A Machine Learning Approach for Predicting Real-time Risk of Intraoperative Hypotension in Traumatic Brain Injury

BACKGROUND

Traumatic brain injury (TBI) is a major cause of death and disability. Episodes of hypotension are associated with worse TBI outcomes. Our aim was to model the real-time risk of intraoperative hypotension in TBI patients, compare machine learning and traditional modeling techniques, and identify key contributory features from the patient monitor and medical record for the prediction of intraoperative hypotension.

METHODS

The data included neurosurgical procedures in 1005 TBI patients at an academic level 1 trauma center. The clinical event was intraoperative hypotension, defined as mean arterial pressure <65 mm Hg for 5 or more consecutive minutes. Two types of models were developed: one based on preoperative patient-level predictors and one based on intraoperative predictors measured per minute. For each of these models, we took 2 approaches to predict the occurrence of a hypotensive event: a logistic regression model and a gradient boosting tree model.

RESULTS

The area under the receiver operating characteristic curve for the intraoperative logistic regression model was 0.80 (95% confidence interval [CI]: 0.78-0.83), and for the gradient boosting model was 0.83 (95% CI: 0.81-0.85). The area under the precision-recall curve for the intraoperative logistic regression model was 0.16 (95% CI: 0.12-0.20), and for the gradient boosting model was 0.19 (95% CI: 0.14-0.24). Model performance based on preoperative predictors was poor. Features derived from the recent trend of mean arterial pressure emerged as dominantly predictive in both intraoperative models.

CONCLUSIONS

This study developed a model for real-time prediction of intraoperative hypotension in TBI patients, which can use computationally efficient machine learning techniques and a streamlined feature-set derived from patient monitor data.

Anesthesiology Performance Improvement and Reporting Exchange (ASPIRE) Quality Metrics in Patients Undergoing Decompressive Craniectomy and Endoscopic Clot Evacuation after Spontaneous Supratentorial Intracerebral Hemorrhage: A Retrospective Observational Study

BACKGROUND

We report adherence to 6 Anesthesiology Performance Improvement and Reporting Exchange (ASPIRE) quality metrics (QMs) relevant to patients undergoing decompressive craniectomy or endoscopic clot evacuation after spontaneous supratentorial intracerebral hemorrhage (sICH).

METHODS

In this retrospective observational study, we describe adherence to the following ASPIRE QMs: acute kidney injury (AKI-01); mean arterial pressure < 65 mm Hg for less than 15 minutes (BP-03); myocardial injury (CARD-02); treatment of high glucose (> 200 mg/dL, GLU-03); reversal of neuromuscular blockade (NMB-02); and perioperative hypothermia (TEMP-03).

RESULT

The study included 95 patients (70% male) with median (interquartile range) age 55 (47 to 66) years and ICH score 2 (1 to 3) undergoing craniectomy (n=55) or endoscopic clot evacuation (n=40) after sICH. In-hospital mortality attributable to sICH was 23% (n=22). Patients with American Society of Anesthesiologists physical status class 5 (n=16), preoperative reduced glomerular filtration rate (n=5), elevated cardiac troponin (n=21) and no intraoperative labs with high glucose (n=71), those who were not extubated at the end of the case (n=62) or did not receive a neuromuscular blocker given (n=3), and patients having emergent surgery (n=64) were excluded from the analysis for their respective ASPIRE QM based on predetermined ASPIRE exclusion criteria. For the remaining patients, the adherence to ASPIRE QMs were: AKI-01, craniectomy 34%, endoscopic clot evacuation 1%; BP-03, craniectomy 72%, clot evacuation 73%; CARD-02, 100% for both groups; GLU-03, craniectomy 67%, clot evacuation 100%; NMB-02, clot evacuation 79%, and; TEMP-03, clot evacuation 0% with hypothermia.

CONCLUSION

This study found variable adherence to ASPIRE QMs in sICH patients undergoing decompressive craniectomy or endoscopic clot evacuation. The relatively high number of patients excluded from individual ASPIRE metrics is a major limitation.

