Intracranial pressure monitoring in adult patients with traumatic brain injury: challenges and innovations.

Intracranial pressure monitoring enables the detection and treatment of intracranial hypertension, a potentially lethal insult after traumatic brain injury. Despite its widespread use, robust evidence supporting intracranial pressure monitoring and treatment remains sparse. International studies have shown large variations between centres regarding the indications for intracranial pressure monitoring and treatment of intracranial hypertension. Experts have reviewed these two aspects and, by consensus, provided practical approaches for monitoring and treatment. Advances have occurred in methods for non-invasive estimation of intracranial pressure although, for now, a reliable way to non-invasively and continuously measure intracranial pressure remains aspirational. Analysis of the intracranial pressure signal can provide information on brain compliance (ie, the ability of the cranium to tolerate volume changes) and on cerebral autoregulation (ie, the ability of cerebral blood vessels to react to changes in blood pressure). The information derived from the intracranial pressure signal might allow for more individualised patient management. Machine learning and artificial intelligence approaches are being increasingly applied to intracranial pressure monitoring, but many obstacles need to be overcome before their use in clinical practice could be attempted. Robust clinical trials are needed to support indications for intracranial pressure monitoring and treatment. Progress in non-invasive assessment of intracranial pressure and in signal analysis (for targeted treatment) will also be crucial.

Dynamic Estimation of Cardiovascular State From Arterial Blood Pressure Recordings.

Real-time estimation of patient cardiovascular states, including cardiac output and systemic vascular resistance, is necessary for personalized hemodynamic monitoring and management. Highly invasive measurements enable reliable estimation of these states but increase patient risk. Prior methods using minimally invasive measurements reduce patient risk but have produced unreliable estimates limited due to trade-offs in accuracy and time resolution. Our objective was to develop an approach to estimate cardiac output and systemic vascular resistance with both a high time resolution and high accuracy from minimally invasive measurements. Using the two-element Windkessel model, we formulated a state-space method to estimate a dynamic time constant - the product of systemic vascular resistance and compliance - from arterial blood pressure measurements. From this time constant, we derived proportional estimates of systemic vascular resistance and cardiac output. We then validated our method with a swine cardiovascular dataset. Our estimates produced using arterial blood pressure measurements not only closely align with those using highly invasive measurements, but also closely align when derived from three separate locations on the arterial tree. Moreover, our estimates predictably change in response to standard cardiovascular drugs. Overall, our approach produces reliable, real-time estimates of cardiovascular states crucial for monitoring and control of the cardiovascular system.

Open cranium model for the study of cerebrovascular dynamics in intracranial hypertension.

BACKGROUND: Significant research has been devoted to developing noninvasive approaches to neuromonitoring. Clinical validation of such approaches is often limited, with minimal data available in the clinically relevant elevated ICP range. NEW METHOD: To allow ultrasound-guided placement of an intraventricular catheter and to perform simultaneous long-duration ICP and ultrasound recordings of cerebral blood flow, we developed a large unilateral craniectomy in a swine model. We also used a microprocessor-controlled actuator for intraventricular saline infusion to reliably and reversibly manipulate ICP according to pre-determined profiles. RESULTS: The model was reproducible, resulting in over 80 hours of high-fidelity, multi-parameter physiological waveform recordings in twelve animals, with ICP ranging from 2 to 78 mmHg. ICP elevations were reversible and reproducible according to two predetermined profiles: a stepwise elevation up to an ICP of 30-35 mmHg and return to normotension, and a clinically significant plateau wave. Finally, ICP was elevated to extreme levels of greater than 60 mmHg, simulating extreme clinical emergency. COMPARISON WITH EXISTING METHODS: Existing methods for ICP monitoring in large animals typically relied on burr-hole approaches for catheter placement. Accurate catheter placement can be difficult in pigs, given the thickness of their skull. Additionally, ultrasound is significantly attenuated by the skull. The open cranium model overcomes these limitations. CONCLUSIONS: The hemicraniectomy model allowed for verified placement of the intraventricular catheter, and reversible and reliable ICP manipulation over a wide range. The large dural window additionally allowed for long-duration recording of cerebral blood flow velocity from the middle cerebral artery.

