scholarly journals 350. Joint Modeling of EHR and CXR Data to Predict COVID-19 Deterioration

2021 ◽  
Vol 8 (Supplement_1) ◽  
pp. S279-S279
Author(s):  
Emily Mu ◽  
Sarah Jabbour ◽  
Michael Sjoding ◽  
John Guttag ◽  
Jenna Wiens ◽  
...  
Keyword(s):  
Positive Predictive Value ◽  
Predictive Value ◽  
Joint Modeling ◽  
Structured Data ◽  
Low Risk ◽  
X Rays ◽  
Urban Hospital ◽  
Image Model ◽  
Number Of Patients ◽  
Risk Patients

Abstract Background Infectious respiratory-track pathogens are a common trigger of healthcare capacity strain, e.g. the COVID19 pandemic. Patient risk stratification models to identify low-risk patients can help improve patient care processes and allocate limited resources. Many existing deterioration indices are based entirely on structured data from the Electronic Health Record (EHR) and ignore important information from other data sources. However, chest radiographs have been demonstrated to be helpful in predicting the progress of respiratory diseases. We developed a joint EHR and chest x-ray (CXR) model method and applied it to identify low-risk COVID19+ patients within the first 48 hours of hospital admission. Methods All COVID19+ patients admitted to a large urban hospital between March 2020 and February 2021 were included. We trained an image model using large public chest radiograph datasets and fine-tuned this model to predict acute dyspnea using a cohort from the same hospital. We then combined this image model with two existing EHR deterioration indices to predict the risk of a COVID19+ patient being intubated, receiving a nasal cannula, or being treated with a vasopressor. We evaluated models’ ability to identify low-risk patients by using the positive predictive value (PPV). Results The image-augmented deterioration index was able to identify 12% of 716 COVID-19+ patients as low risk with 0.95 positive predictive value in the first 48 hours of admission. In contrast, when used individually, the EHR and CXR models each identified roughly 3% of the patients with a PPV of 0.95. Predicting Low Risk Patients Aggregated predictions for COVID19 positive patients within the first 48 hours of admission, shown with exponential weight moving average and 95% CIs. Each plot shows the number of patients flagged as low-risk by lowest aggregated prediction and the resulting accuracy for that fraction of patients. The bottom plot compares the MCURES fused model to the MCURES model. The top plot compares the EDI fused model to the EDI model. Conclusion Our multi-modal models were able to identify far more patients at low-risk of COVID19 deterioration than models trained on either modality alone. This indicates the importance of combining structured data with chest X-rays when creating a deterioration index performance for infectious respiratory-track diseases. Disclosures All Authors: No reported disclosures

Outcome of Severe Vaso-Occlusive Crisis in Sickle Cell Disease Adults Admitted to Referral Centers in Africa and Europe. Introduction of Machine Learning Methods to Improve the Presev Score

Blood ◽  
2020 ◽  
Vol 136 (Supplement 1) ◽  
pp. 14-15
Author(s):  
Yamna Ouchtar ◽  
Christian Kassasseya ◽  
Kene Sekou ◽  
Anne-Laure Pham Hung D'Alexandry D'Orengiani ◽  
Mehdi Kellaf ◽  
...  
Keyword(s):  
Machine Learning ◽  
Sickle Cell Disease ◽  
Decision Tree ◽  
Predictive Value ◽  
Research Funding ◽  
Low Risk ◽  
Cell Disease ◽  
Risk Patients ◽  
Decision Tree Method ◽  
Tree Method

