survival; adverse events; ventilator settings and physiological state; time spent in ventilator modes; links to other therapy; the frequency of advice utilization and time spent outside normal physiological limits. The study was terminated early with a total of 112 patients included. Fifty-four were randomised to the intervention arm and fifty-eight to usual care. The study was underpowered and no significant differences were seen in duration of mechanical ventilation (p = 0.773), prolonged intubation or survival. Intervention arm patients had lower rates of adverse events (p = 0.016), including fewer hypoxaemic events (p = 0.008) and lower values of PEEP (p = 0.030) and tidal volume (p = 0.042). Values of peak inspiratory pressure and pressure support were reduced but at the boarder of statistical significance (p = 0.104, p = 0.093, respectively). No differences were seen for time in ventilator mode or other therapy. Advice presented by the decision support system was applied at the beside an average of 88% of occasions, with a significantly increased number of changes only in inspired oxygen fraction. No significant differences were seen in time spent outside physiological limits. This study investigated the use of the BEACON Caresystem, an open loop clinical decision support system providing advice on ventilator settings. It was terminated early, with no significant difference shown in duration of mechanical ventilation, the primary outcome. Application of advice indicated potential for fewer adverse events and improved physiological status. (Trial registration ClinicalTrials.gov under NCT03249623. Registered 22nd June 2017).</p>","PeriodicalId":15513,"journal":{"name":"Journal of Clinical Monitoring and Computing","volume":" ","pages":""},"PeriodicalIF":2.0,"publicationDate":"2024-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142621241","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":"Comparison of time-series models for predicting physiological metrics under sedation.","authors":"Zheyan Tu, Sean D Jeffries, Joshua Morse, Thomas M Hemmerling","doi":"10.1007/s10877-024-01237-z","DOIUrl":"https://doi.org/10.1007/s10877-024-01237-z","url":null,"abstract":"<p><p>This study presents a comprehensive comparison of multiple time-series models applied to physiological metric predictions. It aims to explore the effectiveness of both statistical prediction models and pharmacokinetic-pharmacodynamic prediction model and modern deep learning approaches. Specifically, the study focuses on predicting the bispectral index (BIS), a vital metric in anesthesia used to assess the depth of sedation during surgery, using datasets collected from real-life surgeries. The goal is to evaluate and compare model performance considering both univariate and multivariate schemes. Accurate BIS prediction is essential for avoiding under- or over-sedation, which can lead to adverse outcomes. The study investigates a range of models: The traditional mathematical models include the pharmacokinetic-pharmacodynamic model and statistical models such as autoregressive integrated moving average (ARIMA) and vector autoregression (VAR). The deep learning models encompass recurrent neural networks (RNNs), specifically Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU), as well as Temporal Convolutional Networks (TCNs) and Transformer models. The analysis focuses on evaluating model performance in predicting the BIS using two distinct datasets of physiological metrics collected from actual surgical procedures. It explores both univariate and multivariate prediction schemes and investigates how different combinations of features and input sequence lengths impact model accuracy. The experimental findings reveal significant performance differences among the models: In univariate prediction scenarios for predicting BIS, the LSTM model demonstrates a 2.88% improvement over the second-best performing model. For multivariate predictions, the LSTM model outperforms others by 6.67% compared to the next best model. Furthermore, the addition of Electromyography (EMG) and Mean Arterial Pressure (MAP) brings significant accuracy improvement when predicting BIS. The study emphasizes the importance of selecting and building appropriate time-series models to achieve accurate predictions in biomedical applications. This research provides insights to guide future efforts in improving vital sign prediction methodologies for clinical and research purposes. Clinically, with improvements in the prediction of physiological parameters, clinicians can be informed of interventions if an anomaly is detected or predicted.</p>","PeriodicalId":15513,"journal":{"name":"Journal of Clinical Monitoring and Computing","volume":" ","pages":""},"PeriodicalIF":2.0,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142545767","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}