scholarly journals Validating a computable phenotype for nephrotic syndrome in children and adults using PCORnet® data

Kidney360 ◽  
2021 ◽  
pp. 10.34067/KID.0002892021
Author(s):  
Andrea L. Oliverio ◽  
Dorota Marchel ◽  
Jonathan P. Troost ◽  
Isabelle Ayoub ◽  
Salem Almaani ◽  
...  
Keyword(s):  
Nephrotic Syndrome ◽  
Language Processing ◽  
Laboratory Data ◽  
Area Under The Curve ◽  
The United States ◽  
Primary Nephrotic Syndrome ◽  
Common Causes ◽  
Icd 10 ◽  
Positive Classification ◽  
Sensitivity Specificity

Background: Primary nephrotic syndromes are rare diseases which impedes adequate sample size for observational patient-oriented research and clinical trial enrollment. A computable phenotype may be powerful in identifying patients with these diseases for research across multiple institutions. Methods: A comprehensive algorithm of inclusion and exclusion ICD-9 and ICD-10 codes to identify patients with primary nephrotic syndrome was developed. The algorithm was executed against the PCORnet® CDM at 3 institutions from Jan 1, 2009 to Jan 1, 2018, where a random selection of 50 cases and 50 non-cases (individuals not meeting case criteria seen within the same calendar year and within five years of age of a case) were reviewed by a nephrologist, for a total of 150 cases and 150 non-cases reviewed. The classification accuracy (sensitivity, specificity, positive and negative predictive value, F1 score) of the computable phenotype was determined. Results: The algorithm identified a total of 2,708 patients with nephrotic syndrome from 4,305,092 distinct patients in the CDM at all sites from 2009-2018. For all sites, the sensitivity, specificity, and area under the curve of the algorithm were 99% (95% CI: 97-99%), 79% (95% CI: 74-85%), and 0.9 (0.84-0.97), respectively. The most common causes of false positive classification were secondary FSGS (9/39) and lupus nephritis (9/39). Conclusion: This computable phenotype had good classification in identifying both children and adults with primary nephrotic syndrome utilizing only ICD-9 and ICD-10 codes, which are available across institutions in the United States. This may facilitate future screening and enrollment for research studies and enable comparative effectiveness research. Further refinements to the algorithm including use of laboratory data or addition of natural language processing may help better distinguish primary and secondary causes of nephrotic syndrome.

scholarly journals 1184. Making Pneumonia Surveillance Easy: Automation of Pneumonia Case Detection

2019 ◽  
Vol 6 (Supplement_2) ◽  
pp. S424-S425
Author(s):  
Dan Ding ◽  
Anna Stachel ◽  
Eduardo Iturrate ◽  
Michael Phillips
Keyword(s):  
Language Processing ◽  
Cost Effective ◽  
The United States ◽  
Surveillance Data ◽  
X Rays ◽  
Healthcare Facilities ◽  
X Ray ◽  
Chest X Ray ◽  
Sensitivity Specificity ◽  
Time Critical