Introduction: Sickle Cell Disease (SCD) is one of the most common genetic disease worldwide. The Acute Chest Syndrome (ACS) is a leading cause of death for SCD patients. The PRESEV1 study was set to produce a predictive score to assess the risk of an ACS development (Bartolucci et al., 2016). PRESEV2 was an international, multicenter prospective confirmatory study to validate the PRESEV score. This study aims at improving these predictions with the addition of a machine learning (ML) method. Patients and methods: Included patients follow PRESEV1 and PRESEV2 studies 'rules. The dataset thus contains 97 patients who developed an ACS episode (18.3%) against 434 patients who did not (81.7%). To compute the PRESEV score, we firstly used the method developed previously with the following variables as input: leukocytes, reticulocytes, hemoglobin levels and cervical spine pain. This method is based on a decision tree with fixed rules and is referred to as the decision tree method throughout this abstract. Secondly we used a ML method using a combined sampling method named SMOTEENN to balance the data and a C-Support Vector Classification (SVC) with fixed parameters to predict the score. This method produces a probability, with a threshold of 0.2, under which the patient is predicted to declare an ACS. We considered the dataset composed of PRESEV1 dataset and 80 percent of PRESEV2 with a randomly choice. The test dataset is thus composed of the remaining 20 percent of PRESEV2. This technique of random choice allowed us to use a 50-cross-validation and compute with Python an average score and a standard deviation (std). In order to allow comparison of the developed score with or without the addition of the ML method, rates were calculated by adding the weight of ACS representation in the dataset. Results: Among all parameters analyzed, the SVC method considered the following variables for calculation of the score: leukocytes, LDH, urea, reticulocytes and hemoglobin levels. A hundred and two adult patients with a severe VOC requiring hospitalization were included. Out of this pool of patients, 26 (25.5%) were predicted with a low risk of developing an ACS episode (SVC method). Sensibility and specificity were of 94.7% and 26.8%, respectfully. The negative predictive value (NPV) was of 95.8% and the positive predictive value (PPV) of 22.4%. Results are resumed in table 1. When compared to the PRESEV score (decision tree method), 44 patients out of 372 were identified with a low risk score (11.8%), Discussion and Conclusion: While the addition of a ML method did not allow the improvement of the sensibility or the NPV of the PRESEV score, it improved both the specificity and the PPV. The addition of artificial intelligence thus provides a better prediction with a higher percentage of "low-risk" patients. As highlighted in the international PRESEV study, this score could represent a useful tool for physicians in hospital settings, with limited beds. While the PRESEV score could allow a better management of "low risk" patients on one side, the identification of "high-risk" patients could also represent a serious advantage to physicians, as it could improve the feasibility of clinical trials for the prevention of this lethal complication in SCD patients. Disclosures Bartolucci: Innovhem: Other; Novartis: Research Funding; Roche: Consultancy; Bluebird: Consultancy; Emmaus: Consultancy; Bluebird: Research Funding; Addmedica: Research Funding; AGIOS: Consultancy; Fabre Foundation: Research Funding; Novartis: Consultancy; ADDMEDICA: Consultancy; HEMANEXT: Consultancy; GBT: Consultancy.

A validated risk model for early neutropenic events in older cancer patients receiving systemic chemotherapy

2007 ◽  
Vol 25 (18_suppl) ◽  
pp. 9036-9036 ◽  
Author(s):  
M. Shayne ◽  
E. Culakova ◽  
D. C. Dale ◽  
M. S. Poniewierski ◽  
D. A. Wolff ◽  
...  
Keyword(s):  
Cancer Patients ◽  
Predictive Value ◽  
Risk Model ◽  
Low Risk ◽  
Severe Neutropenia ◽  
Validation Dataset ◽  
Cancer Type ◽  
C Statistic ◽  
Risk Patients ◽  
Older Cancer Patients

