Machine Learning Automated Detection of Large Vessel Occlusion From Mobile Stroke Unit Computed Tomography Angiography

Background and Purpose: Prehospital automated large vessel occlusion (LVO) detection in Mobile Stroke Units (MSUs) could accelerate identification and treatment of patients with LVO acute ischemic stroke. Here, we evaluate the performance of a machine learning (ML) model on CT angiograms (CTAs) obtained from 2 MSUs to detect LVO. Methods: Patients evaluated on MSUs in Houston and Los Angeles with out-of-hospital CTAs were identified. Anterior circulation LVO was defined as an occlusion of the intracranial internal carotid artery, middle cerebral artery (M1 or M2), or anterior cerebral artery vessels and determined by an expert human reader. A ML model to detect LVO was trained and tested on independent data sets consisting of in-hospital CTAs and then tested on MSU CTA images. Model performance was determined using area under the receiver-operator curve statistics. Results: Among 68 patients with out-of-hospital MSU CTAs, 40% had an LVO. The most common occlusion location was the middle cerebral artery M1 segment (59%), followed by the internal carotid artery (30%), and middle cerebral artery M2 (11%). Median time from last known well to CTA imaging was 88.0 (interquartile range, 59.5–196.0) minutes. After training on 870 in-hospital CTAs, the ML model performed well in identifying LVO in a separate in-hospital data set of 441 images with area under receiver-operator curve of 0.84 (95% CI, 0.80–0.87). ML algorithm analysis time was under 1 minute. The performance of the ML model on the MSU CTA images was comparable with area under receiver-operator curve 0.80 (95% CI, 0.71–0.89). There was no significant difference in performance between the Houston and Los Angeles MSU CTA cohorts. Conclusions: In this study of patients evaluated on MSUs in 2 cities, a ML algorithm was able to accurately and rapidly detect LVO using prehospital CTA acquisitions.

A Novel Noninvasive Technique for Intracranial Pressure Waveform Monitoring in Critical Care

Background: We validated a new noninvasive tool (B4C) to assess intracranial pressure waveform (ICPW) morphology in a set of neurocritical patients, correlating the data with ICPW obtained from invasive catheter monitoring. Materials and Methods: Patients undergoing invasive intracranial pressure (ICP) monitoring were consecutively evaluated using the B4C sensor. Ultrasound-guided manual internal jugular vein (IJV) compression was performed to elevate ICP from the baseline. ICP values, amplitudes, and time intervals (P2/P1 ratio and time-to-peak [TTP]) between the ICP and B4C waveform peaks were analyzed. Results: Among 41 patients, the main causes for ICP monitoring included traumatic brain injury, subarachnoid hemorrhage, and stroke. Bland–Altman’s plot indicated agreement between the ICPW parameters obtained using both techniques. The strongest Pearson’s correlation for P2/P1 and TTP was observed among patients with no cranial damage (r = 0.72 and 0.85, respectively) to the detriment of those who have undergone craniotomies or craniectomies. P2/P1 values of 1 were equivalent between the two techniques (area under the receiver operator curve [AUROC], 0.9) whereas B4C cut-off 1.2 was predictive of intracranial hypertension (AUROC 0.9, p < 000.1 for ICP > 20 mmHg). Conclusion: B4C provided biometric amplitude ratios correlated with ICPW variation morphology and is useful for noninvasive critical care monitoring.

Towards risk stratification and prediction of disease severity and mortality in COVID-19: Next generation metabolomics for the measurement of host response to COVID-19 infection

