A computational streak mode cytometry biosensor for rare cell analysis.

Streak mode imaging flow cytometry for rare cell detection involves imaging moving fluorescently labeled cells in the video mode with a CCD camera. The path of the moving cells results in a "streak", whose length is proportional to the exposure time. The dynamic imaging conditions introduce detection challenges (e.g., images with high signal-to-noise ratio (SNR) backgrounds), especially for enumerating cells using low resolution webcams or smartphone cameras suitable for point of care testing (POCT). To overcome the imaging challenges, a new approach called a "computational biosensor" was developed. It involves combining biosensing hardware with computational algorithms to "computationally transduce" measureable signals from events captured by the hardware. The computational biosensor quantifies potential cells based on the streak intensity, length and relative location of the streaks in consecutive frames. Cell identification consists of three parts: (1) finding streaks, (2) identifying candidate cells, and (3) filtering out spurious cells to identify true cells. Samples of 1 cell per mL were analyzed in batch sizes of 30 mL at flow rates of 10 mL min-1 and imaged at 4 frames per second (fps). The detected cells were annotated, and the SNR was calculated. For images with SNR greater than 4.4 dB, the total detected cells (TD) compared with ground truth (GT) are 98%, while 66% were detected for low SNR. For true positive cells detected compared with ground truth (TP/GT), 91% were detected for high SNR. This demonstrated the new analytical capabilities of the computational biosensor to enumerate rare cells in large volumes not possible with current technologies.

Utilizing ultra-early continuous physiologic data to develop automated measures of clinical severity in a traumatic brain injury population.

Determination of prognosis in the triage process after traumatic brain injury (TBI) is difficult to achieve. Current severity measures like the Trauma and injury severity score (TRISS) and revised trauma score (RTS) rely on additional information from the Glasgow Coma Scale (GCS) and the Injury Severity Score (ISS) which may be inaccurate or delayed, limiting their usefulness in the rapid triage setting. We hypothesized that machine learning based estimations of GCS and ISS obtained through modeling of continuous vital sign features could be used to rapidly derive an automated RTS and TRISS. We derived variables from electrocardiograms (ECG), photoplethysmography (PPG), and blood pressure using continuous data obtained in the first 15 min of admission to build machine learning models of GCS and ISS (ML-GCS and ML-ISS). We compared the TRISS and RTS using ML-ISS and ML-GCS and its value using the actual ISS and GCS in predicting in-hospital mortality. Models were tested in TBI with systemic injury (head abbreviated injury scale (AIS) ≥ 1), and isolated TBI (head AIS ≥ 1 and other AIS ≤ 1). The area under the receiver operating characteristic curve (AUROC) was used to evaluate model performance. A total of 21,077 cases (2009-2015) were in the training set. 6057 cases from 2016 to 2017 were used for testing, with 472 (7.8%) severe TBI (GCS 3-8), 223 (3.7%) moderate TBI (GCS 9-12), and 5913 (88.5%) mild TBI (GCS 13-15). In the TBI with systemic injury group, ML-TRISS had similar AUROC (0.963) to TRISS (0.965) in predicting mortality. ML-RTS had AUROC (0.823) and RTS had AUROC 0.928. In the isolated TBI group, ML-TRISS had AUROC 0.977, and TRISS had AUROC 0.983. ML-RTS had AUROC 0.790 and RTS had AUROC 0.957. Estimation of ISS and GCS from machine learning based modeling of vital sign features can be utilized to provide accurate assessments of the RTS and TRISS in a population of TBI patients. Automation of these scores could be utilized to enhance triage and resource allocation during the ultra-early phase of resuscitation.

Evaluation of Tumor Development Using Hemoglobin Saturation Profile on Rodent Dorsal Window Chamber.

Tumor development can be indirectly evaluated using features of the tumor microenvironment (TME), such as hemoglobin saturation (HbSat), blood vessel dilation, and formation of new vessels. High values of HbSat and other features of the TME could indicate high metabolic activity and could precede the formation of angiogenic tumors; therefore, changes in HbSat profile can be used as a biomarker for tumor progression. One methodology to evaluate HbSat profile over time, and correlate it with tumor development in vivo in a preclinical model, is through a dorsal skin-fold window chamber. In this chapter, we provide a detailed description of this methodology to evaluate hemoglobin saturation profile and to predict tumor development. We will cover the surgical preparation of the mouse, the installation/maintenance of the dorsal window chamber, and the imaging processing and evaluation to the HbSat profile to predict new development of new tumor areas over time. We included, in this chapter, step by step examples of the imaging processing method to obtain pixel level HbSat values from raw pixels data, the computational method to determine the HbSat profile, and the steps for the classification of the areas into tumor and no-tumor.

Merkel Cell Carcinoma-Update on Diagnosis, Management and Future Perspectives.