9036 Background: A prospective, nationwide study was undertaken to develop and validate a risk model for early neutropenic events (NE) in older cancer patients undergoing chemotherapy. Methods: 1,386 patients =65 years of age with lung, breast, colorectal, ovarian cancer or lymphoma were prospectively registered at 117 randomly selected sites. Data on up to 4 cycles were collected upon initiation of chemotherapy. A logistic regression model for cycle 1 NE consisting of febrile neutropenia (FN; fever/infection and absolute neutrophil count nadir <1x109/L) or severe neutropenia (SN; neutrophils <.5x109/L) was derived on 1,378 patients with available data. Validation was performed using a split sample random selection process. Results: No significant differences in distribution of NE or predictive factors were observed between derivation dataset (n=922) and validation dataset (n=464). Major independent baseline clinical risk factors for cycle 1 NE in the derivation model (DM) included: anthracycline based regimens (p<.001), non-chemotherapy immune-modulatory agents (p=.003), elevated bilirubin (p=.016), reduced glomerular filtration rate (p<.001), cancer type (p=.02), planned relative dose intensity =85% (p=.027), and regimens containing cyclophosphamide (p<.001), etoposide (p=.002) or ifosfamide (p=.032). Reduced risk of cycle 1 NE was associated with myeloid growth factor (MGF) prophylaxis (p<.001). DM R2 was 0.478 and c-statistic 0.88 [95% CI 0.86–0.91; p<.001]. At median predicted risk of cycle 1 NE of 7%, model test performance (MTP) showed: sensitivity 90%; specificity 59%; and predictive value positive and negative of 32% and 97%, respectively. Cycle 1–4 FN risk in the DM was 16.6% and 3.3% among high and low risk patients, respectively. The validation model (VM) R2 was 0.508 and c-statistic 0.89 [95% CI: 0.86–0.93; p<.001]. MTP in the VM demonstrated: sensitivity 90%; specificity 65%; predictive value positive and negative of 36% and 97%, respectively. Cycle 1–4 FN risk in the VM was 16.8% and 1.6% in high and low risk patients, respectively. Conclusions: This validated risk model demonstrated good discrimination between older cancer patients at decreased risk for NE, and those at increased risk who may benefit from targeted prophylaxis with MGF. No significant financial relationships to disclose.

scholarly journals Improved HLA-based prediction of coeliac disease identifies two novel HLA risk modifiers, DQ6.2 and DQ7.3

2019 ◽  
Author(s):  
Michael Erlichster ◽  
Justin Bedo ◽  
Efstratios Skafidas ◽  
Patrick Kwan ◽  
Adam Kowalczyk ◽  
...  
Keyword(s):  
Positive Predictive Value ◽  
Coeliac Disease ◽  
Risk Score ◽  
Predictive Value ◽  
State Of The Art ◽  
Clinical Work ◽  
Hla Typing ◽  
Nucleotide Polymorphisms ◽  
Risk Models ◽  
Number Of Patients

AbstractPurposeHuman Leukocyte Antigen (HLA) testing is useful in the clinical work-up of coeliac disease (CD), with high negative but low positive predictive value. We construct a genomic risk score (GRS) using HLA risk loci to improve CD prediction and guide exclusion criteria.MethodsImputed HLA genotypes for five European CD case-control GWAS (n>15,000) were used to construct and validate an HLA based risk models (HDQ15). Conditioning on this score, we identified novel HLA interactions which modified CD risk, and integrated these novel alleles into a new risk score (HDQ17).ResultsA GRS from HLA risk allele genotypes yields performance equivalent to a state-of-the-art GRS (GRS228) using 228 single nucleotide polymorphisms (SNPs) and significantly improves upon all previous HLA based risk models. Conditioning on this model, we find two novel associations, HLA-DQ6.2 and HLA-DQ7.3, that interact significantly with HLA-DQ2.5 (p = 2.51 × 10−9, 1.99 × 10−7 for DQ6.2 and DQ7.3 respectively). These epistatic interactions yield the best performing risk score (HDQ17) which retains performance when implemented using 6 tag SNPs. Using the HDQ17 model, the positive predictive value of CD testing in high risk populations increases from 17.5% to 27.1% while maintaining a negative predictive value above 99%.ConclusionOur proposed HLA-based GRS achieves state-of-the-art risk prediction, helps elucidate further risk factors and improves HLA typing exclusionary criteria, which may reduce the number of patients requiring unnecessary endoscopies.

