Jose M. Gonzalez’s research while affiliated with United States Army Institute of Surgical Research and other places

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (8)


Figure 2. Summary of Wearable Healthcare Devices (WHDs) for Electroencephalogram (EEG) Measurement. Potential uses in the prehospital setting, clinical decision support applications for the sensor technology, and current technology limitations are summarized.
Figure 3. Summary of Wearable Healthcare Devices (WHDs) for Photoplethysmography (PPG) Measurement. Potential uses in the prehospital setting, clinical decision support applications for the sensor technology, and current technology limitations are summarized.
Figure 4. Summary of Wearable Healthcare Devices (WHDs) for Medical Imaging. Potential uses in the prehospital setting, CDS applications for the sensor technology, and current technology limitations are summarized.
Figure 5. Summary of Wearable Healthcare Devices (WHDs) for Chemical Sensing. Potential uses in the prehospital setting, clinical decision support applications for the sensor technology, and current technology limitations are summarized.
Figure 6. Summary of Wearable Healthcare Devices (WHDs) for Electrocardiogram (ECG) Measurement. Potential uses in the prehospital setting, clinical decision support applications for the sensor technology, and current technology limitations are summarized.

+2

Overview of Wearable Healthcare Devices for Clinical Decision Support in the Prehospital Setting
  • Literature Review
  • Full-text available

December 2024

·

31 Reads

·

1 Citation

Sensors

Rachel Gathright

·

Isiah Mejia

·

Jose M. Gonzalez

·

[...]

·

Eric J. Snider

Prehospital medical care is a major challenge for both civilian and military situations as resources are limited, yet critical triage and treatment decisions must be rapidly made. Prehospital medicine is further complicated during mass casualty situations or remote applications that require more extensive medical treatments to be monitored. It is anticipated on the future battlefield where air superiority will be contested that prolonged field care will extend to as much 72 h in a prehospital environment. Traditional medical monitoring is not practical in these situations and, as such, wearable sensor technology may help support prehospital medicine. However, sensors alone are not sufficient in the prehospital setting where limited personnel without specialized medical training must make critical decisions based on physiological signals. Machine learning-based clinical decision support systems can instead be utilized to interpret these signals for diagnosing injuries, making triage decisions, or driving treatments. Here, we summarize the challenges of the prehospital medical setting and review wearable sensor technology suitability for this environment, including their use with medical decision support triage or treatment guidance options. Further, we discuss recommendations for wearable healthcare device development and medical decision support technology to better support the prehospital medical setting. With further design improvement and integration with decision support tools, wearable healthcare devices have the potential to simplify and improve medical care in the challenging prehospital environment.

Download

Figure 3. Overview of (A,B) the adaptive resuscitation controller (ARC) and (C,D) dual-input fuzzy logic (DFL) resuscitation with simulated non-invasive, intermittent signal input. (A,C) average results with shaded regions denoting standard deviation, and (B,D) pressure vs. time results for each individual subject (n = five swine each), each identified by a different color. Pressure values are relative to their target MAP for each subject. For DFL, the subject identified by the blue line did not receive an initial 100 mL bolus of whole blood (as mentioned in Section 2.2).
Figure 5. Summary of performance metrics for invasive and non-invasive ARC. (A) Relative pressure vs. time results for invasive ARC-based resuscitation for each individual subject (n = 10); each subject is identified by a different line color. (B) Average results for invasive (n = 10) and non-invasive (n = 5) ARC-based resuscitation. Shaded region denotes standard deviation. Performance metric comparison between invasive and non-invasive ARC for (C) effectiveness and resuscitation effectiveness, (D) MDPE and wobble, and (E) area above and below target MAP. Lines denote averages
Figure 6. Effects of intermittent sampling on correlation to continuous MAP signal. Results are shown comparing the mean arterial pressure to (A,D) the pressure after being streamed to the controller computer (MAPStreamed), (B,E) after downsampling the controller signal to one value received every 60 s (MAPIntermittent), and (C,F) the signal having undergone upsampling (MAPUpsampled). (A-C) Correlation plots are shown for each with the goodness of fit coefficient for linear regression shown as well as 95% confidence intervals. (D-F) Bland-Altman plots for differences between each signal vs. the average signal, with 95% confidence intervals shown for each.
MAP Cuff Performance Metrics of Swine Subjects Compared to Continuous MAP.
In Vivo Evaluation of Two Hemorrhagic Shock Resuscitation Controllers with Non-Invasive, Intermittent Sensors

