A Deep Learning Framework for Deriving Noninvasive Intracranial Pressure Waveforms from Transcranial Doppler.

Increased intracranial pressure (ICP) causes disability and mortality in the neurointensive care population. Current methods for monitoring ICP are invasive. We designed a deep learning framework using a domain adversarial neural network to estimate noninvasive ICP, from blood pressure, electrocardiogram, and cerebral blood flow velocity. Our model had a mean of median absolute error of 3.88 ± 3.26 mmHg for the domain adversarial neural network, and 3.94 ± 1.71 mmHg for the domain adversarial transformers. Compared with nonlinear approaches, such as support vector regression, this was 26.7% and 25.7% lower. Our proposed framework provides more accurate noninvasive ICP estimates than currently available. ANN NEUROL 2023;94:196-202.

Optimal Cerebral Perfusion Pressure and Brain Tissue Oxygen in Aneurysmal Subarachnoid Hemorrhage.

BACKGROUND: Targeting a cerebral perfusion pressure optimal for cerebral autoregulation (CPPopt) has been gaining more attention to prevent secondary damage after acute neurological injury. Brain tissue oxygenation (PbtO2) can identify insufficient cerebral blood flow and secondary brain injury. Defining the relationship between CPPopt and PbtO2 after aneurysmal subarachnoid hemorrhage may result in (1) mechanistic insights into whether and how CPPopt-based strategies might be beneficial and (2) establishing support for the use of PbtO2 as an adjunctive monitor for adequate or optimal local perfusion. METHODS: We performed a retrospective analysis of a prospectively collected 2-center dataset of patients with aneurysmal subarachnoid hemorrhage with or without later diagnosis of delayed cerebral ischemia (DCI). CPPopt was calculated as the cerebral perfusion pressure (CPP) value corresponding to the lowest pressure reactivity index (moving correlation coefficient of mean arterial and intracranial pressure). The relationship of (hourly) deltaCPP (CPP-CPPopt) and PbtO2 was investigated using natural spline regression analysis. Data after DCI diagnosis were excluded. Brain tissue hypoxia was defined as PbtO2 <20 mmHg. RESULTS: One hundred thirty-one patients were included with a median of 44.0 (interquartile range, 20.8-78.3) hourly CPPopt/PbtO2 datapoints. The regression plot revealed a nonlinear relationship between PbtO2 and deltaCPP (P<0.001) with PbtO2 decrease with deltaCPP <0 mmHg and stable PbtO2 with deltaCPP ≥0mmHg, although there was substantial individual variation. Brain tissue hypoxia (34.6% of all measurements) was more frequent with deltaCPP <0 mmHg. These dynamics were similar in patients with or without DCI. CONCLUSIONS: We found a nonlinear relationship between PbtO2 and deviation of patients' CPP from CPPopt in aneurysmal subarachnoid hemorrhage patients in the pre-DCI period. CPP values below calculated CPPopt were associated with lower PbtO2. Nevertheless, the nature of PbtO2 measurements is complex, and the variability is high. Combined multimodality monitoring with CPP/CPPopt and PbtO2 should be recommended to redefine individual pressure targets (CPP/CPPopt) and retain the option to detect local perfusion deficits during DCI (PbtO2), which cannot be fulfilled by both measurements interchangeably.

A mathematical model of SARS-CoV-2 immunity predicts paxlovid rebound.

Nirmatrelvir/ritonavir (Paxlovid), an oral antiviral medication targeting SARS-CoV-2, remains an important treatment for COVID-19. Initial studies of nirmatrelvir/ritonavir were performed in SARS-CoV-2 unvaccinated patients without prior confirmed SARS-CoV-2 infection; however, most individuals have now either been vaccinated and/or have experienced SARS-CoV-2 infection. After nirmatrelvir/ritonavir became widely available, reports surfaced of "Paxlovid rebound," a phenomenon in which symptoms (and SARS-CoV-2 test positivity) would initially resolve, but after finishing treatment, symptoms and test positivity would return. We used a previously described parsimonious mathematical model of immunity to SARS-CoV-2 infection to model the effect of nirmatrelvir/ritonavir treatment in unvaccinated and vaccinated patients. Model simulations show that viral rebound after treatment occurs only in vaccinated patients, while unvaccinated (SARS-COV-2 naïve) patients treated with nirmatrelvir/ritonavir do not experience any rebound in viral load. This work suggests that an approach combining parsimonious models of the immune system could be used to gain important insights in the context of emerging pathogens.

The oxygen reactivity index indicates disturbed local perfusion regulation after aneurysmal subarachnoid hemorrhage: an observational cohort study.