Abstract Background Pneumonia (PNU) is the second most common nosocomial infection in the United States and is associated with substantial morbidity and mortality. While definitions from CDC were developed to increase the reliability of surveillance data, reduce the burden of surveillance in healthcare facilities, and enhance the utility of surveillance data for improving patient safety - the algorithm is still laborious. We propose an implementation of a refined algorithm script which combines two CDC definitions with the use of natural language processing (NLP), a tool which relies on pattern matching to determine whether a condition of interest is reported as present or absent in a report, to automate PNU surveillance. Methods Using SAS v9.4 to write a query, we used a combination of National Healthcare Safety Network’s (NHSN) PNU and ventilator-associated event (VAE) definitions that use discrete fields found in electronic medical records (EMR) and trained an NLP tool to determine whether chest x-ray report was indicative of PNU (Fig1). To validate, we assessed sensitivity/specificity of NLP tool results compared with clinicians’ interpretations. Results The NLP tool was highly accurate in classifying the presence of PNU in chest x-rays. After training the NLP tool, there were only 4% discrepancies between NLP tool and clinicians interpretations of 223 x-ray reports - sensitivity 92.2% (81.1–97.8), specificity 97.1% (93.4–99.1), PPV 90.4% (79.0–96.8), NPV 97.7% (94.1–99.4). Combining the automated use of discrete EMR fields with NLP tool significantly reduces the time spent manually reviewing EMRs. A manual review for PNU without automation requires approximately 10 minutes each day per admission. With a monthly average of 2,350 adult admissions at our hospital and 16,170 patient-days for admissions with at least 2 days, the algorithm saves approximately 2,695 review hours. Conclusion The use of discrete EMR fields with an NLP tool proves to be a timelier, cost-effective yet accurate alternative to manual PNU surveillance review. By allowing an automated algorithm to review PNU, timely reports can be sent to units about individual cases. Compared with traditional CDC surveillance definitions, an automated tool allows real-time critical review for infection and prevention activities. Disclosures All authors: No reported disclosures.

scholarly journals The ACE (Albumin, CRP and Endoscopy) Index in Acute Colitis: A Simple Clinical Index on Admission that Predicts Outcome in Patients With Acute Ulcerative Colitis

2020 ◽  
Author(s):  
Rebecca K Grant ◽  
Gareth-Rhys Jones ◽  
Nikolas Plevris ◽  
Ruairi W Lynch ◽  
Philip W Jenkinson ◽  
...  
Keyword(s):  
Ulcerative Colitis ◽  
Predictive Value ◽  
Laboratory Data ◽  
Area Under The Curve ◽  
Binary Logistic Regression ◽  
High Risk Population ◽  
Second Line ◽  
Second Line Therapy ◽  
Line Therapy ◽  
Icd 10

Abstract Background Intravenous (IV) steroids remain the first-line treatment for patients with acute ulcerative colitis (UC). However, 30% of patients do not respond to steroids, requiring second-line therapy and/or surgery. There are no existing indices that allow physicians to predict steroid nonresponse at admission. We aimed to determine if admission biochemical and endoscopic values could predict response to IV steroids. Methods All admissions for acute UC (ICD-10 K51) between November 1, 2011, and October 31, 2016 were identified. Case note review confirmed diagnosis; clinical, endoscopic, and laboratory data were collected. Steroid response was defined as discharge home with no further therapy for active UC. Nonresponse was defined as requirement for second-line therapy or surgery. Univariate and binary logistic regression analyses were employed to identify factors associated with steroid nonresponse. Results Two hundred and thirty-five acute UC admissions were identified, comprising both acute severe and acute nonsevere UC; 155 of the 235 patients (66.0%) responded to steroids. Admission C-reactive protein (CRP) (P = 0.009, odds ratio [OR] 1.006), albumin (P < 0.001, OR 0.894) and endoscopic severity (P < 0.001, OR 3.166) differed significantly between responders and nonresponders. A simple UC severity score (area under the curve [AUC] 0.754, P < 0.001) was derived from these variables; 78.1% (25 of 32) of patients with concurrent CRP ≥50 mg/L, albumin ≤30 g/L, and increased endoscopic severity (severe on physician’s global assessment) (maximum score = 3) did not respond to IV steroids (positive predictive value [PPV] 78.1%, negative predictive value [NPV] 87.1%). Conclusions More than three quarters of patients scoring 3 (albumin ≤30 g/L, CRP ≥50 mg/L, and increased endoscopic severity) did not respond to IV steroids. This combination of parameters (ACE) identifies on admission a high-risk population who may benefit from earlier second-line medical treatment or surgical intervention.

scholarly journals The prediction of surgical intervention in patients with tubo-ovarian abscess

2020 ◽  
Author(s):  
Jong Ha Hwang ◽  
Bo Wook Kim
Keyword(s):  
Treatment Failure ◽  
Medical Treatment ◽  
Surgical Intervention ◽  
Risk Group ◽  
Laboratory Data ◽  
Intervention Group ◽  
Area Under The Curve ◽  
Wbc Count ◽  
Sensitivity Specificity ◽  
Ovarian Abscess

