Forecasting algorithms in the ICU.

Despite significant advances in modeling methods and access to large datasets, there are very few real-time forecasting systems deployed in highly monitored environment such as the intensive care unit. Forecasting models may be developed as classification, regression or time-to-event tasks; each could be using a variety of machine learning algorithms. An accurate and useful forecasting systems include several components beyond a forecasting model, and its performance is assessed using end-user-centered metrics. Several barriers to implementation and acceptance persist and clinicians will play an active role in the successful deployment of this promising technology.

Forecasting imminent atrial fibrillation in long-term electrocardiogram recordings.

BACKGROUND: Despite the morbidity associated with acute atrial fibrillation (AF), no models currently exist to forecast its imminent onset. We sought to evaluate the ability of deep learning to forecast the imminent onset of AF with sufficient lead time, which has important implications for inpatient care. METHODS: We utilized the Physiobank Long-Term AF Database, which contains 24-h, labeled ECG recordings from patients with a history of AF. AF episodes were defined as ≥5 min of sustained AF. Three deep learning models incorporating convolutional and transformer layers were created for forecasting, with two models focusing on the predictive nature of sinus rhythm segments and AF epochs separately preceding an AF episode, and one model utilizing all preceding waveform as input. Cross-validated performance was evaluated using area under time-dependent receiver operating characteristic curves (AUC(t)) at 7.5-, 15-, 30-, and 60-min lead times, precision-recall curves, and imminent AF risk trajectories. RESULTS: There were 367 AF episodes from 84 ECG recordings. All models showed average risk trajectory divergence of those with an AF episode from those without ∼15 min before the episode. Highest AUC was associated with the sinus rhythm model [AUC = 0.74; 7.5-min lead time], though the model using all preceding waveform data had similar performance and higher AUCs at longer lead times. CONCLUSIONS: In this proof-of-concept study, we demonstrated the potential utility of neural networks to forecast the onset of AF in long-term ECG recordings with a clinically relevant lead time. External validation in larger cohorts is required before deploying these models clinically.

Measuring Critical Care Unit Performance Using a Postoperative Mechanical Ventilation Quality Metric.

BACKGROUND: Safely minimizing postoperative mechanical ventilation duration after congenital heart surgery could be a cardiac intensive care unit (CICU) quality measure. We aimed to measure CICU performance using duration of postoperative mechanical ventilation and identify organizational factors associated with this metric. METHODS: Observational analysis of 16,848 surgical hospitalizations of patients invasively ventilated on admission from the operating room from 26 Pediatric Cardiac Critical Care Consortium CICUs. We fitted a multivariable model to predict duration of postoperative mechanical ventilation adjusting for pre- and postoperative factors to measure CICU performance accounting for postoperative illness severity. We used our model to calculate observed-to-expected (adjusted) ventilation duration ratios for each CICU, describe variation across CICUs, and characterize outliers based on bias-corrected bootstrap 95% CIs. We explored associations between organizational characteristics and patient-level adjusted ventilation duration by adding these as independent variables to the model. RESULTS: We observed wide variation across CICUs in adjusted ventilation duration ratios, ranging from 0.7 to 1.7. Nine of 26 CICUs had statistically better than expected ventilation duration, while 10 were significantly worse than expected. Organizational characteristics associated with shorter adjusted ventilation duration included mixed (60%-90%) staffing by critical care or anesthesia-trained attendings, lower average attending-to-patient ratio, average CICU daily occupancy 80% to 90%, and greater nurse staffing ratios and experience. CONCLUSIONS: CICU performance in postoperative duration of mechanical ventilation varies widely across Pediatric Cardiac Critical Care Consortium centers. Several potentially modifiable organizational factors are associated with this metric. Taken together, these findings could spur efforts to improve ventilation duration at outlier hospitals.

Prediction of extubation failure in the paediatric cardiac ICU using machine learning and high-frequency physiologic data.