BACKGROUND: Cerebral autoregulation (CA) can be impaired in patients with delayed cerebral ischemia (DCI) after aneurysmal subarachnoid hemorrhage (aSAH). The Pressure Reactivity Index (PRx, correlation of blood pressure and intracranial pressure) and Oxygen Reactivity Index (ORx, correlation of cerebral perfusion pressure and brain tissue oxygenation, PbtO2) are both believed to estimate CA. We hypothesized that CA could be poorer in hypoperfused territories during DCI and that ORx and PRx may not be equally effective in detecting such local variances. METHODS: ORx and PRx were compared daily in 76 patients with aSAH with or without DCI until the time of DCI diagnosis. The ICP/PbtO2-probes of DCI patients were retrospectively stratified by being in or outside areas of hypoperfusion via CT perfusion image, resulting in three groups: DCI + /probe + (DCI patients, probe located inside the hypoperfused area), DCI + /probe- (probe outside the hypoperfused area), DCI- (no DCI). RESULTS: PRx and ORx were not correlated (r = - 0.01, p = 0.56). Mean ORx but not PRx was highest when the probe was located in a hypoperfused area (ORx DCI + /probe + 0.28 ± 0.13 vs. DCI + /probe- 0.18 ± 0.15, p < 0.05; PRx DCI + /probe + 0.12 ± 0.17 vs. DCI + /probe- 0.06 ± 0.20, p = 0.35). PRx detected poorer autoregulation during the early phase with relatively higher ICP (days 1-3 after hemorrhage) but did not differentiate the three groups on the following days when ICP was lower on average. ORx was higher in the DCI + /probe + group than in the other two groups from day 3 onward. ORx and PRx did not differ between patients with DCI, whose probe was located elsewhere, and patients without DCI (ORx DCI + /probe- 0.18 ± 0.15 vs. DCI- 0.20 ± 0.14; p = 0.50; PRx DCI + /probe- 0.06 ± 0.20 vs. DCI- 0.08 ± 0.17, p = 0.35). CONCLUSIONS: PRx and ORx are not interchangeable measures of autoregulation, as they likely measure different homeostatic mechanisms. PRx represents the classical cerebrovascular reactivity and might be better suited to detect disturbed autoregulation during phases with moderately elevated ICP. Autoregulation may be poorer in territories affected by DCI. These local perfusion disturbances leading up to DCI may be more readily detected by ORx than PRx. Further research should investigate their robustness to detect DCI and to serve as a basis for autoregulation-targeted treatment after aSAH.

Classification of Level of Consciousness in a Neurological ICU Using Physiological Data.

BACKGROUND: Impaired consciousness is common in intensive care unit (ICU) patients, and an individual's degree of consciousness is crucial to determining their care and prognosis. However, there are no methods that continuously monitor consciousness and alert clinicians to changes. We investigated the use of physiological signals collected in the ICU to classify levels of consciousness in critically ill patients. METHODS: We studied 61 patients with subarachnoid hemorrhage (SAH) and 178 patients with intracerebral hemorrhage (ICH) from the neurological ICU at Columbia University Medical Center in a retrospective observational study of prospectively collected data. The level of consciousness was determined on the basis of neurological examination and mapped to comatose, vegetative state or unresponsive wakefulness syndrome (VS/UWS), minimally conscious minus state (MCS-), and command following. For each physiological signal, we extracted time-series features and performed classification using extreme gradient boosting on multiple clinically relevant tasks across subsets of physiological signals. We applied this approach independently on both SAH and ICH patient groups for three sets of variables: (1) a minimal set common to most hospital patients (e.g., heart rate), (2) variables available in most ICUs (e.g., body temperature), and (3) an extended set recorded mainly in neurological ICUs (absent for the ICH patient group; e.g., brain temperature). RESULTS: On the commonly performed classification task of VS/UWS versus MCS-, we achieved an area under the receiver operating characteristic curve (AUROC) in the SAH patient group of 0.72 (sensitivity 82%, specificity 57%; 95% confidence interval [CI] 0.63-0.81) using the extended set, 0.69 (sensitivity 83%, specificity 51%; 95% CI 0.59-0.78) on the variable set available in most ICUs, and 0.69 (sensitivity 56%, specificity 78%; 95% CI 0.60-0.78) on the minimal set. In the ICH patient group, AUROC was 0.64 (sensitivity 56%, specificity 65%; 95% CI 0.55-0.74) using the minimal set and 0.61 (sensitivity 50%, specificity 80%; 95% CI 0.51-0.71) using the variables available in most ICUs. CONCLUSIONS: We find that physiological signals can be used to classify states of consciousness for patients in the ICU. Building on this with intraday assessments and increasing sensitivity and specificity may enable alarm systems that alert physicians to changes in consciousness and frequent monitoring of consciousness throughout the day, both of which may improve patient care and outcomes.

Suboptimal Cerebral Perfusion is Associated with Ischemia After Intracerebral Hemorrhage.

