scholarly journals Artificial intelligence matches subjective severity assessment of pneumonia for prediction of patient outcome and need for mechanical ventilation: a cohort study

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Shadi Ebrahimian ◽  
Fatemeh Homayounieh ◽  
Marcio A. B. C. Rockenbach ◽  
Preetham Putha ◽  
Tarun Raj ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Patient Outcome ◽  
Mechanical Ventilation ◽  
Oxygen Saturation ◽  
Laboratory Data ◽  
Qualitative Assessment ◽  
Smoking History ◽  
Lung Edema ◽  
Strong Positive Correlation ◽  
Wbc Count

AbstractTo compare the performance of artificial intelligence (AI) and Radiographic Assessment of Lung Edema (RALE) scores from frontal chest radiographs (CXRs) for predicting patient outcomes and the need for mechanical ventilation in COVID-19 pneumonia. Our IRB-approved study included 1367 serial CXRs from 405 adult patients (mean age 65 ± 16 years) from two sites in the US (Site A) and South Korea (Site B). We recorded information pertaining to patient demographics (age, gender), smoking history, comorbid conditions (such as cancer, cardiovascular and other diseases), vital signs (temperature, oxygen saturation), and available laboratory data (such as WBC count and CRP). Two thoracic radiologists performed the qualitative assessment of all CXRs based on the RALE score for assessing the severity of lung involvement. All CXRs were processed with a commercial AI algorithm to obtain the percentage of the lung affected with findings related to COVID-19 (AI score). Independent t- and chi-square tests were used in addition to multiple logistic regression with Area Under the Curve (AUC) as output for predicting disease outcome and the need for mechanical ventilation. The RALE and AI scores had a strong positive correlation in CXRs from each site (r2 = 0.79–0.86; p < 0.0001). Patients who died or received mechanical ventilation had significantly higher RALE and AI scores than those with recovery or without the need for mechanical ventilation (p < 0.001). Patients with a more substantial difference in baseline and maximum RALE scores and AI scores had a higher prevalence of death and mechanical ventilation (p < 0.001). The addition of patients’ age, gender, WBC count, and peripheral oxygen saturation increased the outcome prediction from 0.87 to 0.94 (95% CI 0.90–0.97) for RALE scores and from 0.82 to 0.91 (95% CI 0.87–0.95) for the AI scores. AI algorithm is as robust a predictor of adverse patient outcome (death or need for mechanical ventilation) as subjective RALE scores in patients with COVID-19 pneumonia.

scholarly journals Computational Simulation to Assess Patient Safety of Uncompensated COVID-19 Two-patient Ventilator Sharing Using the Pulse Physiology Engine

2020 ◽  
Author(s):  
Jeffrey B. Webb ◽  
Aaron Bray ◽  
Philip K. Asare ◽  
Rachel B. Clipp ◽  
Yatin B. Mehta ◽  
...  
Keyword(s):  
Patient Outcome ◽  
Mechanical Ventilation ◽  
Oxygen Saturation ◽  
Saturation Index ◽  
Computational Simulation ◽  
Lung Compliance ◽  
Arterial Oxygen ◽  
Single Patient ◽  
Multiple Patients ◽  
Ventilator Settings

