Deep learning model to predict the need for mechanical ventilation using chest X-ray images in hospitalised patients with COVID-19.

OBJECTIVES: There exists a wide gap in the availability of mechanical ventilator devices and their acute need in the context of the COVID-19 pandemic. An initial triaging method that accurately identifies the need for mechanical ventilation in hospitalised patients with COVID-19 is needed. We aimed to investigate if a potentially deteriorating clinical course in hospitalised patients with COVID-19 can be detected using all X-ray images taken during hospitalisation. METHODS: We exploited the well-established DenseNet121 deep learning architecture for this purpose on 663 X-ray images acquired from 528 hospitalised patients with COVID-19. Two Pulmonary and Critical Care experts blindly and independently evaluated the same X-ray images for the purpose of validation. RESULTS: We found that our deep learning model predicted the need for mechanical ventilation with a high accuracy, sensitivity and specificity (90.06%, 86.34% and 84.38%, respectively). This prediction was done approximately 3 days ahead of the actual intubation event. Our model also outperformed two Pulmonary and Critical Care experts who evaluated the same X-ray images and provided an incremental accuracy of 7.24%-13.25%. CONCLUSIONS: Our deep learning model accurately predicted the need for mechanical ventilation early during hospitalisation of patients with COVID-19. Until effective preventive or treatment measures become widely available for patients with COVID-19, prognostic stratification as provided by our model is likely to be highly valuable.

Development and Validation of a Deep Learning Model to Quantify Interstitial Fibrosis and Tubular Atrophy From Kidney Ultrasonography Images.

Importance: Interstitial fibrosis and tubular atrophy (IFTA) is a strong indicator of decline in kidney function and is measured using histopathological assessment of kidney biopsy core. At present, a noninvasive test to assess IFTA is not available. Objective: To develop and validate a deep learning (DL) algorithm to quantify IFTA from kidney ultrasonography images. Design, Setting, and Participants: This was a single-center diagnostic study of consecutive patients who underwent native kidney biopsy at John H. Stroger Jr. Hospital of Cook County, Chicago, Illinois, between January 1, 2014, and December 31, 2018. A DL algorithm was trained, validated, and tested to classify IFTA from kidney ultrasonography images. Of 6135 Crimmins-filtered ultrasonography images, 5523 were used for training (5122 images) and validation (401 images), and 612 were used to test the accuracy of the DL system. Kidney segmentation was performed using the UNet architecture, and classification was performed using a convolution neural network-based feature extractor and extreme gradient boosting. IFTA scored by a nephropathologist on trichrome stained kidney biopsy slide was used as the reference standard. IFTA was divided into 4 grades (grade 1, 0%-24%; grade 2, 25%-49%; grade 3, 50%-74%; and grade 4, 75%-100%). Data analysis was performed from December 2019 to May 2020. Main Outcomes and Measures: Prediction of IFTA grade was measured using the metrics precision, recall, accuracy, and F1 score. Results: This study included 352 patients (mean [SD] age 47.43 [14.37] years), of whom 193 (54.82%) were women. There were 159 patients with IFTA grade 1 (2701 ultrasonography images), 74 patients with IFTA grade 2 (1239 ultrasonography images), 41 patients with IFTA grade 3 (701 ultrasonography images), and 78 patients with IFTA grade 4 (1494 ultrasonography images). Kidney ultrasonography images were segmented with 91% accuracy. In the independent test set, the point estimates for performance matrices showed precision of 0.8927 (95% CI, 0.8682-0.9172), recall of 0.8037 (95% CI, 0.7722-0.8352), accuracy of 0.8675 (95% CI, 0.8406-0.8944), and an F1 score of 0.8389 (95% CI, 0.8098-0.8680) at the image level. Corresponding estimates at the patient level were precision of 0.9003 (95% CI, 0.8644-0.9362), recall of 0.8421 (95% CI, 0.7984-0.8858), accuracy of 0.8955 (95% CI, 0.8589-0.9321), and an F1 score of 0.8639 (95% CI, 0.8228-0.9049). Accuracy at the patient level was highest for IFTA grade 1 and IFTA grade 4. The accuracy (approximately 90%) remained high irrespective of the timing of ultrasonography studies and the biopsy diagnosis. The predictive performance of the DL system did not show significant improvement when combined with baseline clinical characteristics. Conclusions and Relevance: These findings suggest that a DL algorithm can accurately and independently predict IFTA from kidney ultrasonography images.

APOL1 genotype-associated morphologic changes among patients with focal segmental glomerulosclerosis.