BACKGROUND: Remote ischemic lesions on diffusion-weighted imaging (DWI) occur in one third of patients with intracerebral hemorrhage (ICH) and are associated with worse outcomes. The etiology is unclear and not solely due to blood pressure reduction. We hypothesized that impaired cerebrovascular autoregulation and hypoperfusion below individualized lower limits of autoregulation are associated with the presence of DWI lesions. METHODS: This was a retrospective, single-center study of all primary ICH with intraparenchymal pressure monitoring within 10 days from onset and subsequent magnetic resonance imaging. Pressure reactivity index was calculated as the correlation coefficient between mean arterial pressure and intracranial pressure. Optimal cerebral perfusion pressure (CPPopt) is the cerebral perfusion pressure (CPP) with the lowest corresponding pressure reactivity index. The difference between CPP and CPPopt, time spent below the lower limit of autoregulation (LLA), and time spent above the upper limit of autoregulation (ULA) were calculated by using mean hourly physiologic data. Univariate associations between physiologic parameters and DWI lesions were analyzed by using binary logistic regression. RESULTS: A total of 505 h of artifact-free data from seven patients without DWI lesions and 479 h from six patients with DWI lesions were analyzed. Patients with DWI lesions had higher intracranial pressure (17.50 vs. 10.92 mm Hg; odds ratio 1.14, confidence interval 1.01-1.29) but no difference in mean arterial pressure or CPP compared with patients without DWI lesions. The presence of DWI lesions was significantly associated with a greater percentage of time spent below the LLA (49.85% vs. 14.70%, odds ratio 5.77, confidence interval 1.88-17.75). No significant association was demonstrated between CPPopt, the difference between CPP and CPPopt, ULA, LLA, or time spent above the ULA between groups. CONCLUSIONS: Blood pressure reduction below the LLA is associated with ischemia after acute ICH. Individualized, autoregulation-informed targets for blood pressure reduction may provide a novel paradigm in acute management of ICH and require further study.

Intraarterial Nimodipine Versus Induced Hypertension for Delayed Cerebral Ischemia: A Modified Treatment Protocol.

BACKGROUND: Rescue treatment for delayed cerebral ischemia (DCI) after subarachnoid hemorrhage can include induced hypertension (iHTN) and, in refractory cases, endovascular approaches, of which selective, continuous intraarterial nimodipine (IAN) is one variant. The combination of iHTN and IAN can dramatically increase vasopressor demand. In case of unsustainable doses, iHTN is often prioritized over IAN. However, evidence in this regard is largely lacking. We investigated the effects of a classical (iHTN+IAN) and modified (IANonly) treatment protocol for refractory DCI in an observational study. METHODS: Rescue treatment for DCI was initiated with iHTN (target >180 mm Hg systolic) and escalated to IAN in refractory cases. Until July 2018, both iHTN and IAN were offered in cases refractory to iHTN alone. After protocol modification, iHTN target was preemptively lowered to >120 mm Hg when IAN was initiated (IANonly). Primary outcome was noradrenaline demand. Secondary outcomes included noradrenaline-associated complications, brain tissue oxygenation, DCI-related infarction and favorable 6-month outcome (Glasgow Outcome Scale 4-5). RESULTS: N=29 and n=20 patients were treated according to the classical and modified protocol, respectively. Protocol modification resulted in a significant reduction of noradrenaline demand (iHTN+IAN 0.70±0.54 µg/kg per minute and IANonly 0.26±0.20 µg/kg per minute, P<0.0001) and minor complications (15.0% versus 48.3%, unadjusted odds ratio, 0.19 [95% CI, 0.05-0.79]; P<0.05) with comparable rates of major complications (20.0% versus 20.7%, odds ratio, 0.96 [0.23-3.95]; P=0.95). Incidence of DCI-related infarction (45.0% versus 41.1%, odds ratio, 1.16 [0.37-3.66]; P=0.80) and favorable clinical outcome (55.6% versus 40.0%, odds ratio, 1.88 [0.55-6.39]; P=0.32) were similar. Brain tissue oxygenation was significantly higher with IANonly (26.6±12.8, 39.6±15.4 mm Hg; P<0.01). CONCLUSIONS: Assuming the potential of iHTN to be exhausted in case of refractory hypoperfusion, additional IAN may serve as a last-resort measure to bridge hypoperfusion in the DCI phase. With close monitoring, preemptive lowering of pressure target after induction of IAN may be a safe alternative to alleviate total noradrenaline load and potentially reduce complication rate.

Detection of Brain Activation in Unresponsive Patients with Acute Brain Injury.