Fatigue Assessment from Facial Videos using Deep Neural Networks and Engineered Features Informed by Domain Knowledge.

Fatigue impairs cognitive and motor function, potentially leading to mishaps in high-pressure occupations such as aviation and emergency medical services. The current approach is primarily based on self-assessment, which is subjective and error-prone. An objective method is needed to detect severe and likely dangerous levels of fatigue quickly and accurately. Here, we present a quantitative evaluation tool that uses less than two minutes of facial video, captured using an iPad, to assess fatigue vs. alertness. The tool is fast, easy to use, and scalable since it uses cameras readily available on consumer-electronic devices. We compared the classification performance between a Long Short-Term Memory (LSTM) deep neural network and a Random Forest (RF) classifier applied to engineered features informed by domain knowledge. The preliminary results on an 11-subject dataset show that RF outperforms LSTM, with added interpretability on the features used. For the RF classifiers, the average areas under the receiver operating characteristic curve, based on the 11-fold and individualized 11-fold cross validations, are 0.72 ± 0.16 and 0.8 ± 0.12, respectively. Equal error rates are 0.34 and 0.26, respectively. This study presents a promising approach for rapid fatigue detection. Additional data will be collected to assess the generalizability across populations.

Diagnostic suspicion bias and machine learning: Breaking the awareness deadlock for sepsis detection.

Many early warning algorithms are downstream of clinical evaluation and diagnostic testing, which means that they may not be useful when clinicians fail to suspect illness and fail to order appropriate tests. Depending on how such algorithms handle missing data, they could even indicate "low risk" simply because the testing data were never ordered. We considered predictive methodologies to identify sepsis at triage, before diagnostic tests are ordered, in a busy Emergency Department (ED). One algorithm used "bland clinical data" (data available at triage for nearly every patient). The second algorithm added three yes/no questions to be answered after the triage interview. Retrospectively, we studied adult patients from a single ED between 2014-16, separated into training (70%) and testing (30%) cohorts, and a final validation cohort of patients from four EDs between 2016-2018. Sepsis was defined per the Rhee criteria. Investigational predictors were demographics and triage vital signs (downloaded from the hospital EMR); past medical history; and the auxiliary queries (answered by chart reviewers who were blinded to all data except the triage note and initial HPI). We developed L2-regularized logistic regression models using a greedy forward feature selection. There were 1164, 499, and 784 patients in the training, testing, and validation cohorts, respectively. The bland clinical data model yielded ROC AUC's 0.78 (0.76-0.81) and 0.77 (0.73-0.81), for training and testing, respectively, and ranged from 0.74-0.79 in four hospital validation. The second model which included auxiliary queries yielded 0.84 (0.82-0.87) and 0.83 (0.79-0.86), and ranged from 0.78-0.83 in four hospital validation. The first algorithm did not require clinician input but yielded middling performance. The second showed a trend towards superior performance, though required additional user effort. These methods are alternatives to predictive algorithms downstream of clinical evaluation and diagnostic testing. For hospital early warning algorithms, consideration should be given to bias and usability of various methods.

Low-Order Mechanistic Models for Volumetric and Temporal Capnography: Development, Validation, and Application.