AbstractBackgroundThe COVID-19 pandemic is stretching medical resources internationally, including creating ventilator short-ages that complicate clinical and ethical situations. The possibility of needing to ventilate multiple patients with a single ventilator raises patient health and safety concerns. This simulation study explores patient compatibility and ventilator settings during multi-patient ventilation without the use of flow compensating resistances.MethodsA whole-body computational physiology model was used to simulate each patient on a ventilator. The primary model of a single patient with a dedicated ventilator was augmented to model two patients sharing a single ventilator. A range of ventilator settings and patient characteristics were simulated for paired patients. In addition to mechanical ventilation parameters, the full physiological simulation provides estimates of additional values for oxyhemoglobin saturation, arterial oxygen tension, and other patient parameters.FindingsThese simulations show patient outcome during multi-patient ventilation is most closely correlated to lung compliance, oxygenation index, oxygen saturation index, and endtidal carbon dioxide of individual patients. The simulated patient outcome metrics were satisfactory when the lung compliance difference between two patients was less than 12 cmH2O/mL, and the oxygen saturation index difference was less than 2 mmHg.InterpretationIn resource-limited regions of the world, the COVID-19 pandemic will result in equipment shortages. While single-patient ventilation is preferable, if unavailable, these simulations provide a conceptual framework for clinical patient selection guidelines if ventilator sharing is the only available alternative.FundingKitware employees were internally supported by Kitware. Bucknell and Geisinger participants contributed their time.Research in ContextEvidence before this studyIf numbers of patients requiring mechanical ventilation exceed the number of available ventilators in a surge, shared branched ventilator circuits have been proposed for sharing one ventilator by multiple patients. Only rudimentary laboratory or clinical studies have been reported. Testing over expected ranges of lung-chest wall compliance has not been found. Few clinical experiences of mechanical ventilation parameters employed for COVID-19 patients have been reported.Added value of this studyThe number of possible combinations of ventilation and physiological parameters is very large. Time and resource constraints do not permit conventional research. Computational simulation provides rapid sensitivity evaluation of several factors over a wide range of hypothetical ventilation conditions. Envelopes of evaluated parameters may provide reasonably estimated safety boundaries for clinicians compelled in an emergency surge to employ a poorly characterized practice. A previously well-vetted computational model for ventilation of a single patient by a dedicated ventilator has been modified to model the sharing of a single ventilator by two or more patients. Only pairings of two equally sized 70 kg patients are modeled in this report. These simulations provide estimates of effects on ventilation and blood oxygenation by clinically measurable values using conceivable mismatched patient lung compliance and oxygenation (diffusion and shunt).Implications of all the available evidenceThese estimates are for pressure mode ventilation using a single ventilator shared by branched breathing apparatus for paired patients. Individual patient flow restriction to compensate for compliance mismatch is not considered. Reasonable though arbitrary bounds of acceptable parameters may guide clinicians when determining pairings of patients with different physiological characteristics. Further laboratory testing and clinical experience will be needed to determine the validity or utility of these assessments. Different simulations will be needed for flow-compensated branches, more than two patients, and unmatched body habitus.

scholarly journals Procalcitonin Correlates With but Is Not Superior to Other Diagnostic Markers of Bacterial Pneumonia

2020 ◽  
Author(s):  
Nadia Ayala-Lopez ◽  
David R Peaper ◽  
Roa Harb
Keyword(s):  
Respiratory Tract ◽  
Lower Respiratory Tract ◽  
Bacterial Pneumonia ◽  
Operating Characteristic ◽  
Characteristic Curve ◽  
Laboratory Data ◽  
Chest Imaging ◽  
Wbc Count ◽  
Tract Infections ◽  
Guided Therapy

Abstract Objectives Despite extensive research on procalcitonin (PCT)-guided therapy in lower respiratory tract infections, the association between PCT and bacterial pneumonia remains unclear. Methods We evaluated retrospectively the performance of PCT in patients presenting with lower respiratory tract infection symptoms and grouped by seven diagnoses. All patients had microbial testing, chest imaging, and CBC counts within 1 day of PCT testing. Results Median PCT level in patients diagnosed with bacterial pneumonia was significantly higher than in patients diagnosed with other sources of infections or those not diagnosed with infections. Median PCT levels were not different among patients grouped by type or quantity of pathogen detected. They were significantly higher in patients with higher pathogenicity scores for isolated bacteria, those with abnormal WBC count, and those with chest imaging consistent with bacterial pneumonia. A diagnostic workup that included imaging, WBC count, and Gram stain had an area under the receiver operating characteristic curve of 0.748, and the addition of PCT increased it to 0.778. Conclusions PCT was higher in patients diagnosed with bacterial pneumonia. Less clear is its diagnostic ability to detect bacterial pneumonia over and above imaging and laboratory data routinely available to clinicians.

