Utilizing machine learning to improve clinical trial design for acute respiratory distress syndrome

Heterogeneous patient populations, complex pharmacology and low recruitment rates in the Intensive Care Unit (ICU) have led to the failure of many clinical trials. Recently, machine learning (ML) emerged as a new technology to process and identify big data relationships, enabling a new era in clinical trial design. In this study, we designed a ML model for predictively stratifying acute respiratory distress syndrome (ARDS) patients, ultimately reducing the required number of patients by increasing statistical power through cohort homogeneity. From the Philips eICU Research Institute (eRI) database, no less than 51,555 ARDS patients were extracted. We defined three subpopulations by outcome: (1) rapid death, (2) spontaneous recovery, and (3) long-stay patients. A retrospective univariate analysis identified highly predictive variables for each outcome. All 220 variables were used to determine the most accurate and generalizable model to predict long-stay patients. Multiclass gradient boosting was identified as the best-performing ML model. Whereas alterations in pH, bicarbonate or lactate proved to be strong predictors for rapid death in the univariate analysis, only the multivariate ML model was able to reliably differentiate the disease course of the long-stay outcome population (AUC of 0.77). We demonstrate the feasibility of prospective patient stratification using ML algorithms in the by far largest ARDS cohort reported to date. Our algorithm can identify patients with sufficiently long ARDS episodes to allow time for patients to respond to therapy, increasing statistical power. Further, early enrollment alerts may increase recruitment rate.

Comparison of impedance measurements near the skin of newborns and adults

Electrical impedance tomography (EIT) is a non-invasive imaging technology that has been extensively studied for monitoring lung function of neonatal and adult subjects, especially in neonatal intensive care unit (NICU) and intensive care unit (ICU) environments. The sources of the total impedance in these applications include internal organs, near-boundary tissues, electrode-skin impedance, electrodes and conducting wires. This total impedance must be considered for system design and setting voltage gain since it will contribute to the measured voltage. To adapt a single instrument for use on infants and adults, we studied the difference between the impedance near the skin in both classes of patients. We used a simultaneous multi-source EIT (SMS-EIT) system to make impedance measurements. Characteristic resistance was calculated for two different current patterns: one that is more sensitive to boundary region impedance and another that is more sensitive to interior changes. We present ratios of these resistances to assess the relative contribution of near-skin effects to the overall impedance. Twenty adult ICU subjects (10 male, 10 female, age: 49.05  ±  16.32 years (mean  ±  standard deviation)) and 45 neonates (23 male, 22 female, gestational age: 37.67  ±  2.11 weeks, postnatal age, 2.56  ±  2.67 d) were studied at Columbia University Medical Center. Impedance measurements at 10 kHz were collected for approximately one hour from each subject. The characteristic resistance ratio for each subject was computed and analyzed. The result shows the impedance at or near the skin of newborns is significantly higher than in adult subjects.

Combined optical imaging and mammography of the healthy breast: optical contrast derived from breast structure and compression

In this paper, we report new progress in developing the instrument and software platform of a combined X-ray mammography/diffuse optical breast imaging system. Particularly, we focus on system validation using a series of balloon phantom experiments and the optical image analysis of 49 healthy patients. Using the finite-element method for forward modeling and a regularized Gauss-Newton method for parameter reconstruction, we recovered the inclusions inside the phantom and the hemoglobin images of the human breasts. An enhanced coupling coefficient estimation scheme was also incorporated to improve the accuracy and robustness of the reconstructions. The recovered average total hemoglobin concentration (HbT) and oxygen saturation (SO2) from 68 breast measurements are 16.2 microm and 71%, respectively, where the HbT presents a linear trend with breast density. The low HbT value compared to literature is likely due to the associated mammographic compression. From the spatially co-registered optical/X-ray images, we can identify the chest-wall muscle, fatty tissue, and fibroglandular regions with an average HbT of 20.1+/-6.1 microm for fibroglandular tissue, 15.4+/-5.0 microm for adipose, and 22.2+/-7.3 microm for muscle tissue. The differences between fibroglandular tissue and the corresponding adipose tissue are significant (p < 0.0001). At the same time, we recognize that the optical images are influenced, to a certain extent, by mammographical compression. The optical images from a subset of patients show composite features from both tissue structure and pressure distribution. We present mechanical simulations which further confirm this hypothesis.

Optimal linear inverse solution with multiple priors in diffuse optical tomography

A general framework for incorporating single and multiple priors in diffuse optical tomography is described. We explore the use of this framework for simultaneously utilizing spatial and spectral priors in the context of imaging breast cancer. The utilization of magnetic resonance images of water and lipid content as a statistical spatial prior for the diffuse optical image reconstructions is also discussed. Simulations are performed to demonstrate the significant improvement in image quality afforded by combining spatial and spectral priors.