This study investigated the association between COVID-19 infection and host metabolic signatures as prognostic markers for disease severity and mortality. We enrolled 82 patients with RT-PCR confirmed COVID-19 infection who were classified as mild, moderate, or severe/critical based upon their WHO clinical severity score and compared their results with 31 healthy volunteers. Data on demographics, comorbidities and clinical/laboratory characteristics were obtained from medical records. Peripheral blood samples were collected at the time of clinical evaluation or admission and tested by quantitative mass spectrometry to characterize metabolic profiles using selected metabolites. The findings in COVID-19 (+) patients reveal changes in the concentrations of glutamate, valeryl-carnitine, and the ratios of Kynurenine/Tryptophan (Kyn/Trp) to Citrulline/Ornithine (Cit/Orn). The observed changes may serve as predictors of disease severity with a (Kyn/Trp)/(Cit/Orn) Receiver Operator Curve (ROC) AUC = 0.95. Additional metabolite measures further characterized those likely to develop severe complications of their disease, suggesting that underlying immune signatures (Kyn/Trp), glutaminolysis (Glutamate), urea cycle abnormalities (Cit/Orn) and alterations in organic acid metabolism (C5) can be applied to identify individuals at the highest risk of morbidity and mortality from COVID-19 infection. We conclude that host metabolic factors, measured by plasma based biochemical signatures, could prove to be important determinants of Covid-19 severity with implications for prognosis, risk stratification and clinical management.

An Integrating of Clinical, Pathological, and Radiomic Approach to Predict the Microsatellite Instability in Rectal Carcinoma

Objective: To develop an integrative model with clinical, pathological, and radiomic characteristics to predict the status of microsatellite instability (MSI) in rectal carcinoma (RC). Methods: A cohort of 788 RCs with 97 high MSI status (MSI-H) and 691 microsatellite stable status (MSS) were enrolled. The clinical and pathological characteristics were recorded. The radiomic features were calculated after segmentation of volume of interests and then patients were divided into the training set and validation set with a random proportion of 7:3. The logistic models of simple clinical characteristics (LM-Clin), pathological characteristics (LM-Patho), and radiomic features (LM-Radio) were constructed to distinguish MSI-H from MSS. The relevant radiomic score was calculated. Finally, a integrative nomogram (LM-Nomo) including significant clinical, pathological characteristics, and radiomics was developed. The area under receiver operator curve (AUC) was calculated to evaluate the efficacy of prediction. Results: The AUC of simple LM-Clin including variables of CEA and hypertension and LM-Patho including characteristics of gross type and lymph node metastasis ratio (LNR) was 0.584 (95%CI, 0.549-0.619) and 0.585 (95%CI, 0.550-0.619), which was lower than that of LM-Radio including 12 radiomic features with AUC of 0.737 (95%CI, 0.675-0.799). The LM-Nomo contained CEA, hypertension, LNR, and radiomic score, and the AUC was 0.757 (95%CI, 0.726-0.787). Conclusion: The AUCs of LM-Clin and LM-Patho were disappointing and lower than that of LM-Radio. The LM-Nomo demonstrated the best performance in predicting MSI-H status.

A Novel Noninvasive Technique for Intracranial Pressure Waveform Monitoring in Critical Care

We validated a new noninvasive tool (B4C) to assess intracranial pressure waveform (ICPW) morphology in a set of neurocritical patients, correlating the data with ICPW obtained from invasive catheter monitoring. Materials and Methods: Patients undergoing invasive intracranial pressure (ICP) monitoring were consecutively evaluated using the B4C sensor. Ultrasound-guided manual internal jugular vein (IJV) compression was performed to elevate ICP from the baseline. ICP values, amplitudes, and time intervals (P2/P1 ratio and time-to-peak [TTP]) between the ICP and B4C waveform peaks were analyzed. Results: Among 41 patients, the main causes for ICP monitoring included traumatic brain injury, subarachnoid hemorrhage, and stroke. Bland-Altman&rsquo;s plot indicated agreement between the ICPW parameters obtained using both techniques. The strongest Pearson&rsquo;s correlation for P2/P1 and TTP was observed among patients with no cranial damage (r = 0.72 and 0.85, respectively) in detriment of those who have undergone craniotomies or craniectomies. P2/P1 values of 1 were equivalent between the two techniques (area under the receiver operator curve [AUROC], 0.9) whereas B4C cut-off 1.2 was predictive of intracranial hypertension (AUROC 0.9, p &lt; 000.1 for ICP &gt; 20 mmHg). Conclusion: B4C provided biometric amplitude ratios correlated with ICPW variation morphology and is useful for noninvasive critical care monitoring.