scholarly journals 1002. Epidemiology of Pneumococcal Bacteremia in a Large Tertiary Center

2018 ◽  
Vol 5 (suppl_1) ◽  
pp. S298-S298
Author(s):  
Aristotle Asis ◽  
Esmeralda Gutierrez-Asis ◽  
Ali Hassoun
Keyword(s):  
Mechanical Ventilation ◽  
Hospital Stay ◽  
The United States ◽  
Morbidity And Mortality ◽  
Hospital Length Of Stay ◽  
Smoking History ◽  
High Morbidity ◽  
Icu Stay ◽  
Pneumococcal Bacteremia ◽  
Tertiary Center

Abstract Background Streptococcus pneumoniae remains an important cause of bacteremia in the United States with high morbidity and mortality despite readily available treatment and vaccines. Increased incidence of bacteremia observed during 2017–2018 season. Methods Retrospective chart review of patients admitted with pneumococcal bacteremia over the last two winter seasons. Demographics, laboratory data, ICU stay, need for ventilation or pressor, comorbidities, and mortality were collected. Results Fifty-three patients enrolled. 62% admitted during 2017–2018. Sixty-six percent white, 60% male, mean BMI 27 (38% had normal BMI). Mean age was 55 years (1–93) (57% &gt; 61). Mean hospital length of stay was 7.8 days (1–30). More than 40% required ICU stay. The use of NPPV, vasopressors, and mechanical ventilation were 6%, 15%, and 17%, respectively. Most common presentation: dyspnea 30% and fever 18%. Smoking history (55%). Eighty percent of these patients had pneumonia. Resistance to penicillin 9% and intermediate susceptibility 6%. Resistance to erythromycin 44% and trimethoprim-sulfamethoxazole 12% which increased during winter 2017 (52% and 12%) compared with winter 2016 (30% and 10%). Only 2% of patients with pneumonia had positive sputum culture for pneumococcus and 62% had positive serum pneumococcal antigen with bacteremia. Positive co-detection of bacterial or viral targets in sputum using Multiplex PCR did not correlate with mortality and hospital stay but they were more likely needed ICU stay, use of vasopressor and mechanical ventilation. 43% of empiric therapy was as recommended by IDSA guidelines. Comparing 2016 vs. 2017 seasons, mortality (15% vs. 6%), hospital stay (9 days vs. 7 days), use of NPPV (5% vs. 6%) mechanical ventilation (15% vs. 18%) and vasopressor (5% vs. 21%). No correlation between influenza infection and bacteremia. Overall 6-month mortality and re-admission rate was 9% and 2%, respectively. Mortality was higher in overweight patients (60% vs. 20%), non-smokers (40% vs. 20%), coronary artery disease (40%) and congestive heart failure (40%). Conclusion Pneumococcal bacteremia cause significant morbidity and mortality, we observed less mortality and hospital stay, but more use of NPPV, mechanical ventilation, and vasopressor during 2017–2018 season which had widespread influenza like activity. Disclosures All authors: No reported disclosures.

scholarly journals Revered but Poorly Understood: A Case Report of Dendroaspis polylepis (Black Mamba) Envenomation in Watamu, Malindi Kenya, and a Review of the Literature

2018 ◽  
Vol 3 (3) ◽  
pp. 104 ◽  
Author(s):  
Valentine Erulu ◽  
Mitchel Okumu ◽  
Francis Ochola ◽  
Joseph Gikunju
Keyword(s):  
Mechanical Ventilation ◽  
Oxygen Saturation ◽  
South African ◽  
Artificial Ventilation ◽  
Clinical Course ◽  
Clinical Manifestations ◽  
Hemodynamic Instability ◽  
Rapid Onset ◽  
Sub Saharan Africa ◽  
Sub Saharan