OBJECTIVE: Develop low-order mechanistic models accounting quantitatively for, and identifiable from, the capnogram - the CO 2 concentration in exhaled breath, recorded over time (Tcap) or exhaled volume (Vcap). METHODS: The airflow model's single "alveolar" compartment has compliance and inertance, and feeds a resistive unperfused airway comprising a laminar-flow region followed by a turbulent-mixing region. The gas-mixing model tracks mixing-region CO 2 concentration, fitted breath-by-breath to the measured capnogram, yielding estimates of model parameters that characterize the capnogram. RESULTS: For the 17 examined records (310 breaths) of airflow, airway pressure and Tcap from ventilated adult patients, the models fit closely (mean rmse 1% of end-tidal CO 2 concentration on Vcap; 1.7% on Tcap). The associated parameters (4 for Vcap, 5 for Tcap) for each exhalation, and airflow parameters for the corresponding forced inhalation, are robustly estimated, and consonant with literature values. The models also allow, using Tcap alone, estimation of the entire exhaled airflow waveform to within a scaling. This suggests new Tcap-based tests, analogous to spirometry but with normal breathing, for discriminating chronic obstructive pulmonary disease (COPD) from congestive heart failure (CHF). A version trained on 15 exhalations from each of 24 COPD/24 CHF Tcap records from one hospital, then tested 100 times with 15 random exhalations from each of 27 COPD/31 CHF Tcap records at another, gave mean accuracy 80.6% (stdev 2.1%). Another version, tested on 29 COPD/32 CHF, yielded AUROC 0.84. CONCLUSION: Our mechanistic models closely fit Tcap and Vcap measurements, and yield subject-specific parameter estimates. SIGNIFICANCE: This can inform cardiorespiratory care.

Deconvolution-Based Partial Volume Correction for Volumetric Blood Flow Measurement.

Ultrasound-based blood flow (BF) monitoring is vital in the diagnosis and treatment of a variety of cardiovascular and neurologic conditions. Finite spatial resolution of clinical color flow (CF) systems, however, has hampered measurement of vessel cross Section areas. We propose a resolution enhancement technique that allows reliable determination of BF in small vessels. We leverage sparsity in the spatial distribution of the frequency spectrum of routinely collected CF data to blindly determine the point spread function (PSF) of the imaging system in a robust manner. The CF data are then deconvolved with the PSF, and the volumetric flow is computed using the resulting velocity profiles. Data were collected from phantom blood vessels with diameters between 2 and 6 mm using a clinical ultrasound system at 2 MHz insonation frequency. The proposed method yielded a flow estimation bias of 0 mL/min, standard deviation of error (SDE) of 22 mL/min, and a root-mean-square error (RMSE) of 22 mL/min over a 150 mL/min range of mean flows. Recordings were also obtained in low signal-to-noise ratio (SNR) conditions using a skull mimicking element, resulting in an estimation bias of -13 mL/min, SDE of 23 mL/min, and an RMSE of 26 mL/min. The effect of insonation frequency was also investigated by obtaining recordings at 4.3 MHz, yielding an estimation bias of -16 mL/min, SDE of 16 mL/min, and an RMSE of 22 mL/min. The results indicate that our technique can lead to clinically acceptable flow measurements across a range of vessel diameters in high and low SNR regimes.

Modeling of Usual Care: Vasopressor Initiation for Sepsis With Hypotension.

Usual care regarding vasopressor initiation is ill-defined. We aimed to develop a quantitative "dynamic practice" model for usual care in the emergency department (ED) regarding the timing of vasopressor initiation in sepsis. In a retrospective study of 589 septic patients with hypotension in an urban tertiary care center ED, we developed a multi-variable model that distinguishes between patients who did and did not subsequently receive sustained (>24 h) vasopressor therapy. Candidate predictors were vital signs, intravenous fluid (IVF) volumes, laboratory measurements, and elapsed time from triage computed at timepoints leading up to the final decision timepoint of either vasopressor initiation or ED hypotension resolution without vasopressors. A model with six independently significant covariates (respiratory rate, Glasgow Coma Scale score, SBP, SpO2, administered IVF, and elapsed time) achieved a C-statistic of 0.78 in a held-out test set at the final decision timepoint, demonstrating the ability to reliably model usual care for vasopressor initiation for hypotensive septic patients. The included variables measured depth of hypotension, extent of disease severity and organ dysfunction. At an operating point of 90% specificity, the model identified a minority of patients (39%) more than an hour before actual vasopressor initiation, during which time a median of 2,250 (IQR 1,200-3,300) mL of IVF was administered. This single-center analysis shows the feasibility of a quantitative, objective tool for describing usual care. Dynamic practice models may help assess when management was atypical; such tools may also be useful for designing and interpreting clinical trials.