December 2024

·

11 Reads

Bioengineering

Hemorrhage is a leading cause of preventable death in military and civilian trauma medicine. Fluid resuscitation is the primary treatment option, which can be difficult to manage when multiple patients are involved. Traditional vital signs needed to drive resuscitation therapy being unavailable without invasive catheter placement is a challenge. To overcome these obstacles, we propose using closed-loop fluid resuscitation controllers managed by non-invasive, intermittent signal sensor inputs to simplify their use in far-forward environments. Using non-invasive, intermittent sensor controllers will allow quicker medical intervention due to negating the need for an arterial catheter to be placed for pressure-guided fluid resuscitation. Two controller designs were evaluated in a swine hemorrhagic shock injury model, with each controller only receiving non-invasive blood pressure (NIBP) measurements simulated from invasive input signals every 60 s. We found that both physiological closed-loop controllers were able to effectively resuscitate subjects out of life-threatening hemorrhagic shock using only intermittent data inputs with a resuscitation effectiveness of at least 95% for each respective controller. We also compared this intermittent signal input to a NIBP cuff and to a deep learning model that predicts blood pressure from a photoplethysmography waveform. Each approach showed evidence of tracking blood pressure, but more effort is needed to refine these non-invasive input approaches. We conclude that resuscitation controllers hold promise to one day be capable of non-invasive sensor input while retaining their effectiveness, expanding their utility for managing patients during mass casualty or battlefield conditions.


Figure 1-Summary of average results for compensatory reserve measurement (CRM) and mean arterial pressure (MAP) for canines subjected to controlled hemorrhage and post-hemorrhage shock hold. Average CRM deep learning (hCRM-DL) (blue), CRM machine learning (hCRM-ML) (green), and MAP (red) versus relative time across the baseline, hemorrhage, and post-hemorrhage shock-hold region.
Figure 2-Comparison of hCRM-ML and hCRM-DL for tracking hemorrhage in canines. A-Average coefficient of determination (R 2 ) and (B) root mean squared error (RMSE) for CRM models versus MAP for each canine test data set. C-Measurement of hemorrhage detection time relative to hemorrhage start time for MAP, hCRM-ML, and hCRM-DL based on 5 consistent hemorrhage class predictions. D-Receiver operating characteristic (ROC) curves and (E) area under the ROC (AUROC) values for MAP, hCRM-ML, and hCRM-DL models for categorizing baseline and hemorrhage regions.
Figure 3-Summary of average canine blood loss volume metric (cBLVM) results for tracking hemorrhage for dogs subjected to controlled hemorrhage and posthemorrhage shock hold. Average calculated cBLVM (green line), predicted cBLVM (blue line), and MAP (red line) are shown versus relative time across the baseline, hemorrhage, and post-hemorrhage shock-hold region.
Predicting blood loss volume in a canine model of hemorrhagic shock using arterial waveform machine learning analysis

December 2024

·

3 Reads

American Journal of Veterinary Research

OBJECTIVE To determine if the compensatory reserve algorithm validated in humans can be applied to canines. Our secondary objective was to determine if a simpler waveform analysis could predict the percentage of blood loss volume. METHODS 6 purpose-bred, anesthetized dogs underwent 5 rounds of controlled hemorrhage and resuscitation while continuously recording invasive arterial blood pressure waveforms in this prospective, experimental study. We calculated human compensatory reserve using deep learning (hCRM-DL) and machine learning (hCRM-ML) models previously developed with human data. We trained a metric to track blood loss volume using features extracted from canine (c) arterial waveforms as an input. RESULTS When applied to the 6 dogs, the hCRM-DL model ( R ² = 0.38) more poorly fit a linear regression model against mean arterial pressure and had lower area under the receiver operating characteristic (AUROC; 0.60) compared to the hCRM-ML model ( R ² = 0.61; AUROC, 0.73). Conversely, the arterial waveform analysis for canine blood loss volume metric (cBLVM) predicted blood loss in dogs experiencing controlled hemorrhagic shock more accurately ( R ² = 0.74). The cBLVM model for predicting blood loss volume had the highest AUROC score (0.81) and was the earliest indicator of hemorrhage onset. CONCLUSIONS The hCRM-ML and hCRM-DL algorithms did not translate to accurate prediction of the onset of hemorrhagic shock in dogs. However, the arterial waveform feature analysis–derived cBLVM might provide decision support to resuscitate dogs with hemorrhagic shock. CLINICAL RELEVANCE Canine BLVM may be useful in estimating blood loss in dogs, which can guide resuscitation strategies for these patients.