Abstract Background: The prediction of antibiotic treatment failure is helpful to identify patients with a high likelihood of needing surgical treatment early in patients diagnosed with tubo-ovarian abscess (TOA). The aim of this study was to compare the clinical characteristics of patients with TOA) who responded to medical treatment and those who underwent surgical intervention due to medical treatment failure.Material and Methods: Electronic medical records were evaluated retrospectively to identify patients who were diagnosed with TOA and hospitalized in our obstetrics and gynecology department between March 2014 and June 2019. Demographic, clinical, and laboratory data including white blood cell (WBC) count, erythrocyte sedimentation rate (ESR), and C-reactive protein (CRP) were compared between the medical treatment group and the surgical intervention group. Logistic regression was used to determine the independent predictors of treatment failure.Results: Patient age, TOA diameter, WBC count, CRP, and ESR were significantly different between the groups. On multiple regression analysis, significant correlations were identified between age (p = 0.001), ESR (p = 0.045), and failure of medical treatment. TOA diameter (p = 0.065) showed a borderline association with surgical intervention. The risk group was defined as the combination of factors producing a risk score > 2. The area under the curve (AUC) for the risk group (age >34.3 years, ESR > 45 mm/h, and TOA size > 5.9 cm) was 0.844. The sensitivity, specificity, accuracy, PPV, and NPV were 93.8%, 75%, 83.3%, 75%, and 93.8%, respectively.Conclusions: The risk of needing surgical intervention in TOA patients can be predicted using ESR in addition to age and TOA size as risk factors.

scholarly journals 416 Hyperlipasaemia In an Adult Hospital Population: A Retrospective Audit Demonstrating A High Proportion of Non-Pancreatic Causes of a Diagnostically Raised Lipase

2021 ◽  
Vol 108 (Supplement_6) ◽  
Author(s):  
L Yao ◽  
C Briggs ◽  
P Labib
Keyword(s):  
Acute Pancreatitis ◽  
Roc Analysis ◽  
Area Under The Curve ◽  
Positive Likelihood Ratio ◽  
Specific Test ◽  
Cross Sectional ◽  
Serum Lipase ◽  
Retrospective Audit ◽  
Common Causes ◽  
Sensitivity Specificity

Abstract Introduction Serum lipase is considered to be a more specific test than amylase for acute pancreatitis, and a rise of over three times the laboratory upper limit of normal (ULN) is considered diagnostic. This single-centre retrospective audit assessed the accuracy of a raised lipase in confirming acute pancreatitis. Method All patients with a raised lipase (>78 U/L) admitted over one month were reviewed. Patients whose lipase was measured >48 hours after admission were excluded. Cross-sectional imaging and discharge summaries were reviewed to determine the cause of hyperlipasaemia. Receiver Operator Characteristics (ROC) analysis was performed to determine the most accurate cut-off value for diagnosing acute pancreatitis. Results Ninety-nine patients were included. The most common causes of raised lipase (>78 U/L) were pancreatitis (37%), hepatobiliary (15%), gastroduodenal (8%) and renal (8%) disease. In patients with a lipase >234 U/L (3xULN, n = 46), the most common causes were pancreatitis (70%), drugs (9%), hepatobiliary (9%), gastroduodenal (4%) and renal (4%) disease. ROC analysis showed lipase to have an area under the curve (AUC) of 0.89 (95% CI 0.84-0.96, p < 0.0001). Using the laboratory cut-off of 234 U/L (3xULN), lipase had a sensitivity, specificity, and positive likelihood ratio (PLR) of 86.5%, 77.4% and 3.8. Increasing the lipase cut-off did not improve the specificity without compromising the sensitivity of the test. Conclusions A lipase cut-off of 3xULN is an appropriate cut-off for a biochemical diagnosis of acute pancreatitis. However, up to 30% of patients with lipase values above this cut-off may have alternative diagnoses that should be considered.