MCC is a rare but highly aggressive skin cancer. The identification of the driving role of Merkel cell polyomavirus (MCPyV) and ultraviolet-induced DNA damage in the oncogenesis of MCC allowed a better understanding of its biological behavior. The presence of MCPyV-specific T cells and lymphocytes exhibiting an 'exhausted' phenotype in the tumor microenvironment along with the high prevalence of immunosuppression among affected patients are strong indicators of the immunogenic properties of MCC. The use of immunotherapy has revolutionized the management of patients with advanced MCC with anti-PD-1/PD L1 blockade, providing objective responses in as much as 50-70% of cases when used in first-line treatment. However, acquired resistance or contraindication to immune checkpoint inhibitors can be an issue for a non-negligible number of patients and novel therapeutic strategies are warranted. This review will focus on current management guidelines for MCC and future therapeutic perspectives for advanced disease with an emphasis on molecular pathways, targeted therapies, and immune-based strategies. These new therapies alone or in combination with anti-PD-1/PD-L1 inhibitors could enhance immune responses against tumor cells and overcome acquired resistance to immunotherapy.

Permutation entropy analysis of vital signs data for outcome prediction of patients with severe traumatic brain injury.

Permutation entropy is computationally efficient, robust to outliers, and effective to measure complexity of time series. We used this technique to quantify the complexity of continuous vital signs recorded from patients with traumatic brain injury (TBI). Using permutation entropy calculated from early vital signs (initial 10-20% of patient hospital stay time), we built classifiers to predict in-hospital mortality and mobility, measured by 3-month Extended Glasgow Outcome Score (GOSE). Sixty patients with severe TBI produced a skewed dataset that we evaluated for accuracy, sensitivity and specificity. The overall prediction accuracy achieved 91.67% for mortality, and 76.67% for 3-month GOSE in testing datasets, using the leave-one-out cross validation. We also applied Receiver Operating Characteristic analysis to compare classifiers built from different learning methods. Those results support the applicability of permutation entropy in analyzing the dynamic behavior of TBI vital signs for early prediction of mortality and long-term patient outcomes.

Predicting secondary insults after severe traumatic brain injury.

BACKGROUND: Secondary insults such as hypotension, hypoxia, cerebral hypoperfusion, and intracranial hypertension are associated with poor outcome following severe traumatic brain injury (TBI). Preventing and minimizing the effect of secondary insults are essential in the management of severe TBI. At present, clinicians have no way to predict the development of these events, limiting their ability to plan appropriate timing of interventions. We hypothesized that processing continuous vital signs (VS) data using machine learning methods could predict the development of future intracranial hypertension. METHODS: Continuous VS including intracranial pressure (ICP), heart rate, systolic blood pressure, and mean arterial pressure data were collected from adult patients admitted to a single Level I trauma center requiring an ICP monitor. We tested the ability of Nearest Neighbor Regression (NNR) to predict changes in ICP by algorithmically learning from the patients' past physiology. RESULTS: Continuous VS were collected on 132 adult patients over a minimum of 3 hours per patient (5,466 hours total; 65,600 data points). Bland-Altman plots show that NNR provides good agreement in predicting actual ICP with a bias of 0.02 (±2 SD = 4 mm Hg) for the subsequent 5 minutes and -0.02 (±2 SD = 10 mm Hg) for the subsequent 2 hours. CONCLUSION: We have demonstrated that with the use of physiologic data, it is possible to predict with reasonable accuracy future ICP levels following severe TBI. NNR predicts ICP changes in clinically useful time frames. This ability to predict events may allow clinicians to make better decisions about the timing of necessary interventions, and this method could support the future development of minimally invasive ICP monitoring systems, which may lead to better overall clinical outcomes after severe TBI. LEVEL OF EVIDENCE: Prognostic study, level III.

Forecasting new development of tumor areas using spatial and temporal distribution profiles of hemoglobin saturation in a mouse model.

Features of the tumor microenvironment (TME), such as hemoglobin saturation (HbSat), can provide valuable information on early development and progression of tumors. HbSat correlates with high metabolism and precedes the formation of angiogenic tumors; therefore, changes in HbSat profile can be used as a biomarker for early cancer detection. In this project, we develop a methodology to evaluate HbSat for forecasting early tumor development in a mouse model. We built a delta ([Formula: see text]) cumulative feature that includes spatial and temporal distribution of HbSat for classifying tumor/normal areas. Using a two-class (normal and tumor) logistic regression, the [Formula: see text] feature successfully forecasts tumor areas in two window chamber mice ([Formula: see text] and 0.85). To assess the performance of the logistic regression-based classifier utilizing the [Formula: see text] feature of each region, we conduct a 10-fold cross-validation analysis (AUC of the [Formula: see text]). These results show that the TME features based on HbSat can be used to evaluate tumor progression and forecast new occurrences of tumor areas.