Figure 2. (a) ML model developed using non-detrended data tested on features extracted from nondetrended data. (b) ML model developed using non-detrended data tested on features extracted from detrended data.
Figure 4. (a) ML model developed using unfiltered data for the prediction of PEBL. (b) ML model developed using unfiltered data for the prediction of HemArea.
Figure 5. (a) ML model trained on human data, tested on swine for CRM predictions. (b) DL model trained on human data, tested on swine for CRM predictions.
Average R-Squared and RMSE values from ML models developed using blind non-detrended and detrended waveforms on features extracted from non-detrended and detrended waveforms.
Average R-Squared and RMSE values across 12 LOSOs of PEBL and HemArea predictions versus their respective ground truth.
Machine Learning Models for Tracking Blood Loss and Resuscitation in a Hemorrhagic Shock Swine Injury Model

October 2024

·

18 Reads

Bioengineering

Hemorrhage leading to life-threatening shock is a common and critical problem in both civilian and military medicine. Due to complex physiological compensatory mechanisms, traditional vital signs may fail to detect patients’ impending hemorrhagic shock in a timely manner when life-saving interventions are still viable. To address this shortcoming of traditional vital signs in detecting hemorrhagic shock, we have attempted to identify metrics that can predict blood loss. We have previously combined feature extraction and machine learning methodologies applied to arterial waveform analysis to develop advanced metrics that have enabled the early and accurate detection of impending shock in a canine model of hemorrhage, including metrics that estimate blood loss such as the Blood Loss Volume Metric, the Percent Estimated Blood Loss metric, and the Hemorrhage Area metric. Importantly, these metrics were able to identify impending shock well before traditional vital signs, such as blood pressure, were altered enough to identify shock. Here, we apply these advanced metrics developed using data from a canine model to data collected from a swine model of controlled hemorrhage as an interim step towards showing their relevance to human medicine. Based on the performance of these advanced metrics, we conclude that the framework for developing these metrics in the previous canine model remains applicable when applied to a swine model and results in accurate performance in these advanced metrics. The success of these advanced metrics in swine, which share physiological similarities to humans, shows promise in developing advanced blood loss metrics for humans, which would result in increased positive casualty outcomes due to hemorrhage in civilian and military medicine.


FIGURE 2
FIGURE 3
FIGURE 5
FIGURE 6 Characterization of each predictor for detecting hemorrhage. (A) ROC curves for each ML predictor and MAP. (B) Areas under the ROC curve were quantified for each ML predictor and MAP. (C) Quantified time for detecting hemorrhage for MAP, HemArea, PEBL, and BLVM, based on consistent categorical hemorrhage classification.
Summary of model performance metrics for each trained model type.
Refinement of machine learning arterial waveform models for predicting blood loss in canines

August 2024

·

5 Reads

·

2 Citations

Frontiers in Artificial Intelligence

Introduction Hemorrhage remains a leading cause of death in civilian and military trauma. Hemorrhages also extend to military working dogs, who can experience injuries similar to those of the humans they work alongside. Unfortunately, current physiological monitoring is often inadequate for early detection of hemorrhage. Here, we evaluate if features extracted from the arterial waveform can allow for early hemorrhage prediction and improved intervention in canines. Methods In this effort, we extracted more than 1,900 features from an arterial waveform in canine hemorrhage datasets prior to hemorrhage, during hemorrhage, and during a shock hold period. Different features were used as input to decision tree machine learning (ML) model architectures to track three model predictors—total blood loss volume, estimated percent blood loss, and area under the time versus hemorrhaged blood volume curve. Results ML models were successfully developed for total and estimated percent blood loss, with the total blood loss having a higher correlation coefficient. The area predictors were unsuccessful at being directly predicted by decision tree ML models but could be calculated indirectly from the ML prediction models for blood loss. Overall, the area under the hemorrhage curve had the highest sensitivity for detecting hemorrhage at approximately 4 min after hemorrhage onset, compared to more than 45 min before detection based on mean arterial pressure. Conclusion ML methods successfully tracked hemorrhage and provided earlier prediction in canines, potentially improving hemorrhage detection and objectifying triage for veterinary medicine. Further, its use can potentially be extended to human use with proper training datasets.