Explainable machine-learning predictions for the prevention of hypoxaemia during surgery

Although anaesthesiologists strive to avoid hypoxemia during surgery, reliably predicting future intraoperative hypoxemia is not currently possible. Here, we report the development and testing of a machine-learning-based system that, in real time during general anaesthesia, predicts the risk of hypoxemia and provides explanations of the risk factors. The system, which was trained on minute-by-minute data from the electronic medical records of over fifty thousand surgeries, improved the performance of anaesthesiologists when providing interpretable hypoxemia risks and contributing factors. The explanations for the predictions are broadly consistent with the literature and with prior knowledge from anaesthesiologists. Our results suggest that if anaesthesiologists currently anticipate 15% of hypoxemia events, with this system's assistance they would anticipate 30% of them, a large portion of which may benefit from early intervention because they are associated with modifiable factors. The system can help improve the clinical understanding of hypoxemia risk during anaesthesia care by providing general insights into the exact changes in risk induced by certain patient or procedure characteristics.

Risks of Routinely Clamping External Ventricular Drains for Intrahospital Transport in Neurocritically Ill Cerebrovascular Patients

BACKGROUND

Current guidelines recommend routine clamping of external ventricular drains (EVD) for intrahospital transport (IHT). The aim of this project was to describe intracranial hemodynamic complications associated with routine EVD clamping for IHT in neurocritically ill cerebrovascular patients.

METHODS

We conducted a retrospective review of cerebrovascular adult patients with indwelling EVD admitted to the neurocritical care unit (NICU) during the months of September to December 2015 at a tertiary care center. All IHTs from the NICU of the included patients were examined. Main outcomes were incidence and risk factors for an alteration in intracranial pressure (ICP) and cerebral perfusion pressure after IHT.

RESULTS

Nineteen cerebrovascular patients underwent 178 IHTs (79.8 % diagnostic and 20.2 % therapeutic) with clamped EVD. Twenty-one IHTs (11.8 %) were associated with post-IHT ICP ≥ 20 mmHg, and 33 IHTs (18.5 %) were associated with escalation of ICP category. Forty IHTs (26.7 %) in patients with open EVD status in the NICU prior to IHT were associated with IHT complications, whereas no IHT complications occurred in IHTs with clamped EVD status in the NICU. Risk factors for post-IHT ICP ≥ 20 mmHg were IHT for therapeutic procedures (adjusted relative risk [aRR] 5.82; 95 % CI, 1.76-19.19), pre-IHT ICP 15-19 mmHg (aRR 3.40; 95 % CI, 1.08-10.76), pre-IHT ICP ≥ 20 mmHg (aRR 12.94; 95 % CI, 4.08-41.01), and each 1 mL of hourly cerebrospinal fluid (CSF) drained prior to IHT (aRR 1.11; 95 % CI, 1.01-1.23).

CONCLUSIONS

Routine clamping of EVD for IHT in cerebrovascular patients is associated with post-IHT ICP complications. Pre-IHT ICP ≥ 15 mmHg, increasing hourly CSF output, and IHT for therapeutic procedures are risk factors.

Smart Anesthesia Manager™ (SAM)--a real-time decision support system for anesthesia care during surgery

Anesthesia information management systems (AIMS) are being increasingly used in the operating room to document anesthesia care. We developed a system, Smart Anesthesia Manager™ (SAM) that works in conjunction with an AIMS to provide clinical and billing decision support. SAM interrogates AIMS database in near real time, detects issues related to clinical care, billing and compliance, and material waste. Issues and the steps for their resolution are brought to the attention of the anesthesia provider in real time through "pop-up" messages overlaid on top of AIMS screens or text pages. SAM improved compliance to antibiotic initial dose and redose to 99.3 ± 0.7% and 83.9 ± 3.4% from 88.5 ± 1.4% and 62.5 ± 1.6%, respectively. Beta-blocker protocol compliance increased to 94.6 ± 3.5% from 60.5 ± 8.6%. Inadvertent gaps (>15 min) in blood pressure monitoring were reduced to 34 ± 30 min/1000 cases from 192 ± 58 min/1000 cases. Additional billing charge capture of invasive lines procedures worth $144,732 per year and 1,200 compliant records were achieved with SAM. SAM was also able to reduce wastage of inhalation anesthetic agents worth $120,168 per year.

New horizons mapping of Europa and Ganymede

The New Horizons spacecraft observed Jupiter's icy satellites Europa and Ganymede during its flyby in February and March 2007 at visible and infrared wavelengths. Infrared spectral images map H2O ice absorption and hydrated contaminants, bolstering the case for an exogenous source of Europa's "non-ice" surface material and filling large gaps in compositional maps of Ganymede's Jupiter-facing hemisphere. Visual wavelength images of Europa extend knowledge of its global pattern of arcuate troughs and show that its surface scatters light more isotropically than other icy satellites.