Case Definitions for Paediatric AIDS: The Zambian Experience

1993 ◽  
Vol 4 (2) ◽  
pp. 83-85 ◽  
Author(s):  
C Chintu ◽  
A Malek ◽  
M Nyumbu ◽  
C Luo ◽  
J Masona ◽  
...  
Keyword(s):  
Positive Predictive Value ◽  
Predictive Value ◽  
Clinical Case ◽  
Case Definition ◽  
World Health ◽  
Who Criteria ◽  
Number Of Patients ◽  
Definition Of ◽  
Hiv 1 ◽  
Clinical Case Definition

For the purpose of surveillance of the acquired immunodeficiency syndrome (AIDS) in developing countries, the World Health Organization (WHO) has recommended criteria for the clinical case definition of AIDS in adults and children. In a preliminary examination of children in Zambia a number of patients with obvious AIDS did not fit the published WHO case definition for paediatric AIDS. Based on this the Zambia National AIDS Surveillance Committee designed local criteria for the clinical case definition of paediatric AIDS. We compared the Zambian criteria with the WHO criteria for the diagnosis of paediatric AIDS by studying 134 consecutively admitted children to one of the paediatric wards at the University Teaching Hospital in Lusaka. Twenty-nine of the patients were HIV-1 seropositive and 105 were HIV-1 seronegative. Among the 29 HIV-seropositive patients, the Zambian criteria identified 23, and the WHO criteria identified 20 children as having AIDS. The 105 HIV-seronegative children were classified as having AIDS in 9 cases by the Zambian criteria and in 38 cases by the WHO criteria. These results give the Zambian criteria for the diagnosis of AIDS a sensitivity of 79.3%, a specificity of 91.4% and a positive predictive value of 86.8% compared to a sensitivity of 69%, specificity of 64% and a positive predictive value of 38% for the WHO criteria. The current WHO criteria are inadequate for the diagnosis of paediatric AIDS. The need to refine the WHO criteria for the diagnosis of paediatric AIDS is discussed.

Screening for Thyroid Dysfunction in 1st Trimester of Pregnancy

2016 ◽  
Vol 8 (2) ◽  
pp. 154-156
Author(s):  
Bharath Ramji ◽  
Kavitha Karthikeyan ◽  
Prabha Swaminathan ◽  
Amrita Priscilla Nalini ◽  
Annie Thatheus
Keyword(s):  
High Risk ◽  
Thyroid Dysfunction ◽  
Strong Association ◽  
Thyroid Stimulating Hormone ◽  
Low Risk ◽  
Routine Screening ◽  
High Risk Patients ◽  
Number Of Patients ◽  
Risk Patients ◽  
In Pregnancy

ABSTRACT This study was done to find the prevalence of newly diagnosed thyroid dysfunction in early pregnancy in patients attending the antenatal clinic and to emphasize the need for routine screening for thyroid dysfunction in pregnancy. Free thyroxine (FT4) and thyroid stimulating hormone (TSH) levels were measured and cut-off levels set at FT4 0.86—1.86 ng/dl, TSH 0.1—2.5 mIU/l in 1st trimester, TSH 0.1—3 mIU/l in 2nd and 3rd trimesters. A total of 956 pregnant women were screened in 1st trimester after excluding patients with known thyroid dysfunction. About 13.2% were diagnosed as hypothyroid and 1.6% as hyperthyroid. Incidence in high-risk patients was 21.7% and in low-risk was 10.4%. High-risk factors have a strong association for hypothyroidism (p < 0.001). Screening only high-risk patients will miss a significant number of patients seen positive in the low-risk group. Hence, it is essential to do routine screening for thyroid dysfunction in pregnancy. How to cite this article Karthikeyan K, Swaminatan P, Nalini AP, Ramji B, Thatheus A. Screening for Thyroid Dysfunction in 1st Trimester of Pregnancy. J South Asian Feder Obst Gynae 2016;8(2):154-156.