Figure 1. (A) The Lower Body Negative Pressure (LBNP) step profile and subject distribution. A maximum of nine negative steps were used, including the initial baseline starting pressure. Subjects were removed from LBNP at hemodynamic decompensation or after the final pressure step (B) Sample distribution (N = 218 subjects) for the LBNP pressure where hemodynamic decompensation was reached.
Figure 5. Representative data for (A) 4, (B) 5, (C) 6, (D) 7, and (E) 8 final LBNP step subjects comparing the CRM-ML model (green line), CRM-DL model (red line), and calculated CRM (orange line).
Figure 6. (A) P-R 2 values and (B) P-RMSE of CRM-ML and CRM-DL models using the perfect regression method. (C) R 2 and (D) RMSE values of CRM-ML and CRM-DL models using the conventional linear regression method.
Training and testing results for different classical machine-learning models trained using the top 1, 5, 10, or 15 extracted features. Performance results are shown for perfect RMSE and R 2 values for each model. Green heat map overlay is set between the minimum and maximum value to indicate better performance.
Cont.
An Explainable Machine-Learning Model for Compensatory Reserve Measurement: Methods for Feature Selection and the Effects of Subject Variability

May 2023

·

40 Reads

·

9 Citations

Bioengineering

Tracking vital signs accurately is critical for triaging a patient and ensuring timely therapeutic intervention. The patient's status is often clouded by compensatory mechanisms that can mask injury severity. The compensatory reserve measurement (CRM) is a triaging tool derived from an arterial waveform that has been shown to allow for earlier detection of hemorrhagic shock. However, the deep-learning artificial neural networks developed for its estimation do not explain how specific arterial waveform elements lead to predicting CRM due to the large number of parameters needed to tune these models. Alternatively, we investigate how classical machine-learning models driven by specific features extracted from the arterial waveform can be used to estimate CRM. More than 50 features were extracted from human arterial blood pressure data sets collected during simulated hypovolemic shock resulting from exposure to progressive levels of lower body negative pressure. A bagged decision tree design using the ten most significant features was selected as optimal for CRM estimation. This resulted in an average root mean squared error in all test data of 0.171, similar to the error for a deep-learning CRM algorithm at 0.159. By separating the dataset into sub-groups based on the severity of simulated hypovolemic shock withstood, large subject variability was observed, and the key features identified for these sub-groups differed. This methodology could allow for the identification of unique features and machine-learning models to differentiate individuals with good compensatory mechanisms against hypovolemia from those that might be poor compensators, leading to improved triage of trauma patients and ultimately enhancing military and emergency medicine.


Figure 2. Image processing and algorithm training pathway. M-mode images were obtained from the synthetic phantom, and coordinates of the time capture window were identified. A rolling window method was performed to isolate 100 individual panels from each capture window. The individual panels were used as the initial training set (No Data Aug box). A basic augmentation step was performed to the original dataset to create the second training set (+X-Y Flip, +Zoom Aug box). The third image preprocessing step used a porcine M-mode image to normalize the histogram for the phantom panels (+Histogram Normalization box). The final augmentation step included brightness and contrast augmentation to generate additional images (+Brightness, +Contrast Aug box).
Figure 3. B-mode image comparison with euthanized porcine subjects and synthetic phantom: (A) Baseline thoracic image acquired from porcine subject; (B) Baseline image acquired from rib and lung phantom apparatus; (C) Post-injury image acquired from same porcine subject; (D) Pneumothorax positive image acquired from synthetic phantom apparatus.
Training Ultrasound Image Classification Deep-Learning Algorithms for Pneumothorax Detection Using a Synthetic Tissue Phantom Apparatus

September 2022

·

95 Reads

·

17 Citations

Journal of Imaging

Ultrasound (US) imaging is a critical tool in emergency and military medicine because of its portability and immediate nature. However, proper image interpretation requires skill, limiting its utility in remote applications for conditions such as pneumothorax (PTX) which requires rapid intervention. Artificial intelligence has the potential to automate ultrasound image analysis for various pathophysiological conditions. Training models require large data sets and a means of troubleshooting in real-time for ultrasound integration deployment, and they also require large animal models or clinical testing. Here, we detail the development of a dynamic synthetic tissue phantom model for PTX and its use in training image classification algorithms. The model comprises a synthetic gelatin phantom cast in a custom 3D-printed rib mold and a lung mimicking phantom. When compared to PTX images acquired in swine, images from the phantom were similar in both PTX negative and positive mimicking scenarios. We then used a deep learning image classification algorithm, which we previously developed for shrapnel detection, to accurately predict the presence of PTX in swine images by only training on phantom image sets, highlighting the utility for a tissue phantom for AI applications.


