Applications of Digital Microscopy and Densely Connected Convolutional Neural Networks for Automated Quantification of Babesia-Infected Erythrocytes.

BACKGROUND: Clinical babesiosis is diagnosed, and parasite burden is determined, by microscopic inspection of a thick or thin Giemsa-stained peripheral blood smear. However, quantitative analysis by manual microscopy is subject to error. As such, methods for the automated measurement of percent parasitemia in digital microscopic images of peripheral blood smears could improve clinical accuracy, relative to the predicate method. METHODS: Individual erythrocyte images were manually labeled as "parasite" or "normal" and were used to train a model for binary image classification. The best model was then used to calculate percent parasitemia from a clinical validation dataset, and values were compared to a clinical reference value. Lastly, model interpretability was examined using an integrated gradient to identify pixels most likely to influence classification decisions. RESULTS: The precision and recall of the model during development testing were 0.92 and 1.00, respectively. In clinical validation, the model returned increasing positive signal with increasing mean reference value. However, there were 2 highly erroneous false positive values returned by the model. Further, the model incorrectly assessed 3 cases well above the clinical threshold of 10%. The integrated gradient suggested potential sources of false positives including rouleaux formations, cell boundaries, and precipitate as deterministic factors in negative erythrocyte images. CONCLUSIONS: While the model demonstrated highly accurate single cell classification and correctly assessed most slides, several false positives were highly incorrect. This project highlights the need for integrated testing of machine learning-based models, even when models in the development phase perform well.

Stress as tool or toxin: physiologic markers and subjective report in neonatal simulation.

BACKGROUND: Cognitive appraisal of stress can influence performance. Increased awareness could facilitate titration to optimal stress levels. This study's primary aim was to investigate whether physiologic variables change with increasingly stressful simulations. Secondary aims include effect of stress on procedural competency and whether individuals recognize their experienced stress. METHODS: This was a single-center, mixed-method, simulation-based study. Participants completed three scenarios requiring resuscitation under increasingly stressful conditions. Wearable biometric devices recorded physiologic parameters. Subjects completed surveys assessing knowledge and perceived stress. Intubation success or failure was noted. Heart rate variability (HRV) analysis was used as a proxy for stress. RESULTS: Twelve participants completed the study. Survey analysis revealed progressive amplification of endorsement of affective states associated with stress. Median low frequency (LF)/high frequency (HF) ratio from scenario 1 (median = 2.29, IQR = 1.97, 3.91) was significantly lower than scenario 2 (median = 4.7, IQR = 2.32, 8.35, p = 0.04) and scenario 3 (median = 4.63, IQR = 2.2, 7.43, p = 0.04). Changes in HRV were noted during all scenarios irrespective of subjective self-assessment of stress. Procedural proficiency suffered during more stressful scenarios. CONCLUSIONS: This study demonstrates alterations in subjective assessment and objective physiologic data in simulations with increasing stress. HRV is useful as a proxy for stress response and does not always correlate with perception.

Blood Utilization and Transfusion Reactions in Pediatric Patients Transfused with Conventional or Pathogen Reduced Platelets.

OBJECTIVES: To assess the safety and efficacy of a Food and Drug Administration-approved pathogen-reduced platelet (PLT) product in children, as ongoing questions regarding their use in this population remain. STUDY DESIGN: We report findings from a quality assurance review of PLT utilization, associated red blood cell transfusion trends, and short-term safety of conventional vs pathogen-reduced PLTs over a 21-month period while transitioning from conventional to pathogen-reduced PLTs at a large, tertiary care hospital. We assessed utilization in neonatal intensive care unit (NICU) patients, infants 0-1 year not in the NICU, and children age 1-18 years (PED). RESULTS: In the 48 hours after an index conventional or pathogen-reduced platelet transfusion, respectively, NICU patients received 1.0 ± 1.4 (n = 91 transfusions) compared with 1.2 ± 1.3 (n = 145) additional platelet doses (P = .29); infants 0-1 year not in the NICU received 2.8 ± 3.0 (n = 125) vs 2.6 ± 2.6 (n = 254) additional platelet doses (P = .57); and PEDs received 0.9 ± 1.6 (n = 644) vs 1.4 ± 2.2 (n = 673) additional doses (P < .001). Time to subsequent transfusion and red cell utilization were similar in every group (P > .05). The number and type of transfusion reactions did not significantly vary based on PLT type and no rashes were reported in NICU patients receiving phototherapy and pathogen-reduced PLTs. CONCLUSIONS: Conventional and pathogen-reduced PLTs had similar utilization patterns in our pediatric populations. A small, but statistically significant, increase in transfusions was noted following pathogen-reduced PLT transfusion in PED patients, but not in other groups. Red cell utilization and transfusion reactions were similar for both products in all age groups.