The black mamba (Dendroaspis polylepis) ranks consistently as one of the most revered snakes in sub-Saharan Africa. It has potent neurotoxic venom, and envenomation results in rapid onset and severe clinical manifestations. This report describes the clinical course and reversal of effects of black mamba envenomation in a 13-year-old boy in the Jimba area of Malindi. The victim presented to Watamu Hospital, a low resource health facility with labored breathing, frothing at the mouth, severe ptosis and pupils non-responsive to light. His blood pressure was unrecordable, heart rate was 100 beats per minute but thready, his temperature was 35.5 °C, and oxygen saturation was 83%. Management involved suction to clear salivary secretions, several hours of mechanical ventilation via ambu-bagging, oxygen saturation monitoring, and the use of South African Vaccine Producers (SAVP) polyvalent antivenom. Subcutaneous adrenaline was used to stave off anaphylaxis. The victim went into cardiac arrest on two occasions and chest compressions lasting 3–5 min was used to complement artificial ventilation. Hemodynamic instability was corrected using IV infusion of ringers lactate and normal saline (three liters over 24 h). Adequate mechanical ventilation and the use of specific antivenom remain key in the management of black mamba envenomation.

scholarly journals Study on Guillain-Barré Syndrome in A Tertiary Level Military Hospital

2021 ◽  
Vol 16 (2) ◽  
pp. 44-46
Author(s):  
Md Helal Uddin ◽  
ATM Humayun Kabir ◽  
Md Ismail Chowdhury ◽  
Farzana Zafreen
Keyword(s):  
Mechanical Ventilation ◽  
Electrophysiological Study ◽  
Laboratory Data ◽  
Guillain Barre Syndrome ◽  
Military Hospital ◽  
Upper Respiratory Tract ◽  
Intravenous Immunoglobulin Therapy ◽  
Number Of Patients ◽  
Guillain Barré Syndrome ◽  
Guillain Barré

Introduction: Guillain-Barre Syndrome (GBS) is an acute, frequently severe and fulminant polyradiculopathy that is autoimmune in nature and that causes acute neuromascular failure. The condition is quite common in Bangladesh. GBS is an autoimmune and post-infectious immune disease. Objectives: To see the different presentation and outcome of GBS in combined military hospital (CMH) Dhaka. Materials and Methods: This was a retrospective observational study conducted on all the GBS patients admitted in the Neurology Ward of CMH Dhaka from January 2005 to July 2010. Total 25 patients clinical and laboratory data including CSF analysis, electrophysiological study data were collected from patients’ case sheet. Results: Among the 25 GBS patients male was 22 (88%) and female 03(12%) and most common age group affected was 31-40 years comprising of 09(36%) patients. The most common types of GBS patients were acute inflammatory demyelinating polyneuropathy (AIDP) 17(68%) patients and 10(40%) patients were found to have history of upper respiratory tract infection (URTI). Albuminocytological dissociation was found in 20(80%) patients in CSF study. Intravenous immunoglobulin therapy was given to 13(52%) patients, of them 09(36%) patient needed mechanical ventilation; rest 12(48%) patients were treated conservatively. The final outcome was full recovery 22(88%) patients, 02(8%) patients had residual disability and only one patient died after 2 years of GBS. Conclusion: GBS is an important cause of peripheral neuropathy. Patient should be monitored carefully because a significant number of patients ultimately require mechanical ventilation for respiratory failure which may be of sudden onset. JAFMC Bangladesh. Vol 16, No 2 (December) 2020: 44-46

scholarly journals Artificial intelligence assisted electrocardiography for early diagnosis of thyrotoxic periodic paralysis

2021 ◽  
Author(s):  
Chin Lin ◽  
Chin-Sheng Lin ◽  
Ding-Jie Lee ◽  
Chia-Cheng Lee ◽  
Sy-Jou Chen ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Early Diagnosis ◽  
Validation Cohort ◽  
Laboratory Data ◽  
Diagnostic System ◽  
Periodic Paralysis ◽  
Medical Emergency ◽  
Diagnostic Process ◽  
Routine Laboratory ◽  
Thyrotoxic Periodic Paralysis