BACKGROUND: Brain activation in response to spoken motor commands can be detected by electroencephalography (EEG) in clinically unresponsive patients. The prevalence and prognostic importance of a dissociation between commanded motor behavior and brain activation in the first few days after brain injury are not well understood. METHODS: We studied a prospective, consecutive series of patients in a single intensive care unit who had acute brain injury from a variety of causes and who were unresponsive to spoken commands, including some patients with the ability to localize painful stimuli or to fixate on or track visual stimuli. Machine learning was applied to EEG recordings to detect brain activation in response to commands that patients move their hands. The functional outcome at 12 months was determined with the Glasgow Outcome Scale-Extended (GOS-E; levels range from 1 to 8, with higher levels indicating better outcomes). RESULTS: A total of 16 of 104 unresponsive patients (15%) had brain activation detected by EEG at a median of 4 days after injury. The condition in 8 of these 16 patients (50%) and in 23 of 88 patients (26%) without brain activation improved such that they were able to follow commands before discharge. At 12 months, 7 of 16 patients (44%) with brain activation and 12 of 84 patients (14%) without brain activation had a GOS-E level of 4 or higher, denoting the ability to function independently for 8 hours (odds ratio, 4.6; 95% confidence interval, 1.2 to 17.1). CONCLUSIONS: A dissociation between the absence of behavioral responses to motor commands and the evidence of brain activation in response to these commands in EEG recordings was found in 15% of patients in a consecutive series of patients with acute brain injury. (Supported by the Dana Foundation and the James S. McDonnell Foundation.).

Optimal Cerebral Perfusion Pressure During Delayed Cerebral Ischemia After Aneurysmal Subarachnoid Hemorrhage.

OBJECTIVES: The recommendation of induced hypertension for delayed cerebral ischemia treatment after aneurysmal subarachnoid hemorrhage has been challenged recently and ideal pressure targets are missing. A new concept advocates an individual cerebral perfusion pressure where cerebral autoregulation functions best to ensure optimal global perfusion. We characterized optimal cerebral perfusion pressure at time of delayed cerebral ischemia and tested the conformity of induced hypertension with this target value. DESIGN: Retrospective analysis of prospectively collected data. SETTING: University hospital neurocritical care unit. PATIENTS: Thirty-nine aneurysmal subarachnoid hemorrhage patients with invasive neuromonitoring (20 with delayed cerebral ischemia, 19 without delayed cerebral ischemia). INTERVENTIONS: Induced hypertension greater than 180 mm Hg systolic blood pressure. MEASUREMENTS AND MAIN RESULTS: Changepoint analysis was used to calculate significant changes in cerebral perfusion pressure, optimal cerebral perfusion pressure, and the difference of cerebral perfusion pressure and optimal cerebral perfusion pressure 48 hours before delayed cerebral ischemia diagnosis. Optimal cerebral perfusion pressure increased 30 hours before the onset of delayed cerebral ischemia from 82.8 ± 12.5 to 86.3 ± 11.4 mm Hg (p < 0.05). Three hours before delayed cerebral ischemia, a changepoint was also found in the difference of cerebral perfusion pressure and optimal cerebral perfusion pressure (decrease from -0.2 ± 11.2 to -7.7 ± 7.6 mm Hg; p < 0.05) with a corresponding increase in pressure reactivity index (0.09 ± 0.33 to 0.19 ± 0.37; p < 0.05). Cerebral perfusion pressure at time of delayed cerebral ischemia was lower than in patients without delayed cerebral ischemia in a comparable time frame (cerebral perfusion pressure delayed cerebral ischemia 81.4 ± 8.3 mm Hg, no delayed cerebral ischemia 90.4 ± 10.5 mm Hg; p < 0.05). Inducing hypertension resulted in a cerebral perfusion pressure above optimal cerebral perfusion pressure (+12.4 ± 8.3 mm Hg; p < 0.0001). Treatment response (improvement of delayed cerebral ischemia: induced hypertension+ [n = 15] or progression of delayed cerebral ischemia: induced hypertension- [n = 5]) did not correlate to either absolute values of cerebral perfusion pressure or optimal cerebral perfusion pressure, nor the resulting difference (cerebral perfusion pressure [p = 0.69]; optimal cerebral perfusion pressure [p = 0.97]; and the difference of cerebral perfusion pressure and optimal cerebral perfusion pressure [p = 0.51]). CONCLUSIONS: At the time of delayed cerebral ischemia occurrence, there is a significant discrepancy between cerebral perfusion pressure and optimal cerebral perfusion pressure with worsening of autoregulation, implying inadequate but identifiable individual perfusion. Standardized induction of hypertension resulted in cerebral perfusion pressures that exceeded individual optimal cerebral perfusion pressure in delayed cerebral ischemia patients. The potential benefit of individual blood pressure management guided by autoregulation-based optimal cerebral perfusion pressure should be explored in future intervention studies.

Vector Angle Analysis of Multimodal Neuromonitoring Data for Continuous Prediction of Delayed Cerebral Ischemia.