Health Care and Precision Medicine Research: Analysis of a Scalable Data Science Platform.

BACKGROUND: Health care data are increasing in volume and complexity. Storing and analyzing these data to implement precision medicine initiatives and data-driven research has exceeded the capabilities of traditional computer systems. Modern big data platforms must be adapted to the specific demands of health care and designed for scalability and growth. OBJECTIVE: The objectives of our study were to (1) demonstrate the implementation of a data science platform built on open source technology within a large, academic health care system and (2) describe 2 computational health care applications built on such a platform. METHODS: We deployed a data science platform based on several open source technologies to support real-time, big data workloads. We developed data-acquisition workflows for Apache Storm and NiFi in Java and Python to capture patient monitoring and laboratory data for downstream analytics. RESULTS: Emerging data management approaches, along with open source technologies such as Hadoop, can be used to create integrated data lakes to store large, real-time datasets. This infrastructure also provides a robust analytics platform where health care and biomedical research data can be analyzed in near real time for precision medicine and computational health care use cases. CONCLUSIONS: The implementation and use of integrated data science platforms offer organizations the opportunity to combine traditional datasets, including data from the electronic health record, with emerging big data sources, such as continuous patient monitoring and real-time laboratory results. These platforms can enable cost-effective and scalable analytics for the information that will be key to the delivery of precision medicine initiatives. Organizations that can take advantage of the technical advances found in data science platforms will have the opportunity to provide comprehensive access to health care data for computational health care and precision medicine research.

Mosaic trisomy 15 in a liveborn infant.

With only a small number of cases in the medical literature, mosaic trisomy 15 in liveborn infants is very rare. Despite its rarity, similar features among individuals have been described, including intrauterine growth retardation, craniofacial abnormalities and facial dysmorphisms, cardiac disease, and other organ anomalies. Very few liveborns have survived the first year of life. We report here on a term infant with growth restriction and multiple congenital anomalies who was found to have mosaic trisomy 15. The proband presented with some frequently reported findings such as dysmorphic facies and overlapping fingers, and the uncommon finding of whorled hypopigmentation. Previously unreported findings include abnormal cerebral vasculature and dysplastic kidneys. We add this new phenotypic information to widen the spectrum previously reported and provide a review of the literature to date.

Clinical characteristics and outcomes for 7,995 patients with SARS-CoV-2 infection.

OBJECTIVE: Severe acute respiratory syndrome virus (SARS-CoV-2) has infected millions of people worldwide. Our goal was to identify risk factors associated with admission and disease severity in patients with SARS-CoV-2. DESIGN: This was an observational, retrospective study based on real-world data for 7,995 patients with SARS-CoV-2 from a clinical data repository. SETTING: Yale New Haven Health (YNHH) is a five-hospital academic health system serving a diverse patient population with community and teaching facilities in both urban and suburban areas. POPULATIONS: The study included adult patients who had SARS-CoV-2 testing at YNHH between March 1 and April 30, 2020. MAIN OUTCOME AND PERFORMANCE MEASURES: Primary outcomes were admission and in-hospital mortality for patients with SARS-CoV-2 infection as determined by RT-PCR testing. We also assessed features associated with the need for respiratory support. RESULTS: Of the 28605 patients tested for SARS-CoV-2, 7995 patients (27.9%) had an infection (median age 52.3 years) and 2154 (26.9%) of these had an associated admission (median age 66.2 years). Of admitted patients, 2152 (99.9%) had a discharge disposition at the end of the study period. Of these, 329 (15.3%) required invasive mechanical ventilation and 305 (14.2%) expired. Increased age and male sex were positively associated with admission and in-hospital mortality (median age 80.7 years), while comorbidities had a much weaker association with the risk of admission or mortality. Black race (OR 1.43, 95%CI 1.14-1.78) and Hispanic ethnicity (OR 1.81, 95%CI 1.50-2.18) were identified as risk factors for admission, but, among discharged patients, age-adjusted in-hospital mortality was not significantly different among racial and ethnic groups. CONCLUSIONS: This observational study identified, among people testing positive for SARS-CoV-2 infection, older age and male sex as the most strongly associated risks for admission and in-hospital mortality in patients with SARS-CoV-2 infection. While minority racial and ethnic groups had increased burden of disease and risk of admission, age-adjusted in-hospital mortality for discharged patients was not significantly different among racial and ethnic groups. Ongoing studies will be needed to continue to evaluate these risks, particularly in the setting of evolving treatment guidelines.

Clinical Characteristics and Outcomes for 7,995 Patients with SARS-CoV-2 Infection.