BACKGROUND: Cardiac intensivists frequently assess patient readiness to wean off mechanical ventilation with an extubation readiness trial despite it being no more effective than clinician judgement alone. We evaluated the utility of high-frequency physiologic data and machine learning for improving the prediction of extubation failure in children with cardiovascular disease. METHODS: This was a retrospective analysis of clinical registry data and streamed physiologic extubation readiness trial data from one paediatric cardiac ICU (12/2016-3/2018). We analysed patients' final extubation readiness trial. Machine learning methods (classification and regression tree, Boosting, Random Forest) were performed using clinical/demographic data, physiologic data, and both datasets. Extubation failure was defined as reintubation within 48 hrs. Classifier performance was assessed on prediction accuracy and area under the receiver operating characteristic curve. RESULTS: Of 178 episodes, 11.2% (N = 20) failed extubation. Using clinical/demographic data, our machine learning methods identified variables such as age, weight, height, and ventilation duration as being important in predicting extubation failure. Best classifier performance with this data was Boosting (prediction accuracy: 0.88; area under the receiver operating characteristic curve: 0.74). Using physiologic data, our machine learning methods found oxygen saturation extremes and descriptors of dynamic compliance, central venous pressure, and heart/respiratory rate to be of importance. The best classifier in this setting was Random Forest (prediction accuracy: 0.89; area under the receiver operating characteristic curve: 0.75). Combining both datasets produced classifiers highlighting the importance of physiologic variables in determining extubation failure, though predictive performance was not improved. CONCLUSION: Physiologic variables not routinely scrutinised during extubation readiness trials were identified as potential extubation failure predictors. Larger analyses are necessary to investigate whether these markers can improve clinical decision-making.

Randomized controlled trial comparing the Franseen needle with the Fork-tip needle for EUS-guided fine-needle biopsy.

BACKGROUND AND AIMS: EUS-guided FNA primarily provides cytologic samples. EUS-guided fine-needle biopsy (FNB) with needles that provide histologic specimens may enhance diagnostic yield and facilitate accessory tissue staining. Several different needle designs are currently available and design superiority is unknown. We designed a randomized controlled trial to compare 2 commonly used EUS-FNB needles in their ability to provide histologic tissue samples (primary endpoint) and to reach an accurate diagnosis (secondary endpoint). METHODS: A total of 150 lesions from 134 patients (November 2018 to June 2019) were randomized 1:1 between biopsy with a Franseen needle and a Fork-tip needle. The groups were compared regarding the quality of the tissue samples and diagnostic accuracy. RESULTS: Of 150 lesions, 75 were pancreatic and 75 were other solid lesions in and around the GI tract. There was no statistically significant difference between the Franseen needle and the Fork-tip needle in the yield of adequate histologic samples, 71 of 75 (94.7%) versus 72 of 75 (96%), (P = 1.00), an absolute difference of -1.3% (95% confidence interval [CI], -8.1% to 5.4%). The 2 groups were similar in the diagnostic accuracy of histologic analysis, 64 of 75 (85.3%) versus 68 of 75 (90.7%) (P = .45), absolute difference -5.4% (95% CI, -15.7% to 5%); and in the diagnostic accuracy of combined cytologic and histologic analysis, 65 of 75 (86.7%) versus 69 of 75 (92%) (P = .43), absolute difference -5.3% (95% CI, -15.2% to 4.5%). CONCLUSIONS: There was no significant difference in the performance of the Franseen needle versus the Fork-tip needle. Both needles achieved a high yield of histologic tissue samples and high diagnostic accuracy. (Clinical trial registration number: NCT03672032.).

Influence of Early Extubation Location on Outcomes Following Pediatric Cardiac Surgery.

OBJECTIVES: Early extubation following pediatric cardiac surgery is common, but debate exists whether location affects outcome, with some centers performing routine early extubations in the operating room (odds ratio) and others in the cardiac ICU. We aimed to define early extubation practice variation across hospitals and assess impact of location on hospital length-of-stay and other outcomes. DESIGN: Secondary analysis of the Pediatric Cardiac Critical Care Consortium registry. SETTING: Twenty-eight Pediatric Cardiac Critical Care Consortium hospitals. PATIENTS: Patients undergoing Society of Thoracic Surgeons-European Association for Cardio-Thoracic Surgery mortality category 1-3 operations between August 2014 and February 2018. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: We defined early extubation as extubation less than 6 hours after postoperative admission. Hospitals were categorized based on the proportion of their early extubation patients who underwent an odds ratio extubation. Categories included low- (< 50% of early extubation, n = 12), medium- (50%-90%, n = 8), or high- (> 90%, n = 8) frequency odds ratio early extubation centers. The primary outcome of interest was postoperative hospital length-of-stay. We analyzed 16,594 operations (9,143 early extubation, 55%). Rates of early extubation ranged from 16% to 100% across hospitals. Odds ratio early extubation rates varied from 16% to 99%. Patient characteristics were similar across hospital odds ratio early extubation categories. Early extubation rates paralleled the hospital odds ratio early extubation rates-77% patients underwent early extubation at high-frequency odds ratio extubation centers compared with 39% at low-frequency odds ratio extubation centers (p < 0.001). High- and low-frequency odds ratio early extubation hospitals had similar length-of-stay, cardiac arrest rates, and low mortality. However, high-frequency odds ratio early extubation hospitals used more noninvasive ventilation than low-frequency hospitals (15% vs. 9%; p < 0.01), but had fewer extubation failures (3.6% vs. 4.5%; p = 0.02). CONCLUSIONS: Considerable variability exists in early extubation practices after low- and moderate-complexity pediatric cardiac surgery. In this patient population, hospital length-of-stay did not differ significantly between centers with different early extubation strategies based on location or frequency.