Circulating proteins to predict adverse COVID-19 outcomes

Predicting COVID-19 severity is difficult, and the biological pathways involved are not fully understood. To approach this problem, we measured 4,701 circulating human protein abundances in two independent cohorts totaling 986 individuals. We then trained prediction models including protein abundances and clinical risk factors to predict adverse COVID-19 outcomes in 417 subjects and tested these models in a separate cohort of 569 individuals. For severe COVID-19, a baseline model including age and sex provided an area under the receiver operator curve (AUC) of 65% in the test cohort. Selecting 92 proteins from the 4,701 unique protein abundances improved the AUC to 88% in the training cohort, which remained relatively stable in the testing cohort at 86%, suggesting good generalizability. Proteins selected from different adverse COVID-19 outcomes were enriched for cytokine and cytokine receptors, but more than half of the enriched pathways were not immune-related. Taken together, these findings suggest that circulating proteins measured at early stages of disease progression are reasonably accurate predictors of adverse COVID-19 outcomes. Further research is needed to understand how to incorporate protein measurement into clinical care.

Machine Learning Applied to Electronic Health Records: Identification of Chemotherapy Patients at High Risk for Preventable Emergency Department Visits and Hospital Admissions

PURPOSE Acute care use (ACU) is a major driver of oncologic costs and is penalized by a Centers for Medicare & Medicaid Services quality measure, OP-35. Targeted interventions reduce preventable ACU; however, identifying which patients might benefit remains challenging. Prior predictive models have made use of a limited subset of the data in the electronic health record (EHR). We aimed to predict risk of preventable ACU after starting chemotherapy using machine learning (ML) algorithms trained on comprehensive EHR data. METHODS Chemotherapy patients treated at an academic institution and affiliated community care sites between January 2013 and July 2019 who met inclusion criteria for OP-35 were identified. Preventable ACU was defined using OP-35 criteria. Structured EHR data generated before chemotherapy treatment were obtained. ML models were trained to predict risk for ACU after starting chemotherapy using 80% of the cohort. The remaining 20% were used to test model performance by the area under the receiver operator curve. RESULTS Eight thousand four hundred thirty-nine patients were included, of whom 35% had preventable ACU within 180 days of starting chemotherapy. Our primary model classified patients at risk for preventable ACU with an area under the receiver operator curve of 0.783 (95% CI, 0.761 to 0.806). Performance was better for identifying admissions than emergency department visits. Key variables included prior hospitalizations, cancer stage, race, laboratory values, and a diagnosis of depression. Analyses showed limited benefit from including patient-reported outcome data and indicated inequities in outcomes and risk modeling for Black and Medicaid patients. CONCLUSION Dense EHR data can identify patients at risk for ACU using ML with promising accuracy. These models have potential to improve cancer care outcomes, patient experience, and costs by allowing for targeted, preventative interventions.

Association between blood carboxyhemoglobin level and bronchopulmonary dysplasia in extremely low birthweight infants

Carboxyhemoglobin (CO-Hb) can be endogenously formed in the presence of oxidative stress and may be elevated in inflammatory lung disease. There is lack of evidence of its relationship with the development of bronchopulmonary dysplasia (BPD) in extremely low birthweight (ELBW) infants. The objective of the study is to evaluate the relationship between blood CO-Hb levels in the first 14 days of life (DOL) in ELBW infants and the development of BPD at 36 weeks postmenstrual age (PMA). This is a retrospective cohort study of 58 ELBW infants born at LAC-USC Medical Center between June 2015 and and June 2019 who survived to 36 weeks PMA. CO-Hb values were collected daily from DOL 1 to DOL 14. BPD definition using the recent 2019 NICHD criteria was used. Multivariate logistic regression was performed to determine the association between blood CO-Hb levels and BPD. Receiver operator curve was used to evaluate the ability of the median fraction of inspired oxygen (FiO2) level used at DOL 11–14 in discriminating absent to mild BPD versus moderate to severe BPD. 58 ELBW infants were included in the study. 24 (41%) were diagnosed with moderate to severe BPD, while 34 (59%) were diagnosed with no to mild BPD. Severity of BPD was fairly discriminated by FiO2 at DOL 11–14, but not with CO-Hb levels at any point within the first 14 DOL. The role and mechanism of CO-Hb production in this population need to be further studied.