BACKGROUND: Dysfunctional cerebral autoregulation often precedes delayed cerebral ischemia (DCI). Currently, there are no data-driven techniques that leverage this information to predict DCI in real time. Our hypothesis is that information using continuous updated analyses of multimodal neuromonitoring and cerebral autoregulation can be deployed to predict DCI. METHODS: Time series values of intracranial pressure, brain tissue oxygenation, cerebral perfusion pressure (CPP), optimal CPP (CPPOpt), ΔCPP (CPP - CPPOpt), mean arterial pressure, and pressure reactivity index were combined and summarized as vectors. A validated temporal signal angle measurement was modified into a classification algorithm that incorporates hourly data. The time-varying temporal signal angle measurement (TTSAM) algorithm classifies DCI at varying time points by vectorizing and computing the angle between the test and reference time signals. The patient is classified as DCI+ if the error between the time-varying test vector and DCI+ reference vector is smaller than that between the time-varying test vector and DCI- reference vector. Finally, prediction at time point t is calculated as the majority voting over all the available signals. The leave-one-patient-out cross-validation technique was used to train and report the performance of the algorithms. The TTSAM and classifier performance was determined by balanced accuracy, F1 score, true positive, true negative, false positive, and false negative over time. RESULTS: One hundred thirty-one patients with aneurysmal subarachnoid hemorrhage who underwent multimodal neuromonitoring were identified from two centers (Columbia University: 52 [39.7%], Aachen University: 79 [60.3%]) and included in the analysis. Sixty-four (48.5%) patients had DCI, and DCI was diagnosed 7.2 ± 3.3 days after hemorrhage. The TTSAM algorithm achieved a balanced accuracy of 67.3% and an F1 score of 0.68 at 165 h (6.9 days) from bleed day with a true positive of 0.83, false positive of 0.16, true negative of 0.51, and false negative of 0.49. CONCLUSIONS: A TTSAM algorithm using multimodal neuromonitoring and cerebral autoregulation calculations shows promise to classify DCI in real time.

Predicting Shunt Dependency from the Effect of Cerebrospinal Fluid Drainage on Ventricular Size.

BACKGROUND: Prolonged external ventricular drainage (EVD) in patients with subarachnoid hemorrhage (SAH) leads to morbidity, whereas early removal can have untoward effects related to recurrent hydrocephalus. A metric to help determine the optimal time for EVD removal or ventriculoperitoneal shunt (VPS) placement would be beneficial in preventing the prolonged, unnecessary use of EVD. This study aimed to identify whether dynamics of cerebrospinal fluid (CSF) biometrics can temporally predict VPS dependency after SAH. METHODS: This was a retrospective analysis of a prospective, single-center, observational study of patients with aneurysmal SAH who required EVD placement for hydrocephalus. Patients were divided into VPS-dependent (VPS+) and non-VPS dependent groups. We measured the bicaudate index (BCI) on all available computed tomography scans and calculated the change over time (ΔBCI). We analyzed the relationship of ΔBCI with CSF output by using Pearson's correlation. A k-nearest neighbor model of the relationship between ΔBCI and CSF output was computed to classify VPS. RESULTS: Fifty-eight patients met inclusion criteria. CSF output was significantly higher in the VPS+ group in the 7 days post EVD placement. There was a negative correlation between delta BCI and CSF output in the VPS+ group (negative delta BCI means ventricles become smaller) and a positive correlation in the VPS- group starting from days four to six after EVD placement (p < 0.05). A weighted k-nearest neighbor model for classification had a sensitivity of 0.75, a specificity of 0.70, and an area under the receiver operating characteristic curve of 0.80. CONCLUSIONS: The correlation of ΔBCI and CSF output is a reliable intraindividual biometric for VPS dependency after SAH as early as days four to six after EVD placement. Our machine learning model leverages this relationship between ΔBCI and cumulative CSF output to predict VPS dependency. Early knowledge of VPS dependency could be studied to reduce EVD duration in many centers (intensive care unit length of stay).

Dynamic Intracranial Pressure Waveform Morphology Predicts Ventriculitis.

BACKGROUND: Intracranial pressure waveform morphology reflects compliance, which can be decreased by ventriculitis. We investigated whether morphologic analysis of intracranial pressure dynamics predicts the onset of ventriculitis. METHODS: Ventriculitis was defined as culture or Gram stain positive cerebrospinal fluid, warranting treatment. We developed a pipeline to automatically isolate segments of intracranial pressure waveforms from extraventricular catheters, extract dominant pulses, and obtain morphologically similar groupings. We used a previously validated clinician-supervised active learning paradigm to identify metaclusters of triphasic, single-peak, or artifactual peaks. Metacluster distributions were concatenated with temperature and routine blood laboratory values to create feature vectors. A L2-regularized logistic regression classifier was trained to distinguish patients with ventriculitis from matched controls, and the discriminative performance using area under receiver operating characteristic curve with bootstrapping cross-validation was reported. RESULTS: Fifty-eight patients were included for analysis. Twenty-seven patients with ventriculitis from two centers were identified. Thirty-one patients with catheters but without ventriculitis were selected as matched controls based on age, sex, and primary diagnosis. There were 1590 h of segmented data, including 396,130 dominant pulses in patients with ventriculitis and 557,435 pulses in patients without ventriculitis. There were significant differences in metacluster distribution comparing before culture-positivity versus during culture-positivity (p < 0.001) and after culture-positivity (p < 0.001). The classifier demonstrated good discrimination with median area under receiver operating characteristic 0.70 (interquartile range 0.55-0.80). There were 1.5 true alerts (ventriculitis detected) for every false alert. CONCLUSIONS: Intracranial pressure waveform morphology analysis can classify ventriculitis without cerebrospinal fluid sampling.

