Machine learning to predict vasopressin responsiveness in patients with septic shock

The premise, promise, and perils of artificial intelligence in critical care cardiology

Artificial intelligence (AI) is an emerging technology with numerous healthcare applications. AI could prove particularly useful in the cardiac intensive care unit (CICU) where its capacity to analyze large datasets in real-time would assist clinicians in making more informed decisions. This systematic review aimed to explore current research on AI as it pertains to the CICU. A PRISMA search strategy was carried out to identify the pertinent literature on topics including vascular access, heart failure care, circulatory support, cardiogenic shock, ultrasound, and mechanical ventilation. Thirty-eight studies were included. Although AI is still in its early stages of development, this review illustrates its potential to yield numerous benefits in the CICU.

Precision fluid and vasoactive drug therapy for critically ill patients

There are several clinical practice guidelines concerning the use of fluid and vasoactive drug therapies in critically ill adult patients, but the recommendations in these guidelines are often based on low-quality evidence. Further, some were compiled prior to the publication of landmark clinical trials, particularly in the comparison of balanced crystalloid and normal saline. An important consideration in the treatment of critically ill patients is the application of precision medicine to provide the most effective care to groups of patients most likely to benefit from the therapy. Although not currently widely integrated into these practice guidelines, the utility of precision medicine in critical illness is a recognized research priority for fluid and vasoactive therapy management. The purpose of this narrative review was to illustrate the evaluation and challenges of providing precision fluid and vasoactive therapies to adult critically ill patients. The review includes a discussion of important investigations published after the release of currently available clinical practice guidelines to provide insight into how recommendations and research priorities may change future guidelines and bedside care for critically ill patients.

Sepsis and acute respiratory failure in patients with cancer: how can we improve care and outcomes even further?

PURPOSE OF REVIEW

Care and outcomes of critically ill patients with cancer have improved over the past decade. This selective review will discuss recent updates in sepsis and acute respiratory failure among patients with cancer, with particular focus on important opportunities to improve outcomes further through attention to phenotyping, predictive analytics, and improved outcome measures.

RECENT FINDINGS

The prevalence of cancer diagnoses in intensive care units (ICUs) is nontrivial and increasing. Sepsis and acute respiratory failure remain the most common critical illness syndromes affecting these patients, although other complications are also frequent. Recent research in oncologic sepsis has described outcome variation - including ICU, hospital, and 28-day mortality - across different types of cancer (e.g., solid vs. hematologic malignancies) and different sepsis definitions (e.g., Sepsis-3 vs. prior definitions). Research in acute respiratory failure in oncology patients has highlighted continued uncertainty in the value of diagnostic bronchoscopy for some patients and in the optimal respiratory support strategy. For both of these syndromes, specific challenges include multifactorial heterogeneity (e.g. in etiology and/or underlying cancer), delayed recognition of clinical deterioration, and complex outcomes measurement.

SUMMARY

Improving outcomes in oncologic critical care requires attention to the heterogeneity of cancer diagnoses, timely recognition and management of critical illness, and defining appropriate ICU outcomes.

Initiating angiotensin II at lower vasopressor doses in vasodilatory shock: an exploratory post-hoc analysis of the ATHOS-3 clinical trial

BACKGROUND

High dose vasopressors portend poor outcome in vasodilatory shock. We aimed to evaluate the impact of baseline vasopressor dose on outcomes in patients treated with angiotensin II (AT II).

METHODS

Exploratory post-hoc analysis of the Angiotensin II for the Treatment of High-Output Shock (ATHOS-3) trial data. The ATHOS-3 trial randomized 321 patients with vasodilatory shock, who remained hypotensive (mean arterial pressure of 55-70 mmHg) despite receiving standard of care vasopressor support at a norepinephrine-equivalent dose (NED) > 0.2 µg/kg/min, to receive AT II or placebo, both in addition to standard of care vasopressors. Patients were grouped into low (≤ 0.25 µg/kg/min; n = 104) or high (> 0.25 µg/kg/min; n = 217) NED at the time of study drug initiation. The primary outcome was the difference in 28-day survival between the AT II and placebo subgroups in those with a baseline NED ≤ 0.25 µg/kg/min at the time of study drug initiation.

RESULTS

Of 321 patients, the median baseline NED in the low-NED subgroup was similar in the AT II (n = 56) and placebo (n = 48) groups (median of each arm 0.21 µg/kg/min, p = 0.45). In the high-NED subgroup, the median baseline NEDs were also similar (0.47 µg/kg/min AT II group, n = 107 vs. 0.45 µg/kg/min placebo group, n = 110, p = 0.75). After adjusting for severity of illness, those randomized to AT II in the low-NED subgroup were half as likely to die at 28-days compared to placebo (HR 0.509; 95% CI 0.274-0.945, p = 0.03). No differences in 28-day survival between AT II and placebo groups were found in the high-NED subgroup (HR 0.933; 95% CI 0.644-1.350, p = 0.71). Serious adverse events were less frequent in the low-NED AT II subgroup compared to the placebo low-NED subgroup, though differences were not statistically significant, and were comparable in the high-NED subgroups.