Abstract CONTEXT Thyrotoxic periodic paralysis (TPP) characterized by acute weakness, hypokalemia and hyperthyroidism is a medical emergency with a great challenge in early diagnosis since most TPP patients do not have overt symptoms. OBJECTIVE To assess artificial intelligence (AI)-assisted electrocardiography (ECG) combined with routine laboratory data in the early diagnosis of TPP. METHODS A deep learning model (DLM) based on ECG12Net, an 82-layer convolutional neural network, was constructed to detect hypokalemia and hyperthyroidism. The development cohort consisted of 39 ECGs from patients with TPP and 502 ECGs of hypokalemic control; the validation cohort consisted of 11 ECGs of TPP and 36 ECGs of non-TPP with weakness. The AI-ECG based TPP diagnostic process was then consecutively evaluated in 22 male patients with TTP-like features. RESULTS In the validation cohort, the DLM-based ECG system detected all cases of hypokalemia in TPP patients with a mean absolute error of 0.26 mEq/L and diagnosed TPP with an area under curve (AUC) of ~80%, surpassing the best standard ECG parameter (AUC=0.7285 for the QR interval). Combining the AI predictions with the estimated glomerular filtration rate (eGFR) and serum chloride (Cl -) boosted the diagnostic accuracy of the algorithm to AUC 0.986. In the prospective study, the integrated AI and routine laboratory diagnostic system had a PPV of 100% and F-measure 87.5%. CONCLUSIONS An AI-ECG system reliably identifies hypokalemia in patients with paralysis and integration with routine blood chemistries provides valuable decision support for the early diagnosis of TPP.

scholarly journals Obesity and smoking as risk factors for invasive mechanical ventilation in COVID-19: A retrospective, observational cohort study

PLoS ONE ◽  
2020 ◽  
Vol 15 (12) ◽  
pp. e0238552
Author(s):  
Ana C. Monteiro ◽  
Rajat Suri ◽  
Iheanacho O. Emeruwa ◽  
Robert J. Stretch ◽  
Roxana Y. Cortes-Lopez ◽  
...  
Keyword(s):  
Mechanical Ventilation ◽  
Cohort Study ◽  
Smoking Status ◽  
Univariate Analysis ◽  
Invasive Mechanical Ventilation ◽  
Multivariable Analysis ◽  
Observational Cohort Study ◽  
Smoking History ◽  
Observational Cohort ◽  
Retrospective Observational Cohort Study

Purpose To describe the trajectory of respiratory failure in COVID-19 and explore factors associated with risk of invasive mechanical ventilation (IMV). Materials and methods A retrospective, observational cohort study of 112 inpatient adults diagnosed with COVID-19 between March 12 and April 16, 2020. Data were manually extracted from electronic medical records. Multivariable and Univariable regression were used to evaluate association between baseline characteristics, initial serum markers and the outcome of IMV. Results Our cohort had median age of 61 (IQR 45–74) and was 66% male. In-hospital mortality was 6% (7/112). ICU mortality was 12.8% (6/47), and 18% (5/28) for those requiring IMV. Obesity (OR 5.82, CI 1.74–19.48), former (OR 8.06, CI 1.51–43.06) and current smoking status (OR 10.33, CI 1.43–74.67) were associated with IMV after adjusting for age, sex, and high prevalence comorbidities by multivariable analysis. Initial absolute lymphocyte count (OR 0.33, CI 0.11–0.96), procalcitonin (OR 1.27, CI 1.02–1.57), IL-6 (OR 1.17, CI 1.03–1.33), ferritin (OR 1.05, CI 1.005–1.11), LDH (OR 1.57, 95% CI 1.13–2.17) and CRP (OR 1.13, CI 1.06–1.21), were associated with IMV by univariate analysis. Conclusions Obesity, smoking history, and elevated inflammatory markers were associated with increased need for IMV in patients with COVID-19.

scholarly journals An evaluation of toxigenic Clostridioides difficile positivity as a patient outcome metric of antimicrobial stewardship in Saudi Arabia