Dynamic Detection of Delayed Cerebral Ischemia: A Study in 3 Centers.

BACKGROUND AND PURPOSE: Delayed cerebral ischemia (DCI) after aneurysmal subarachnoid hemorrhage negatively impacts long-term recovery but is often detected too late to prevent damage. We aim to develop hourly risk scores using routinely collected clinical data to detect DCI. METHODS: A DCI classification model was trained using vital sign measurements (heart rate, blood pressure, respiratory rate, and oxygen saturation) and demographics routinely collected for clinical care. Twenty-two time-varying physiological measures were computed including mean, SD, and cross-correlation of heart rate time series with each of the other vitals. Classification was achieved using an ensemble approach with L2-regularized logistic regression, random forest, and support vector machines models. Classifier performance was determined by area under the receiver operating characteristic curves and confusion matrices. Hourly DCI risk scores were generated as the posterior probability at time t using the Ensemble classifier on cohorts recruited at 2 external institutions (n=38 and 40). RESULTS: Three hundred ten patients were included in the training model (median, 54 years old [interquartile range, 45-65]; 80.2% women, 28.4% Hunt and Hess scale 4-5, 38.7% Modified Fisher Scale 3-4); 101 (33%) developed DCI with a median onset day 6 (interquartile range, 5-8). Classification accuracy before DCI onset was 0.83 (interquartile range, 0.76-0.83) area under the receiver operating characteristic curve. Risk scores applied to external institution datasets correctly predicted 64% and 91% of DCI events as early as 12 hours before clinical detection, with 2.7 and 1.6 true alerts for every false alert. CONCLUSIONS: An hourly risk score for DCI derived from routine vital signs may have the potential to alert clinicians to DCI, which could reduce neurological injury.

Use of Clustering to Investigate Changes in Intracranial Pressure Waveform Morphology in Patients with Ventriculitis.

OBJECTIVE: This study aimed to examine whether changes in intracranial pressure (ICP) waveform morphologies can be used as a biomarker for early detection of ventriculitis. METHODS: Consecutive patients (N = 1653) were prospectively enrolled in a hemorrhage outcomes study from 2006 to 2018. Of these, 435 patients (26%) required external ventricular drains (EVDs) and 76 (17.5% of those with EVDs) had ventriculitis treated with antibiotics. Nineteen patients (25% of those with ventriculitis) showed culture-positive cerebrospinal fluid (CSF) and were included in the present analysis. CSF was routinely cultured three times per week and additionally if infection was suspected. EVDs were left open for drainage, with ICP assessed hourly by clamping. Using wavelet analysis, we extracted uninterrupted segments of ICP waveforms. We extracted dominant pulses from continuous high-resolution data, using morphological clustering analysis of intracranial pressure (MOCAIP). Then we applied k-means clustering, using the dynamic time warping distance to obtain morphologically similar groupings. Finally, metaclusters and further-split clusters (when equipoise existed) were categorized for broad comparison by clinician consensus. RESULTS: We extracted 275,911 dominant pulses from 459.9 h of EVD data. Of these, 112,898 pulses (40.9%) occurred before culture positivity, 41,300 pulses (15.0%) occurred during culture positivity, and 121,713 pulses (44.1%) occurred after it. K-means identified 20 clusters, which were further grouped into metaclusters: tri-/biphasic, single-peak, and artifactual waveforms. Prior to ventriculitis, 61.8% of dominant pulses were tri-/biphasic; this percentage reduced to 22.6% during ventriculitis and 28.4% after it (p < 0.0001). One day before the first positive cultures were collected, the distribution of metaclusters changed to include more single-peak and artifactual ICP waveforms (p < 0.0001). CONCLUSION: The distribution of ICP waveform morphology changes significantly prior to clinical diagnosis of ventriculitis and may be a potential biomarker.

Heart Rate Variability as a Biomarker of Neurocardiogenic Injury After Subarachnoid Hemorrhage.