The clinical characteristics of melanoma with BRAF V600R mutation: a case series study.

Currently, several targeted therapy regimens are approved as first-line treatment in V600E/K-mutant advanced and metastatic melanoma. Patients with the third most common pathologic variant in the BRAF gene, V600R, were not included in BRAF/MEK inhibitors clinical trials, so there is lack of information about the clinical characteristics and predictive value of this mutation in systemic therapy of unresectable disease. We retrospectively reviewed clinical BRAF mutation testing results and the records of melanoma patients at the University of Iowa Hospitals and Clinics from 2011 to 2017. DNA from formalin-fixed, paraffin-embedded tumor specimens were sequenced using a next-generation sequencing panel or dye terminator sequencing covering exon 15 of the BRAF gene. The study protocol was approved by the University of Iowa Institutional Review Board. Nine patients (5.3% of 168 cases with BRAF mutation) were found to have the V600R mutation. We report our experience in treatment of seven patients with V600R-mutant melanoma, whose clinical records were available for review. Four patients in our cohort received BRAF inhibitors. Three patients demonstrated partial objective response to BRAF/MEK targeted therapy. V600R-mutant melanoma accounts for a significant number of cases even in single-institution practices. We believe that testing for BRAF-mutation status should include rare variants of this mutation. From our experience, the high rate of ulceration, male predominance and advanced age at diagnosis are features of melanoma with V600R mutation, which are similar to those reported for V600K mutation. We observed objective response to BRAF/MEK inhibitors in three cases with V600R variant.

CYP2C9*2 is associated with indomethacin treatment failure for patent ductus arteriosus.

Aims: To identify clinical andgenetic factors associated with indomethacin treatment failure in preterm neonates with patent ductus arteriosus (PDA). Patients & Methods: This is a multicenter cohort study of 144 preterm infants (22-32 weeks gestational age) at three centers who received at least one treatment course of indomethacin for PDA. Indomethacin failure was defined as requiring subsequent surgical intervention. Results: In multivariate analysis, gestational age (AOR 0.76, 95% CI 0.60-0.96), surfactant use (AOR 9.77, 95% CI 1.15-83.26), and CYP2C9*2 (AOR 3.74; 95% CI 1.34-10.44) were each associated with indomethacin failure. Conclusion: Age, surfactant use, and CYP2C9*2 influence indomethacin treatment outcome in preterm infants with PDA. This combination of clinical and genetic factors may facilitate targeted indomethacin use for PDA.

Extubation Failure Rates After Pediatric Cardiac Surgery Vary Across Hospitals.

OBJECTIVES: Many hospitals aim to extubate children early after cardiac surgery, yet it remains unclear how this practice associates with extubation failure. We evaluated adjusted extubation failure rates and duration of postoperative mechanical ventilation across hospitals and assessed cardiac ICU organizational factors associated with extubation failure. DESIGN: Secondary analysis of the Pediatric Cardiac Critical Care Consortium clinical registry. SETTING: Pediatric Cardiac Critical Care Consortium cardiac ICUs. PATIENTS: Patients with qualifying index surgical procedures from August 2014 to June 2017. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: We modeled hospital-level adjusted extubation failure rates using multivariable logistic regression. A previously validated Pediatric Cardiac Critical Care Consortium model was used to calculate adjusted postoperative mechanical ventilation. Observed-to-expected ratios for both metrics were derived for each hospital to assess performance. Hierarchical logistic regression was used to assess the association between cardiac ICU factors and extubation failure. Overall, 16,052 surgical hospitalizations were analyzed. Predictors of extubation failure (p < 0.05 in final case-mix adjustment model) included younger age, underweight, greater surgical complexity, airway anomaly, chromosomal anomaly/syndrome, longer cardiopulmonary bypass time, and other preoperative comorbidities. Three hospitals were better-than-expected outliers for extubation failure (95% CI around observed-to-expected < 1), and three hospitals were worse-than-expected (95% CI around observed-to-expected > 1). Two hospitals were better-than-expected outliers for both extubation failure and postoperative mechanical ventilation, and three were worse-than-expected for both. No hospital was an outlier in opposite directions. Greater nursing hours per patient day and percent nursing staff with critical care certification were associated with lower odds of extubation failure. Cardiac ICU factors such as fewer inexperienced nurses, greater percent critical care trained attendings, cardiac ICU-dedicated respiratory therapists, and fewer patients per cardiac ICU attending were not associated with lower odds of extubation failure. CONCLUSIONS: We saw no evidence that hospitals trade higher extubation failure rates for shorter duration of postoperative mechanical ventilation after pediatric cardiac surgery. Increasing specialized cardiac ICU nursing hours per patient day may achieve better extubation outcomes and mitigate the impact of inexperienced nurses.