BACKGROUND: The G1 and G2 alleles of apolipoprotein L1 (APOL1) are common in the Black population and associated with increased risk of focal segmental glomerulosclerosis (FSGS). The molecular mechanisms linking APOL1 risk variants with FSGS are not clearly understood, and APOL1's natural absence in laboratory animals makes studying its pathobiology challenging. METHODS: In a cohort of 90 Black patients with either FSGS or minimal change disease (MCD) enrolled in the Nephrotic Syndrome Study Network (58% pediatric onset), we used kidney biopsy traits as an intermediate outcome to help illuminate tissue-based consequences of APOL1 risk variants and expression. We tested associations between APOL1 risk alleles or glomerular APOL1 mRNA expression and 83 light- or electron-microscopy traits measuring structural and cellular kidney changes. RESULTS: Under both recessive and dominant models in the FSGS patient subgroup (61%), APOL1 risk variants were significantly correlated (defined as FDR <0.1) with decreased global mesangial hypercellularity, decreased condensation of cytoskeleton, and increased tubular microcysts. No significant correlations were detected in MCD cohort. Independent of risk alleles, glomerular APOL1 expression in FSGS patients was not correlated with morphologic features. CONCLUSIONS: While APOL1-associated FSGS is associated with two risk alleles, both one and two risk alleles are associated with cellular/tissue changes in this study of FSGS patients. Our lack of discovery of a large group of tissue differences in FSGS and no significant difference in MCD may be due to the lack of power but also supports investigating whether machine learning methods may more sensitively detect APOL1-associated changes.

Association Between Early Treatment With Tocilizumab and Mortality Among Critically Ill Patients With COVID-19.

Importance: Therapies that improve survival in critically ill patients with coronavirus disease 2019 (COVID-19) are needed. Tocilizumab, a monoclonal antibody against the interleukin 6 receptor, may counteract the inflammatory cytokine release syndrome in patients with severe COVID-19 illness. Objective: To test whether tocilizumab decreases mortality in this population. Design, Setting, and Participants: The data for this study were derived from a multicenter cohort study of 4485 adults with COVID-19 admitted to participating intensive care units (ICUs) at 68 hospitals across the US from March 4 to May 10, 2020. Critically ill adults with COVID-19 were categorized according to whether they received or did not receive tocilizumab in the first 2 days of admission to the ICU. Data were collected retrospectively until June 12, 2020. A Cox regression model with inverse probability weighting was used to adjust for confounding. Exposures: Treatment with tocilizumab in the first 2 days of ICU admission. Main Outcomes and Measures: Time to death, compared via hazard ratios (HRs), and 30-day mortality, compared via risk differences. Results: Among the 3924 patients included in the analysis (2464 male [62.8%]; median age, 62 [interquartile range {IQR}, 52-71] years), 433 (11.0%) received tocilizumab in the first 2 days of ICU admission. Patients treated with tocilizumab were younger (median age, 58 [IQR, 48-65] vs 63 [IQR, 52-72] years) and had a higher prevalence of hypoxemia on ICU admission (205 of 433 [47.3%] vs 1322 of 3491 [37.9%] with mechanical ventilation and a ratio of partial pressure of arterial oxygen to fraction of inspired oxygen of <200 mm Hg) than patients not treated with tocilizumab. After applying inverse probability weighting, baseline and severity-of-illness characteristics were well balanced between groups. A total of 1544 patients (39.3%) died, including 125 (28.9%) treated with tocilizumab and 1419 (40.6%) not treated with tocilizumab. In the primary analysis, during a median follow-up of 27 (IQR, 14-37) days, patients treated with tocilizumab had a lower risk of death compared with those not treated with tocilizumab (HR, 0.71; 95% CI, 0.56-0.92). The estimated 30-day mortality was 27.5% (95% CI, 21.2%-33.8%) in the tocilizumab-treated patients and 37.1% (95% CI, 35.5%-38.7%) in the non-tocilizumab-treated patients (risk difference, 9.6%; 95% CI, 3.1%-16.0%). Conclusions and Relevance: Among critically ill patients with COVID-19 in this cohort study, the risk of in-hospital mortality in this study was lower in patients treated with tocilizumab in the first 2 days of ICU admission compared with patients whose treatment did not include early use of tocilizumab. However, the findings may be susceptible to unmeasured confounding, and further research from randomized clinical trials is needed.

The longitudinal relationship between patient-reported outcomes and clinical characteristics among patients with focal segmental glomerulosclerosis in the Nephrotic Syndrome Study Network.