BACKGROUND: The objective of this study was to examine whether heart rate variability (HRV) measures can be used to detect neurocardiogenic injury (NCI). METHODS: Three hundred and twenty-six consecutive admissions with aneurysmal subarachnoid hemorrhage (SAH) met criteria for the study. Of 326 subjects, 56 (17.2%) developed NCI which we defined by wall motion abnormality with ventricular dysfunction on transthoracic echocardiogram or cardiac troponin-I > 0.3 ng/mL without electrocardiogram evidence of coronary artery insufficiency. HRV measures (in time and frequency domains, as well as nonlinear technique of detrended fluctuation analysis) were calculated over the first 48 h. We applied longitudinal multilevel linear regression to characterize the relationship of HRV measures with NCI and examine between-group differences at baseline and over time. RESULTS: There was decreased vagal activity in NCI subjects with a between-group difference in low/high frequency ratio (ß 3.42, SE 0.92, p = 0.0002), with sympathovagal balance in favor of sympathetic nervous activity. All time-domain measures were decreased in SAH subjects with NCI. An ensemble machine learning approach translated these measures into a classification tool that demonstrated good discrimination using the area under the receiver operating characteristic curve (AUROC 0.82), the area under precision recall curve (AUPRC 0.75), and a correct classification rate of 0.81. CONCLUSIONS: HRV measures are significantly associated with our label of NCI and a machine learning approach using features derived from HRV measures can classify SAH patients that develop NCI.

Predicting delayed cerebral ischemia after subarachnoid hemorrhage using physiological time series data.

To develop and validate a prediction model for delayed cerebral ischemia (DCI) after subarachnoid hemorrhage (SAH) using a temporal unsupervised feature engineering approach, demonstrating improved precision over standard features. 488 consecutive SAH admissions from 2006 to 2014 to a tertiary care hospital were included. Models were trained on 80%, while 20% were set aside for validation testing. Baseline information and standard grading scales were evaluated: age, sex, Hunt Hess grade, modified Fisher Scale (mFS), and Glasgow Coma Scale (GCS). An unsupervised approach applying random kernels was used to extract features from physiological time series (systolic and diastolic blood pressure, heart rate, respiratory rate, and oxygen saturation). Classifiers (Partial Least Squares, linear and kernel Support Vector Machines) were trained on feature subsets of the derivation dataset. Models were applied to the validation dataset. The performances of the best classifiers on the validation dataset are reported by feature subset. Standard grading scale (mFS): AUC 0.58. Combined demographics and grading scales: AUC 0.60. Random kernel derived physiologic features: AUC 0.74. Combined baseline and physiologic features with redundant feature reduction: AUC 0.77. Current DCI prediction tools rely on admission imaging and are advantageously simple to employ. However, using an agnostic and computationally inexpensive learning approach for high-frequency physiologic time series data, we demonstrated that our models achieve higher classification accuracy.

Morphologically constrained spectral unmixing by dictionary learning for multiplex fluorescence microscopy.

MOTIVATION: Current spectral unmixing methods for multiplex fluorescence microscopy have a limited ability to cope with high spectral overlap as they only analyze spectral information over individual pixels. Here, we present adaptive Morphologically Constrained Spectral Unmixing (MCSU) algorithms that overcome this limitation by exploiting morphological differences between sub-cellular structures, and their local spatial context. RESULTS: The proposed method was effective at improving spectral unmixing performance by exploiting: (i) a set of dictionary-based models for object morphologies learned from the image data; and (ii) models of spatial context learned from the image data using a total variation algorithm. The method was evaluated on multi-spectral images of multiplex-labeled pancreatic ductal adenocarcinoma (PDAC) tissue samples. The former constraint ensures that neighbouring pixels correspond to morphologically similar structures, and the latter constraint ensures that neighbouring pixels have similar spectral signatures. The average Mean Squared Error (MSE) and Signal Reconstruction Error (SRE) ratio of the proposed method was 39.6% less and 8% more, respectively, compared to the best of all other algorithms that do not exploit these spatial constraints. AVAILABILITY AND IMPLEMENTATION: Open source software (MATLAB). CONTACT: broysam@central.uh.edu. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Deriving the PRx and CPPopt from 0.2-Hz Data: Establishing Generalizability to Bedmaster Users.