Figure 3. Arterial waveform results for the phantom platform. (A-C) Three distinct arterial waveforms were generated at both normal and hypovolemic levels. Each plot shows at least 3 waves for both pressure settings. (D) Arterial in-plane doppler signal for the tissue phantom after adding flour to the arterial flow.
Summary of normal and hypovolemic circulating fluid pressure readings for arterial and venous flow. Results are shown for three waveform examples and as mean results. For simplicity, arterial flow is described as systolic, diastolic, and mean arterial pressure (MAP), while central venous pressure (CVP) is shown for venous flow. All values are in units of mmHg.
Comparison of the modular tissue phantom platform vs. commercial vascular trainers. Checkmark indicates model can successfully perform. * Depths and distances between vessels vary across the most commercial phantoms but cannot be adjusted. ** Commercial trainers are likely normovolemic compatible but without pressure control, cannot confirm.
Development of a Modular Tissue Phantom for Evaluating Vascular Access Devices

July 2022

·

47 Reads

·

6 Citations

Bioengineering

Central vascular access (CVA) may be critical for trauma care and stabilizing the casualty. However, it requires skilled personnel, often unavailable during remote medical situations and combat casualty care scenarios. Automated CVA medical devices have the potential to make life-saving therapeutics available in these resource-limited scenarios, but they must be properly designed. Unfortunately, currently available tissue phantoms are inadequate for this use, resulting in delayed product development. Here, we present a tissue phantom that is modular in design, allowing for adjustable flow rate, circulating fluid pressure, vessel diameter, and vessel positions. The phantom consists of a gelatin cast using a 3D-printed mold with inserts representing vessels and bone locations. These removable inserts allow for tubing insertion which can mimic normal and hypovolemic flow, as well as pressure and vessel diameters. Trauma to the vessel wall is assessed using quantification of leak rates from the tubing after removal from the model. Lastly, the phantom can be adjusted to swine or human anatomy, including modeling the entire neurovascular bundle. Overall, this model can better recreate severe hypovolemic trauma cases and subject variability than commercial CVA trainers and may potentially accelerate automated CVA device development.

Citations (5)


... In future applications, nanosensor arrays analysing the volatolome will be integrated into wearable self-powered healthcare devices for clinical decision of prehospitalization [316]. This will also promote the development of telemedicine using monitoring platforms enabling wireless communication [317,318]. ...

Reference:

Volatolomics for Anticipated Diagnosis of Cancers with Chemoresistive Vapour Sensors: A Review
Overview of Wearable Healthcare Devices for Clinical Decision Support in the Prehospital Setting

Sensors

... Additionally, the USAISR has developed blood loss monitoring metrics in canine hemorrhage models. 17 These metrics could accurately predict blood loss in a canine hemorrhage model and had earlier detection time compared to traditional vital signs that are lagging indicators of hypovolemic shock due to compensatory mechanisms present in a subject. However, these ML models were computationally intensive for processing the arterial signals and developing, training, and testing the models. ...

Refinement of machine learning arterial waveform models for predicting blood loss in canines

Frontiers in Artificial Intelligence

... Other CDS examples are related to vital sign signal monitoring for quantifying underlying compensatory effects on patient status to provide earlier identification of shock [38,39]. These algorithms relied on photoplethysmography or arterial blood pressure waveforms to predict compensatory status using deep learning or classical ML models [39][40][41]. An additional CDS tool for predicting hypotension was commercialized by Edwards Lifesciences using invasive arterial waveform data or non-invasive measurement analogues [42][43][44]. ...

An Explainable Machine-Learning Model for Compensatory Reserve Measurement: Methods for Feature Selection and the Effects of Subject Variability

Bioengineering

... As such, AI/ML-based CDS tools have been widely developed for medical applications and have been thoroughly reviewed elsewhere [113][114][115][116]. Some relevant CDS applications for prehospital medicine include automated US-based detection of abdominal hemorrhage [117,118], pneumothorax [119,120], and COVID-19 [36,37]. By redesigning these imaging devices to be in a wearable format, data can be continuously collected "hands-free", opening the possibility to a wider range of CDS applications as the imaging WHD technology becomes more readily available. ...

Training Ultrasound Image Classification Deep-Learning Algorithms for Pneumothorax Detection Using a Synthetic Tissue Phantom Apparatus

Journal of Imaging

... The US display provides track lines to delineate the expected insertion path. Our team previously developed laboratory test platforms [14] for vascular access device evaluation as well as an ex vivo swine model [15]. We expanded on the testing pipeline to evaluate the Vu-Path™ ACVAD in a swine model as well as conduct a human usability assessment. ...

Development of a Modular Tissue Phantom for Evaluating Vascular Access Devices

Bioengineering