Functionally compromised synovium-derived mesenchymal stem cells in Charcot neuroarthropathy.

Charcot neuroarthropathy (CNA) often presents as a diabetic foot complication. The role of synovial mesenchymal stem cells (syn-MSCs) in the pathogenesis of CNA is unclear. Synovial samples were collected, for isolation of syn-MSCs, from diabetic patients with CNA (n=7) and non-diabetic patients with intra-articular fracture or normal joints (non-CNA; n=7) during foot surgery. The syn-MSCs in the CNA and non-CNA groups were characterized comparatively. The average number of colonies formed in the CNA group was 6±3.5 per half plate (10mm in diameter), while it was 43±21.6 in the non-CNA group (p<0.05). The average size (pixels) of the colonies in the CNA group was smaller than that in the non-CNA group. When the colonies were stratified into high-, medium- and low-density subgroups, colonies in the high-density subgroup of the CNA group were reduced in density. Expression of PPAR-γ, RUNX2, Sox9 and type II collagen by syn-MSCs in the CNA group was decreased during adipogenic, osteogenic and chondrogenic differentiation as compared with the non-CNA group. In conclusion, syn-MSCs in CNA joints were reduced in number, with declined differentiation potentials. The high-density subpopulation of the syn-MSCs was particularly affected by the pathology of CNA.

Immunohistochemical expression of MYB in salivary gland basal cell adenocarcinoma and basal cell adenoma.

BACKGROUND: Basal cell predominant salivary gland neoplasms can be difficult to separate histologically. One of the most aggressive of basaloid salivary gland neoplasms is adenoid cystic carcinoma. MYB expression by immunohistochemistry has been documented in adenoid cystic carcinoma. Some investigators have suggested that using this expression can help in establishing the diagnosis of adenoid cystic carcinoma. Utilizing tissue microarrays, we studied a group of basal cell adenocarcinomas and basal cell adenomas to determine: (i) whether either tumor expressed MYB and (ii) the frequency of any expression in either tumors. METHODS: Seventeen salivary gland basal cell adenocarcinomas and 30 salivary gland basal cell adenomas were used to construct microarrays. These tissue microarrays were used to assess for immunohistochemical MYB expression. RESULTS: Fifty-three percent (nine of 17) of salivary gland basal cell adenocarcinomas and 57% (17 of 30) of salivary gland basal cell adenomas showed MYB overexpression. For comparison, we studied 11 adenoid cystic carcinomas for MYB expression and found that 64% (seven of 11) overexpressed MYB. We found no relation to clinical course for basal adenomas or basal cell adenocarcinomas that overexpressed MYB vs those that did not. CONCLUSIONS: MYB expression does not help separate basal cell adenocarcinomas from basal cell adenomas, and our data suggest it does not differentiate between either of these neoplasms and adenoid cystic carcinoma.

Use of a Rapid Ethylene Glycol Assay: a 4-Year Retrospective Study at an Academic Medical Center.

Ethylene glycol (EG) is a common cause of toxic ingestions. Gas chromatography (GC)-based laboratory assays are the gold standard for diagnosing EG intoxication. However, GC requires specialized instrumentation and technical expertise that limits feasibility for many clinical laboratories. The objective of this retrospective study was to determine the utility of incorporating a rapid EG assay for management of cases with suspected EG poisoning. The University of Iowa Hospitals and Clinics core clinical laboratory adapted a veterinary EG assay (Catachem, Inc.) for the Roche Diagnostics cobas 8000 c502 analyzer and incorporated this assay in an osmolal gap-based algorithm for potential toxic alcohol/glycol ingestions. The main limitation is that high concentrations of propylene glycol (PG), while readily identifiable by reaction rate kinetics, can interfere with EG measurement. The clinical laboratory had the ability to perform GC for EG and PG, if needed. A total of 222 rapid EG and 24 EG/PG GC analyses were documented in 106 patient encounters. Of ten confirmed EG ingestions, eight cases were managed entirely with the rapid EG assay. PG interference was evident in 25 samples, leading to 8 GC analyses to rule out the presence of EG. Chart review of cases with negative rapid EG assay results showed no evidence of false negatives. The results of this study highlight the use of incorporating a rapid EG assay for the diagnosis and management of suspected EG toxicity by decreasing the reliance on GC. Future improvements would involve rapid EG assays that completely avoid interference by PG.