BACKGROUND: Understanding the relationship between clinical and patient-reported outcomes (PROs) will help support clinical care and future clinical trial design of novel therapies for focal segmental glomerulosclerosis (FSGS). METHODS: FSGS patients ≥8 years of age enrolled in the Nephrotic Syndrome Study Network completed Patient-Reported Outcomes Measurement Information System PRO measures of health-related quality of life (HRQoL) (children: global health, mobility, fatigue, pain interference, depression, anxiety, stress and peer relationships; adults: physical functioning, fatigue, pain interference, sleep impairment, mental health, depression, anxiety and social satisfaction) at baseline and during longitudinal follow-up for a maximum of 5 years. Linear mixed-effects models were used to determine which demographic, clinical and laboratory features were associated with PROs for each of the eight children and eight adults studied. RESULTS: There were 45 children and 114 adult FSGS patients enrolled that had at least one PRO assessment and 519 patient visits. Multivariable analyses among children found that edema was associated with global health (-7.6 points, P = 0.02) and mobility (-4.2, P = 0.02), the number of reported symptoms was associated with worse depression (-2.7 per symptom, P = 0.009) and anxiety (-2.3, P = 0.02) and the number of emergency room (ER) visits in the prior 6 months was associated with worse mobility (-2.8 per visit, P < 0.001) and fatigue (-2.4, P = 0.03). Multivariable analyses among adults found the number of reported symptoms was associated with worse function in all eight PROMIS measures and the number of ER visits was associated with worse fatigue, pain interference, sleep impairment, depression, anxiety and social satisfaction. Laboratory markers of disease severity (i.e. proteinuria, estimated glomerular filtration rate and serum albumin) did not predict PRO in multivariable analyses, with the single exception of complete remission and better pain interference scores among children (+9.3, P = 0.03). CONCLUSIONS: PROs provide important information about HRQoL for persons with FSGS that is not captured solely by the examination of laboratory-based markers of disease. However, it is critical that instruments capture the patient experience and FSGS clinical trials may benefit from a disease-specific instrument more sensitive to within-patient changes.

Factors Associated With Death in Critically Ill Patients With Coronavirus Disease 2019 in the US.

Importance: The US is currently an epicenter of the coronavirus disease 2019 (COVID-19) pandemic, yet few national data are available on patient characteristics, treatment, and outcomes of critical illness from COVID-19. Objectives: To assess factors associated with death and to examine interhospital variation in treatment and outcomes for patients with COVID-19. Design, Setting, and Participants: This multicenter cohort study assessed 2215 adults with laboratory-confirmed COVID-19 who were admitted to intensive care units (ICUs) at 65 hospitals across the US from March 4 to April 4, 2020. Exposures: Patient-level data, including demographics, comorbidities, and organ dysfunction, and hospital characteristics, including number of ICU beds. Main Outcomes and Measures: The primary outcome was 28-day in-hospital mortality. Multilevel logistic regression was used to evaluate factors associated with death and to examine interhospital variation in treatment and outcomes. Results: A total of 2215 patients (mean [SD] age, 60.5 [14.5] years; 1436 [64.8%] male; 1738 [78.5%] with at least 1 chronic comorbidity) were included in the study. At 28 days after ICU admission, 784 patients (35.4%) had died, 824 (37.2%) were discharged, and 607 (27.4%) remained hospitalized. At the end of study follow-up (median, 16 days; interquartile range, 8-28 days), 875 patients (39.5%) had died, 1203 (54.3%) were discharged, and 137 (6.2%) remained hospitalized. Factors independently associated with death included older age (≥80 vs <40 years of age: odds ratio [OR], 11.15; 95% CI, 6.19-20.06), male sex (OR, 1.50; 95% CI, 1.19-1.90), higher body mass index (≥40 vs <25: OR, 1.51; 95% CI, 1.01-2.25), coronary artery disease (OR, 1.47; 95% CI, 1.07-2.02), active cancer (OR, 2.15; 95% CI, 1.35-3.43), and the presence of hypoxemia (Pao2:Fio2<100 vs ≥300 mm Hg: OR, 2.94; 95% CI, 2.11-4.08), liver dysfunction (liver Sequential Organ Failure Assessment score of 2-4 vs 0: OR, 2.61; 95% CI, 1.30-5.25), and kidney dysfunction (renal Sequential Organ Failure Assessment score of 4 vs 0: OR, 2.43; 95% CI, 1.46-4.05) at ICU admission. Patients admitted to hospitals with fewer ICU beds had a higher risk of death (<50 vs ≥100 ICU beds: OR, 3.28; 95% CI, 2.16-4.99). Hospitals varied considerably in the risk-adjusted proportion of patients who died (range, 6.6%-80.8%) and in the percentage of patients who received hydroxychloroquine, tocilizumab, and other treatments and supportive therapies. Conclusions and Relevance: This study identified demographic, clinical, and hospital-level risk factors that may be associated with death in critically ill patients with COVID-19 and can facilitate the identification of medications and supportive therapies to improve outcomes.