scholarly journals The prediction of surgical intervention in patients with tubo-ovarian abscess

2020 ◽  
Author(s):  
Jong Ha Hwang ◽  
Bo Wook Kim
Keyword(s):  
Treatment Failure ◽  
Medical Treatment ◽  
Surgical Intervention ◽  
Risk Group ◽  
Laboratory Data ◽  
Intervention Group ◽  
Area Under The Curve ◽  
Wbc Count ◽  
Sensitivity Specificity ◽  
Ovarian Abscess

Abstract Background: The prediction of antibiotic treatment failure is helpful to identify patients with a high likelihood of needing surgical treatment early in patients diagnosed with tubo-ovarian abscess (TOA). The aim of this study was to compare the clinical characteristics of patients with TOA) who responded to medical treatment and those who underwent surgical intervention due to medical treatment failure. Material and Methods: Electronic medical records were evaluated retrospectively to identify patients who were diagnosed with TOA and hospitalized in our obstetrics and gynecology department between March 2014 and June 2019. Demographic, clinical, and laboratory data including white blood cell (WBC) count, erythrocyte sedimentation rate (ESR), and C-reactive protein (CRP) were compared between the medical treatment group and the surgical intervention group. Logistic regression was used to determine the independent predictors of treatment failure. Results: Patient age, TOA diameter, WBC count, CRP, and ESR were significantly different between the groups. On multiple regression analysis, significant correlations were identified between age ( p = 0.001), ESR ( p = 0.045), and failure of medical treatment. TOA diameter ( p = 0.065) showed a borderline association with surgical intervention. The risk group was defined as the combination of factors producing a risk score > 2. The area under the curve (AUC) for the risk group (age >34.3 years, ESR > 45 mm/h, and TOA size > 5.9 cm) was 0.844. The sensitivity, specificity, accuracy, PPV, and NPV were 93.8%, 75%, 83.3%, 75%, and 93.8%, respectively. Conclusions: The risk of needing surgical intervention in TOA patients can be predicted using ESR in addition to age and TOA size as risk factors.

STEROID THERAPY EFFICACY FOR PRIMARY NEPHROTIC SYNDROME DEBUT IN CHILDREN

2018 ◽  
Vol 97 (5) ◽  
pp. 61-66
Author(s):  
T.L. Nastausheva ◽  
◽  
O.A. Zhdanova ◽  
G.A. Batishcheva ◽  
Yu.N. Chernov ◽  
...  
Keyword(s):  
Nephrotic Syndrome ◽  
Steroid Therapy ◽  
Primary Nephrotic Syndrome ◽  
Therapy Efficacy

Race and Gender

2020 ◽  
pp. 251-269 ◽  
Author(s):  
Timnit Gebru
Keyword(s):  
Machine Learning ◽  
Language Processing ◽  
The United States ◽  
Error Rates ◽  
Political Factors ◽  
Recidivism Rates ◽  
Race And Gender ◽  
Decision Tools ◽  
And Gender ◽  
Technical Solutions

This chapter discusses the role of race and gender in artificial intelligence (AI). The rapid permeation of AI into society has not been accompanied by a thorough investigation of the sociopolitical issues that cause certain groups of people to be harmed rather than advantaged by it. For instance, recent studies have shown that commercial automated facial analysis systems have much higher error rates for dark-skinned women, while having minimal errors on light-skinned men. Moreover, a 2016 ProPublica investigation uncovered that machine learning–based tools that assess crime recidivism rates in the United States are biased against African Americans. Other studies show that natural language–processing tools trained on news articles exhibit societal biases. While many technical solutions have been proposed to alleviate bias in machine learning systems, a holistic and multifaceted approach must be taken. This includes standardization bodies determining what types of systems can be used in which scenarios, making sure that automated decision tools are created by people from diverse backgrounds, and understanding the historical and political factors that disadvantage certain groups who are subjected to these tools.

Sign in / Sign up

Export Citation Format

Share Document