Journal of clinical monitoring and computing
-
J Clin Monit Comput · Oct 2023
LetterFrom Big Data's 5Vs to clinical practice's 5Ws: enhancing data-driven decision making in healthcare.
The use of AI-based algorithms is rapidly growing in healthcare, but there is still an ongoing debate about how to manage and ensure accountability for their clinical use. While most of the studies focus on demonstrating a good algorithm performance it is important to acknowledge that several additional steps are needed for reaching an effective implementation of AI-based models in daily clinical practice, with implementation being one of the main key factors. We propose a model characterized by five questions that can guide in this process. Additionally, we believe that a hybrid intelligence, human and artificial respectively, is the new clinical paradigm that offer the most benefits for developing clinical decision support systems for bedside use.
-
J Clin Monit Comput · Oct 2023
Reliability and reproducibility of the DICART device to assess capillary refill time: a bench and in-silico study.
Capillary refill time (CRT) is an important indicator of peripheral perfusion with a strong prognostic value, but it is sensitive to environmental factors and numerous measurement methods are reported in the litterature. DiCARTECH has developed a device that assesses CRT. We sought to investigate the robustness of the device and the reproducibility of the algorithm in a bench and in-silico study. ⋯ For the color-jitter modified video the coefficient of variation was 62% (95%CI: 55-70). We confirmed the ability of the DiCART™ II device to perform multiple measurements without mechanical or electronic dysfunction. The precision and reproducibility of the algorithm are compatible with the assessment of clinical small changes in CRT.
-
J Clin Monit Comput · Oct 2023
Effects of tidal volume challenge on the reliability of plethysmography variability index in hepatobiliary and pancreatic surgeries: a prospective interventional study.
The plethysmography variability index (PVI) is a non-invasive, real-time, and automated parameter for evaluating fluid responsiveness, but it does not reliably predict fluid responsiveness during low tidal volume (VT) ventilation. We hypothesized that in a 'tidal volume challenge' with a transient increase in tidal volume from 6 to 8 ml Kg- 1, the changes in PVI could predict fluid responsiveness reliably. ⋯ In hepatobiliary and pancreatic surgeries, tidal volume challenge improves the reliability of PVI for predicting fluid responsiveness and changes in PVI values obtained after tidal volume challenge are comparable to the changes in SVI.
-
J Clin Monit Comput · Oct 2023
Modeling the impacts of assumptions and nonpulmonary factors on the performance and reliability of indices of oxygenation.
Assessment of oxygenation is fundamental to the care of patients. Numerous indices of oxygenation have been developed that entail variable degrees of invasiveness, complexity and physiologic underpinning. The clinical reliability of these indices has been questioned. ⋯ These effects manifested as calculated indices either over or under-estimating actual shunt by FShunt, or wide unpredictable variability (scatter) when correlating A-a [Formula: see text] gradient and Pa:Fi ratio to actual shunt. Cardiac output and oxygen extraction have noticeable impacts on all calculated indices. The results support the clinical observations that the performance of indices of oxygenation can vary with fraction of inspired oxygen and various nonpulmonary physiological factors that underly heterogeneity present in the clinical population.
-
J Clin Monit Comput · Oct 2023
Single-FiO2 lung modelling with machine learning: a computer simulation incorporating volumetric capnography.
We investigated whether machine learning (ML) analysis of ICU monitoring data incorporating volumetric capnography measurements of mean alveolar PCO2 can partition venous admixture (VenAd) into its shunt and low V/Q components without manipulating the inspired oxygen fraction (FiO2). From a 21-compartment ventilation / perfusion (V/Q) model of pulmonary blood flow we generated blood gas and mean alveolar PCO2 data in simulated scenarios with shunt values from 7.3% to 36.5% and a range of FiO2 settings, indirect calorimetry and cardiac output measurements and acid- base and hemoglobin oxygen affinity conditions. A 'deep learning' ML application, trained and validated solely on single FiO2 bedside monitoring data from 14,736 scenarios, then recovered shunt values in 500 test scenarios with true shunt values 'held back'. ⋯ With corresponding VenAd values calculated from the same bedside data, low V/Q flow can be reported as VenAd-shunt. ML analysis of blood gas, indirect calorimetry, volumetric capnography and cardiac output measurements can quantify pulmonary oxygenation deficits as percentage shunt flow (V/Q = 0) versus percentage low V/Q flow (V/Q > 0). High fidelity reports are possible from analysis of data collected solely at the operating FiO2.