OBJECTIVE: Severe acute respiratory syndrome virus (SARS-CoV-2) has infected millions of people worldwide. Our goal was to identify risk factors associated with admission and disease severity in patients with SARS-CoV-2. DESIGN: This was an observational, retrospective study based on real-world data for 7,995 patients with SARS-CoV-2 from a clinical data repository. SETTING: Yale New Haven Health (YNHH) is a five-hospital academic health system serving a diverse patient population with community and teaching facilities in both urban and suburban areas. POPULATIONS: The study included adult patients who had SARS-CoV-2 testing at YNHH between March 1 and April 30, 2020. MAIN OUTCOME AND PERFORMANCE MEASURES: Primary outcomes were admission and in-hospital mortality for patients with SARS-CoV-2 infection as determined by RT-PCR testing. We also assessed features associated with the need for respiratory support. RESULTS: Of the 28605 patients tested for SARS-CoV-2, 7995 patients (27.9%) had an infection (median age 52.3 years) and 2154 (26.9%) of these had an associated admission (median age 66.2 years). Of admitted patients, 2152 (99.9%) had a discharge disposition at the end of the study period. Of these, 329 (15.3%) required invasive mechanical ventilation and 305 (14.2%) expired. Increased age and male sex were positively associated with admission and in-hospital mortality (median age 80.7 years), while comorbidities had a much weaker association with the risk of admission or mortality. Black race (OR 1.43, 95%CI 1.14-1.78) and Hispanic ethnicity (OR 1.81, 95%CI 1.50-2.18) were identified as risk factors for admission, but, among discharged patients, age-adjusted in-hospital mortality was not significantly different among racial and ethnic groups. CONCLUSIONS: This observational study identified, among people testing positive for SARSCoV-2 infection, older age and male sex as the most strongly associated risks for admission and in-hospital mortality in patients with SARS-CoV-2 infection. While minority racial and ethnic groups had increased burden of disease and risk of admission, age-adjusted in-hospital mortality for discharged patients was not significantly different among racial and ethnic groups. Ongoing studies will be needed to continue to evaluate these risks, particularly in the setting of evolving treatment guidelines.

Elevated midline head positioning of extremely low birth weight infants: effects on cardiopulmonary function and the incidence of periventricular-intraventricular hemorrhage.

OBJECTIVE: Changes in cerebrovascular hemodynamics associated with head position may be important in the pathogenesis of periventricular-intraventricular hemorrhage (PIVH) in premature infants. This study evaluated the effect of elevated midline head positioning on cardiopulmonary function and the incidence of PIVH. STUDY DESIGN: ELBW infants were randomized to FLAT (flat, supine) or ELEV (supine, bed elevated 30 degrees) for 96 h. Cardiopulmonary function, complications of prematurity, and the occurrence of PIVH were documented. RESULTS: Infants were randomized into FLAT (n = 90) and ELEV groups (n = 90). No significant differences were seen in the incidence of BPD or other respiratory complications. The ELEV group developed significantly fewer grade 4 hemorrhages (p = 0.036) and survival to discharge was significantly higher in the ELEV group (p = 0.037). CONCLUSIONS: Managing ELBW infants in an elevated midline head position for the first 4 days of life appears safe and may decrease the likelihood of severe PIVH and improve survival.

Changes in Cerebral Oxygenation in Preterm Infants With Progressive Posthemorrhagic Ventricular Dilatation.

BACKGROUND: Optimal timing of intervention in neonatal progressive posthemorrhagic hydrocephalus is often a difficult decision. Unchecked hydrocephalus can lead to irreversible brain injury through impaired perfusion, while placement of a shunt is not without long-term morbidity. The purpose of this study was to assess the use of near-infrared spectroscopy to measure changes in regional cerebral oxygen saturation as an indicator of cerebral perfusion in infants with progressive posthemorrhagic ventricular dilatation. METHODS: Near-infrared spectroscopy was used to measure regional cerebral oxygen saturation for more than a one-hour period in infants within 24 hours of cranial ultrasound. Simultaneous pulse oximetry was recorded and oxygen extraction was calculated. Ventricular size was measured by ultrasound using the frontal-occipital horn ratio and compared with average oxygen saturation and oxygen extraction. Statistical analysis was done using the Spearman rank test and analysis of variance. RESULTS: Ventricular measurements were made in 20 very low birth weight premature infants with periventricular-intraventricular hemorrhage and 12 infants with normal ultrasound scans. Ventricular dilatation was associated with lower cerebral oxygen saturation and higher oxygen extraction (P < 0.001). Progressive ventricular dilatation was inversely related to changes in cerebral oxygen saturation (P < 0.001). CONCLUSIONS: Progressive posthemorrhagic ventricular dilatation is associated with a significant decrease in cerebral oxygenation and increase in oxygen extraction suggesting a decrease in cerebral perfusion. Near-infrared spectroscopy could potentially provide additional clinical information to assist in determining optimal timing of surgical intervention in preterm infants with progressive ventricular enlargement.