Validation of parsimonious prognostic models for patients infected with COVID-19

ObjectivesPredictive studies play important roles in the development of models informing care for patients with COVID-19. Our concern is that studies producing ill-performing models may lead to inappropriate clinical decision-making. Thus, our objective is to summarise and characterise performance of prognostic models for COVID-19 on external data.MethodsWe performed a validation of parsimonious prognostic models for patients with COVID-19 from a literature search for published and preprint articles. Ten models meeting inclusion criteria were either (a) externally validated with our data against the model variables and weights or (b) rebuilt using original features if no weights were provided. Nine studies had internally or externally validated models on cohorts of between 18 and 320 inpatients with COVID-19. One model used cross-validation. Our external validation cohort consisted of 4444 patients with COVID-19 hospitalised between 1 March and 27 May 2020.ResultsMost models failed validation when applied to our institution’s data. Included studies reported an average validation area under the receiver–operator curve (AUROC) of 0.828. Models applied with reported features averaged an AUROC of 0.66 when validated on our data. Models rebuilt with the same features averaged an AUROC of 0.755 when validated on our data. In both cases, models did not validate against their studies’ reported AUROC values.DiscussionPublished and preprint prognostic models for patients infected with COVID-19 performed substantially worse when applied to external data. Further inquiry is required to elucidate mechanisms underlying performance deviations.ConclusionsClinicians should employ caution when applying models for clinical prediction without careful validation on local data.

Study on prediction of arterio-venous fistula maturation by flow mediated dilatation and AVF blood flow

Background: The physiology and pathology of AVF maturation depends on the vessels characteristics and its ability to remodel. Outcome of AVF using flow mediated dilatation (FMD), AVF blood flow and diameter has been studied. Methodology: Present observational study included single stage AVF (both Radiocephalic and Brachiocephalic) in consecutive CKD five patients ( n = 158) prospectively over 1 year. Demographic and Doppler ultrasound parameters of upper limb (for vessel diameter and FMD) at baseline were recorded. Blood flow, diameter and depth of AVF were studied at 2, 6 and 12 weeks and their association with clinical maturation (usage of fistula with two needles for 75% of dialysis sessions during 15 day period) was studied ( n = 129, after excluding lost to followup and expired patients; accordingly cohort was divided in matured ( M) or non-matured (NM) groups. Clinical and radiological parameters between both groups were compared; receiver operator curve (ROC) and correlation of Doppler parameters were analysed. Results: Of 129 AVF, 67.4% were matured and 32.5% non-matured. Mean age was 40 years with male predominance75% in both the groups. The mean arterial diameter for distal (NM = 1.96 ± 0.58 and M = 2.02 ± 0.41) and proximal AVF (NM = 3.37 ± 0.82 and M = 3.36 ± 0.75) was not statistically different in both the groups. The matured fistula group had a mean FMD of 11.67 ± 4.09 as against FMD value of 9.365 ± 3.55 in the failed fistula group ( p value 0.01). For maturation prediction, sensitivity and specificity of blood flow at 2 weeks were 86.2% and 59.5% and at 6 weeks 96.6% and 64.3%, respectively. In multivariate analysis predictors for AVF maturation were FMD (adjusted odds ratio (AOR) = 1.15) and blood flow (AOR = 1.67). Conclusion: Second and Sixth week AVF blood flow was found to be predicting AVF maturation. Higher baseline FMD correlated with the AVF maturation, but not with vessel diameter.