Incidence of, Risk Factors for, and Mortality Associated With Severe Acute Kidney Injury After Gunshot Wound.

Importance: Acute kidney injury increases the risk of mortality in hospitalized patients. However, incidence of severe acute kidney injury (SAKI) and its association with mortality in civilians with gunshot wounds (GSWs) is not known. Objective: To determine the incidence of and risk factors associated with SAKI and acute kidney injury requiring dialysis (AKI-D) after GSWs and the association of SAKI and AKI-D with mortality among civilians in the United States. Design, Setting, and Participants: This retrospective cross-sectional study included civilians with GSW reported to the National Trauma Data Bank between July 1, 2010, and June 30, 2015. Torso GSWs were included in study; GSWs to the head were excluded. The data were analyzed between September and November 2018. Exposure: Civilians with GSW. Main Outcomes and Measures: Incidence of SAKI and AKI-D; association of SAKI and AKI-D with mortality. Results: Most of the 64 059 civilian GSWs affected men (57 431 [89.7%]) and racial/ethnic minorities (36 205 [56.5%] African American individuals; 9681 [15.1%] Hispanic individuals). Incidence of SAKI was 2.3% (1450 of 64 059), and incidence of AKI-D was 0.9% (588 of 64 059). On multivariate analysis, SAKI was associated with older age (odds ratio [OR], 1.02; 95% CI, 1.01-1.02; P < .001), male sex (OR, 1.37; 95% CI, 1.12-1.66; P = .002), diabetes (OR, 1.55; 95% CI, 1.20-2.00; P = .001), hypertension (OR, 1.76; 95% CI, 1.46-2.11; P < .001), Glasgow Coma Scale score (OR, 0.98; 95% CI, 0.96-0.99; P = .002), sepsis (OR, 13.83; 95% CI, 11.77-16.24; P < .001), hollow viscus injury (OR, 2.31; 95% CI, 2.05-2.59; P < .001), and injury severity score (OR, 1.02; 95% CI, 1.01-1.02; P < .001); AKI-D was associated with systolic blood pressure (OR, 0.99; 95% CI, 0.99-1.00; P < .001), sepsis (OR, 1.56; 95% CI, 1.18-2.04; P = .001), and injury severity score (OR, 1.01; 95% CI, 1.01-1.02; P = .001). Mortality was significantly higher in patients with AKI-D (167 of 588 patients [28.4%]) compared with patients with SAKI (172 of 862 [20.0%]) and no SAKI or AKI-D (5521 of 62 609 [8.8%]) (P < .001). Mortality was associated with older age (OR, 1.01; 95% CI, 1.01-1.01; P < .001), systolic blood pressure (OR, 0.997; 95% CI, 0.997-0.998; P < .001), Glasgow Coma Scale score (OR, 0.87; 95% CI, 0.87-0.88; P < .001), SAKI (OR, 2.32; 95% CI, 1.93-2.79; P < .001), AKI-D (OR, 1.46; 95% CI, 1.12-1.90; P < .001), hollow viscus injury (OR, 1.87; 95% CI, 1.76-1.98; P < .001), and higher injury severity score (OR, 1.01; 95% CI, 1.01-1.01; P < .001). After matching for variables except SAKI or AKI-D, patients with SAKI were twice as likely to die than patients without SAKI (320 of 1391 [23.0%] vs 158 of 1391 [11.4%]; P < .001). Conclusions and Relevance: In this cross-sectional study, SAKI among civilians who experienced GSWs was associated with mortality.

Sickle cell disease in central India.

OBJECTIVE: The incidence and the risk factors of sickle cell disease (SCD), vaccinated with Pneumococcal vaccine and on penicillin prophylaxis has not been previously reported in India. METHODS: This prospective hospital based study followed 325 children on penicillin prophylaxis, of which 161 were vaccinated for pneumococci, over 146.84 person years to determine the incidence and determinants of crisis (SCC) and infections. The average age at presentation was 7.05 +/- 3.26 years with male preponderance below 2 years. RESULTS: The main causes for hospitalizations were for blood transfusion, SCC and infections. The incidence of SCC was 1.25 per patient per year and that of infection was 1.38 per person per year. The risk factors for SCC were Mahar caste (p = 0.007) non-compliance (p = 0.000) and protein energy malnutrition (PEM) (p = 0.0015) and for infection were also PEM (p = 0.023), Mahar caste (p = 0.021) and noncompliance (p = 0.001). CONCLUSION: Malnutrition and non-compliance with medication increased the patient's susceptibility to SCC and infections.