CONCLUSIONS

This exploratory post-hoc analysis of phase 3 clinical trial data suggests a potential benefit of AT II introduction at lower doses of other vasopressor agents. These data may inform design of a prospective trial.

TRIAL REGISTRATION

The ATHOS-3 trial was registered in the clinicaltrials.gov repository (no. NCT02338843). Registered 14 January 2015.

Timing of vasopressin initiation and mortality in patients with septic shock: analysis of the MIMIC-III and MIMIC-IV databases

BACKGROUND

vasopressin is commonly used as a second-line vasopressor for patients with septic shock, but the optimal timing of initiation is uncertain. This study was designed to investigate when vasopressin initiation may be beneficial for 28-day mortality in septic shock patients.

METHODS

This was a retrospective observational cohort study from the MIMIC-III v1.4 and MIMIC-IV v2.0 databases. All adults diagnosed with septic shock according to Sepsis-3 criteria were included. Patients were stratified into two groups based on norepinephrine (NE) dose at the time of vasopressin initiation, defined as the low doses of NE group (NE<0.25 µg/kg/min) and the high doses of NE group (NE ≥ 0.25 µg/kg/min). The primary end-point was 28-day mortality after diagnosis of septic shock. The analysis involved propensity score matching (PSM), multivariable logistic regression, doubly robust estimation, the gradient boosted model, and an inverse probability-weighting model.

RESULTS

A total of 1817 eligible patients were included in our original cohort (613 in the low doses of NE group and 1204 in the high doses of NE group). After 1:1 PSM, 535 patients from each group with no difference in disease severity were included in the analysis. The results showed that vasopressin initiation at low doses of NE was associated with reduced 28-day mortality (odds ratio [OR] 0.660, 95% confidence interval [CI] 0.518-0.840, p < 0.001). Compared with patients in the high doses of NE group, patients in the low doses of NE group received significantly shorter duration of NE, with less intravenous fluid volume on the first day after initiation of vasopressin, more urine on the second day, and longer mechanical ventilation-free days and CRRT-free days. Nevertheless, there were no significant differences in hemodynamic response to vasopressin, duration of vasopressin, and ICU or hospital length of stay.

CONCLUSIONS

Among adults with septic shock, vasopressin initiation when low-dose NE was used was associated with an improvement in 28-day mortality.

Vasopressin Response and Clinical Trajectory in Septic Shock Patients

BACKGROUND

In septic shock, vasopressors aim to improve tissue perfusion and prevent persistent organ dysfunction, a characteristic of chronic critical illness (CCI). Adjunctive vasopressin is often used to decrease catecholamine dosage, but the association of vasopressin response with subsequent patient outcomes is unclear. We hypothesized vasopressin response is associated with favorable clinical trajectory.

METHODS

We included patients with septic shock receiving vasopressin as a catecholamine adjunct in this retrospective cohort study. We defined vasopressin response as a lowering of the catecholamine dose required to maintain mean arterial pressure ≥65 mm Hg, 6 h after vasopressin initiation. Clinical trajectories were adjudicated as early death (ED; death before day 14), CCI (ICU stay ≥14 days with persistent organ dysfunction), or rapid recovery (RR; not meeting ED or CCI criteria). Trajectories were placed on an ordinal scale with ED the worst outcome, CCI next, and RR the best outcome. The association of vasopressin response with clinical trajectory was assessed with multivariable ordinal logistic regression.

RESULTS

In total 938 patients were included; 426 (45.4%) were vasopressin responders. The most frequent trajectory was ED (49.8%), 29.7% developed CCI, and 20.5% had rapid recovery. In survivors to ICU day 14 (those without ED), 59.2% had CCI and 40.8% experienced RR. Compared with vasopressin non-responders, vasopressin responders less frequently experienced ED (42.5% vs. 55.9%) and more frequently experienced RR (24.6% vs. 17.0%; P < 0.01). After controlling for confounders, vasopressin response was independently associated with higher odds of developing a better clinical trajectory (OR 1.63; 95% CI 1.26-2.10). Medical patients most frequently developed ED and survivors more commonly developed CCI than RR; surgical patients developed the three trajectories with similar frequency (P < 0.01).

CONCLUSIONS

Vasopressin responsive status was associated with improved clinical trajectory in septic shock patients. Early vasopressin response is a potential novel prognostic marker for short-term clinical trajectory.