OBJECTIVE: The objective was to explore the validity of industry-parameterized vital signs in the generation of pressure reactivity index (PRx) and optimal cerebral perfusion pressure (CPPopt) values. MATERIALS AND METHODS: Ten patients with intracranial pressure (ICP) monitors from 2008 to 2013 in a tertiary care hospital were included. Arterial blood pressure (ABP) and ICP were sampled at 240 Hz (of waveform data) and 0.2 Hz (of parameterized data produced by heuristic industry proprietary algorithms). 240-Hz ABP were filtered for pulse pressure and diastolic ABP within the limits of 20-150 mmHg. The PRx was calculated as Pearson's correlation coefficient using 10-s averages of ICP and ABP over a 5-min moving window with 80% overlap. For ease of comparison, we used the naming convention of BMx for PRx values derived from 0.2-Hz data. A 5-min median cerebral perfusion pressure (CPP) trend was calculated, PRx or BMx values divided and averaged into CPP bins spanning 5 mmHg. The minimum Y value (PRx or BMx) of the parabolic function fit to the resulting XY plot of 4 h of data was obtained, and updated every 1 min. Pearson's R correlations were calculated for each patient. Linear mixed-effects models were used with a random intercept to assess the overall correlation between the PRx (outcome) and the BMx (fixed effect) or the CPPopt-PRx (outcome) and the CPPopt-BMx (fixed effect). RESULTS: The overall correlation between the PRx and BMx was 0.78 based on the linear mixed effects models (p < 0.0001), and the overall correlation for the CPPopt-PRx and CPPopt-BMx based on the linear mixed effects models was 0.76 (p < 0.0001). One patient had low correlation of CPPopts derived from the PRx vs the BMx; this patient had the least number of hours of CPPopt data to compare. CONCLUSIONS: The BMx shows promise in CPPopt derivation against the validated PRx measure. If further developed, it could expand the capability of centers to derive CPPopt goals for use in clinical trials.

Population-scale three-dimensional reconstruction and quantitative profiling of microglia arbors.

MOTIVATION: The arbor morphologies of brain microglia are important indicators of cell activation. This article fills the need for accurate, robust, adaptive and scalable methods for reconstructing 3-D microglial arbors and quantitatively mapping microglia activation states over extended brain tissue regions. RESULTS: Thick rat brain sections (100-300 µm) were multiplex immunolabeled for IBA1 and Hoechst, and imaged by step-and-image confocal microscopy with automated 3-D image mosaicing, producing seamless images of extended brain regions (e.g. 5903 × 9874 × 229 voxels). An over-complete dictionary-based model was learned for the image-specific local structure of microglial processes. The microglial arbors were reconstructed seamlessly using an automated and scalable algorithm that exploits microglia-specific constraints. This method detected 80.1 and 92.8% more centered arbor points, and 53.5 and 55.5% fewer spurious points than existing vesselness and LoG-based methods, respectively, and the traces were 13.1 and 15.5% more accurate based on the DIADEM metric. The arbor morphologies were quantified using Scorcioni's L-measure. Coifman's harmonic co-clustering revealed four morphologically distinct classes that concord with known microglia activation patterns. This enabled us to map spatial distributions of microglial activation and cell abundances. AVAILABILITY AND IMPLEMENTATION: Experimental protocols, sample datasets, scalable open-source multi-threaded software implementation (C++, MATLAB) in the electronic supplement, and website (www.farsight-toolkit.org). http://www.farsight-toolkit.org/wiki/Population-scale_Three-dimensional_Reconstruction_and_Quanti-tative_Profiling_of_Microglia_Arbors CONTACT: broysam@central.uh.edu SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Non-invasive pulse arrival time is associated with cardiac index in pediatric heart transplant patients with normal ejection fraction.

Objective.Cardiac Index (CI) is a key physiologic parameter to ensure end organ perfusion in the pediatric intensive care unit (PICU). Determination of CI requires invasive cardiac measurements and is not routinely done at the PICU bedside. To date, there is no gold standard non-invasive means to determine CI. This study aims to use a novel non-invasive methodology, based on routine continuous physiologic data, called Pulse Arrival Time (PAT) as a surrogate for CI in patients with normal Ejection Fraction (EF).Approach.Electrocardiogram (ECG) and photoplethysmogram (PPG) signals were collected from beside monitors at a sampling frequency of 250 samples per second. Continuous PAT, derived from the ECG and PPG waveforms was averaged per patient. Pearson's correlation coefficient was calculated between PAT and CI, PAT and heart rate (HR), and PAT and EF.Main Results.Twenty patients underwent right heart cardiac catheterization. The mean age of patients was 11.7 ± 5.4 years old, ranging from 11 months old to 19 years old, the median age was 13.4 years old. HR in this cohort was 93.8 ± 17.0 beats per minute. The average EF was 54.4 ± 9.6%. The average CI was 3.51 ± 0.72 l min-1m-2, with ranging from 2.6 to 4.77 l min-1m-2. The average PAT was 0.31 ± 0.12 s. Pearson correlation analysis showed a positive correlation between PAT and CI (0.57,p< 0.01). Pearson correlation between HR and CI, and correlation between EF and CI was 0.22 (p= 0.35) and 0.03 (p= 0.23) respectively. The correlation between PAT, when indexed by HR (i.e. PAT × HR), and CI minimally improved to 0.58 (p< 0.01).Significance.This pilot study demonstrates that PAT may serve as a valuable surrogate marker for CI at the bedside, as a non-invasive and continuous modality in the PICU. The use of PAT in clinical practice remains to be thoroughly investigated.