Noise-robust bioimpedance approach for cardiac output measurement

Rapid patient-specific FEM meshes from 3D smart-phone based scans

Objective.The objective of this study was to describe and evaluate a smart-phone based method to rapidly generate subject-specific finite element method (FEM) meshes. More accurate FEM meshes should lead to more accurate thoracic electrical impedance tomography (EIT) images.Approach.The method was evaluated on an iPhone®that utilized an app called Heges, to obtain 3D scans (colored, surface triangulations), a custom belt, and custom open-source software developed to produce the subject-specific meshes. The approach was quantitatively validated via mannequin and volunteer tests using an infrared tracker as the gold standard, and qualitatively assessed in a series of tidal-breathing EIT images recorded from 9 subjects.Main results.The subject-specific meshes can be generated in as little as 6.3 min, which requires on average 3.4 min of user interaction. The mannequin tests yielded high levels of precision and accuracy at 3.2 ± 0.4 mm and 4.0 ± 0.3 mm root mean square error (RMSE), respectively. Errors on volunteers were only slightly larger (5.2 ± 2.1 mm RMSE precision and 7.7 ± 2.9 mm RMSE accuracy), illustrating the practical RMSE of the method.Significance.Easy-to-generate, subject-specific meshes could be utilized in the thoracic EIT community, potentially reducing geometric-based artifacts and improving the clinical utility of EIT.

Artificial intelligence in perioperative management of major gastrointestinal surgeries

Artificial intelligence (AI) demonstrated by machines is based on reinforcement learning and revolves around the usage of algorithms. The purpose of this review was to summarize concepts, the scope, applications, and limitations in major gastrointestinal surgery. This is a narrative review of the available literature on the key capabilities of AI to help anesthesiologists, surgeons, and other physicians to understand and critically evaluate ongoing and new AI applications in perioperative management. AI uses available databases called "big data" to formulate an algorithm. Analysis of other data based on these algorithms can help in early diagnosis, accurate risk assessment, intraoperative management, automated drug delivery, predicting anesthesia and surgical complications and postoperative outcomes and can thus lead to effective perioperative management as well as to reduce the cost of treatment. Perioperative physicians, anesthesiologists, and surgeons are well-positioned to help integrate AI into modern surgical practice. We all need to partner and collaborate with data scientists to collect and analyze data across all phases of perioperative care to provide clinical scenarios and context. Careful implementation and use of AI along with real-time human interpretation will revolutionize perioperative care, and is the way forward in future perioperative management of major surgery.

Cardiac eigen imaging: a novel method to isolate cardiac activity in thoracic electrical impedance tomography

OBJECTIVE

As the global burden of cardiovascular disease increases, proactive cardiovascular healthcare by means of accurate, precise, continuous, and non-invasive monitoring is becoming crucial. However, no current device is able to provide cardiac hemodynamic monitoring with the aforementioned criterion. Electrical impedance tomography (EIT) is an inexpensive, non-invasive imaging modality that can provide real-time images of internal conductivity distributions that describe physiological activity. This work explores and compares a standard approach of regular cardiac gated averaging (RCGA) and a newly developed method, cardiac eigen-imaging (CEI), based on the singular value decomposition (SVD) to isolate cardiac activity in thoracic EIT.

APPROACH

EIT and heart-rate (HR) data were collected from 20 heart-failure patients preceding echocardiography. Features from RCGA and CEI images were correlated with stroke volume (SV) from echocardiography and image reconstruction parameters were optimized using leave-one-out (LOO) cross-validation.

MAIN RESULTS

CEI per-pixel-based features achieved a Pearson correlation coefficient of 0.80 with SV relative to 0.72 with RCGA. CEI had 33 high-correlating pixels while RCGA had 8. High-correlating pixels tend to concentrate in the right-ventricle (RV) when referenced to a general chest model.

SIGNIFICANCE

While both RCGA and CEI images had high-correlating pixels, CEI had higher correlations, a larger number of high-correlating pixels, and unlike RCGA is not dependent on the quality of the HR data collected. The observed performance of the CEI approach represents a promising step forward for EIT-based cardiac monitoring in either clinical or ambulatory settings.

A robust and novel electrical impedance metric of pulmonary function in ALS patients

OBJECTIVE

Pulmonary function tests (PFTs) are important for assessing respiratory function in amyotrophic lateral sclerosis (ALS) patients. However, weakness of oral and glottal closure, due to concomitant bulbar dysfunction, may result in unreliable PFT values stemming from leakage of air around the breathing tube and through the glottis. In this study, we assessed whether standard thoracic electrical impedance tomography (EIT) could serve as a surrogate measure for PFTs.

APPROACH

Thoracic EIT was performed simultaneously with standard PFTs on seven ALS patients without clinical bulbar weakness (six men and one woman, mean age of 63 years) and ten healthy volunteers (seven men and three women, mean age of 57 years). A raw impedance metric along with more standard EIT measures were computed and correlated with the normalized forced vital capacity (FVC). Additionally, test/re-test metrics and EIT images were analyzed.

MAIN RESULTS

The impedance metric was found to be robust and sensitive to lung activity. We also identified qualitative EIT differences between healthy volunteers and ALS patients, with the ALS images showing greater heterogeneity. Significant correlations with FVC were found for both impedance and EIT metrics in ALS patients (r² = 0.89) and for the impedance metric only in healthy volunteers (r² = 0.49).

SIGNIFICANCE

This suggests that EIT, using our novel impedance metric, has the potential to serve as an alternative technology to standard PFTs for assessing pulmonary function in patients with ALS, offering new metrics of disease status for those with bulbar weakness.