2021 ◽  
Author(s):  
Christopher A. Okeahialam ◽  
Ali A. Rabaan ◽  
Albert Bolhuis
Keyword(s):  
Patient Outcome ◽  
Saudi Arabia ◽  
Antimicrobial Stewardship ◽  
Laboratory Data ◽  
Hospitalized Patients ◽  
Antimicrobial Stewardship Program ◽  
Repeated Testing ◽  
Clostridioides Difficile ◽  
Stewardship Program ◽  
The Impact

AbstractBackgroundAntimicrobial stewardship has been associated with a reduction in the incidence of health care associated Clostridium difficile infection (HA-CDI). However, CDI remains under-recognized in many low and middle-income countries where clinical and surveillance resources required to identify HA-CDI are often lacking. The rate of toxigenic C. difficile stool positivity in the stool of hospitalized patients may offer an alternative metric for these settings, but its utlity remains largely untested.Aim/ObjectiveTo examine the impact of an antimicrobial stewardship on the rate of toxigenic C. difficile positivity among hospitalized patients presenting with diarrhoeaMethodsA 12-year retrospective review of laboratory data was conducted to compare the rates of toxigenic C. difficile in diarrhoea stool of patients in a hospital in Saudi Arabia, before and after implementation of an antimicrobial stewardship programResultThere was a significant decline in the rate of toxigenic C difficile positivity from 9.8 to 7.4% following the implementation of the antimicrobial stewardship program, and a reversal of a rising trend.DiscussionThe rate of toxigenic C. difficile positivity may be a useful patient outcome metric for evaluating the long term impact of antimicrobial stewardship on CDI, especially in settings with limited surveillance resources. The accuracy of this metric is however dependent on the avoidance of arbitrary repeated testing of a patient for cure, and testing only unformed or diarrhoea stool specimens. Further studies are required within and beyond Saudi Arabia to examine the utility of this metric.

Future of biomarker evaluation in the realm of artificial intelligence algorithms: application in improved therapeutic stratification of patients with breast and prostate cancer

2021 ◽  
pp. jclinpath-2020-207351
Author(s):  
Jenny Fitzgerald ◽  
Debra Higgins ◽  
Claudia Mazo Vargas ◽  
William Watson ◽  
Catherine Mooney ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Artificial Intelligence ◽  
Patient Outcome ◽  
Image Analysis ◽  
High Throughput Screening ◽  
Personalised Medicine ◽  
Digital Pathology ◽  
Disease Stage ◽  
Breast And Prostate Cancer ◽  
Biomarker Evaluation

Clinical workflows in oncology depend on predictive and prognostic biomarkers. However, the growing number of complex biomarkers contributes to costly and delayed decision-making in routine oncology care and treatment. As cancer is expected to rank as the leading cause of death and the single most important barrier to increasing life expectancy in the 21st century, there is a major emphasis on precision medicine, particularly individualisation of treatment through better prediction of patient outcome. Over the past few years, both surgical and pathology specialties have suffered cutbacks and a low uptake of pathology specialists means a solution is required to enable high-throughput screening and personalised treatment in this area to alleviate bottlenecks. Digital imaging in pathology has undergone an exponential period of growth. Deep-learning (DL) platforms for hematoxylin and eosin (H&E) image analysis, with preliminary artificial intelligence (AI)-based grading capabilities of specimens, can evaluate image characteristics which may not be visually apparent to a pathologist and offer new possibilities for better modelling of disease appearance and possibly improve the prediction of disease stage and patient outcome. Although digital pathology and AI are still emerging areas, they are the critical components for advancing personalised medicine. Integration of transcriptomic analysis, clinical information and AI-based image analysis is yet an uncultivated field by which healthcare professionals can make improved treatment decisions in cancer. This short review describes the potential application of integrative AI in offering better detection, quantification, classification, prognosis and prediction of breast and prostate cancer and also highlights the utilisation of machine learning systems in biomarker evaluation.

Sign in / Sign up

Export Citation Format

Share Document