Tuberculosis and Tuberculin Quality: Best Intentions, Misleading Results

2001 ◽  
Vol 22 (08) ◽  
pp. 481-484 ◽  
Author(s):  
M. Sigfrido Rangel-Frausto ◽  
Samuel Ponce-de-León-Rosales ◽  
Claudia Martinez-Abaroa ◽  
Kaare Hasløv
Keyword(s):  
Medical Students ◽  
High Risk ◽  
Positive Predictive Value ◽  
Negative Predictive Value ◽  
Predictive Value ◽  
Healthcare Workers ◽  
Low Risk ◽  
University Hospital ◽  
High Risk Population ◽  
Risk Population

Abstract Objective: To compare the performance of three purified protein derivative (PPD) formulations: Tubersol (Connaught); RT23, Statens Serum Institut (SSI); and RT23, Mexico, tested in Mexican populations at low and high risk for tuberculosis (TB). Design: A double-blinded clinical trial. Setting: A university hospital in Mexico City. Participants: The low-risk population was first or second-year medical students with no patient contact; the high-risk population was healthcare workers at a university hospital. Methods: Each of the study subjects received the three different PPD preparations. Risk factors for TB, including age, gender, occupation, bacille Calmette-Guerin (BCG) status, and TB exposure, were recorded. A 0.1-mL aliquot of each preparation was injected in the left and right forearms of volunteers using the Mantoux technique. Blind readings were done 48 to 72 hours later. Sensitivity and specificity were calculated at 10 mm of induration using Tubersol as the reference standard. The SSI tested the potency of the different PPD preparations in previously sensitized guinea pigs. Results: The low-risk population had a prevalence of positive PPD of 26%. In the low-risk population, RT23 prepared in Mexico, compared to the 5 TU of Tubersol, had a sensitivity of 51%, a specificity of 100%, a positive predictive value of 100%, and a negative predictive value of 86%. The RT23 prepared at the SSI had a sensitivity of 69%, a specificity of 99%, a positive predictive value of 95%, and a negative predictive value of 90%. In the high-risk population, the prevalence of positive PPD was 57%. The RT23 prepared in Mexico had a sensitivity of 33%, a specificity of 100%, and a positive predictive value of 53%; the RT23 prepared at the SSI had a sensitivity of 91%, a specificity of 98%, a positive predictive value of 98%, and a negative predictive value of 89%. RT23 used in Mexico had a potency of only 23% of that of the control. There was no statistical association among those with a positive PPD, irrespective of previous BCG vaccination (relative risk, 0.97; 95% confidence interval, 0.76-1.3; P=.78). Conclusions: Healthcare workers had twice the prevalence of positive PPD compared to medical students. RT23 prepared in Mexico had a low sensitivity in both populations compared to 5 TU of Tubersol and RT23 prepared at the SSI. Previous BCG vaccination did not correlate with a positive PPD. Low potency of the RT23 preparation in Mexico was confirmed in guinea pigs. Best intentions in a TB program are not enough if they are not followed by high-quality control.

scholarly journals Identifying High-Cost, High-Risk Patients Using Administrative Databases in Tuscany, Italy

2017 ◽  
Vol 2017 ◽  
pp. 1-12 ◽  
Author(s):  
Irene Bellini ◽  
Valentina Barletta ◽  
Francesco Profili ◽  
Alessandro Bussotti ◽  
Irene Severi ◽  
...  
Keyword(s):  
General Population ◽  
Positive Predictive Value ◽  
Predictive Value ◽  
Incidence Rates ◽  
Adverse Outcomes ◽  
Administrative Databases ◽  
Administrative Database ◽  
Complex Patients ◽  
Risk Patients ◽  
Health Registry

Objective. (1) Assessing the performance of the algorithm in terms of sensitivity and positive predictive value, considering General Practitioners’ (GPs) judgement as benchmark, and (2) describing adverse events (hospitalisation, death, and health services’ consumption) of complex patients compared to the general population. Data Sources. (i) Tuscany administrative database containing health data (2013-5); (ii) lists of complex patients indicated by GPs; and (iii) annual health registry of Tuscany. Study Design. The present study is a validation study. It compares a list of complex patients extracted through an administrative algorithm (criteria of high health consumption) to a gold standard list of patients indicated by GPs. GPs’ decision was subjective but fairly well reasoned. The study compares also adverse outcomes (Emergency Room visits, hospitalisation, and death) between identified complex patients and general population. Principal Findings. Considering GPs’ judgement, the algorithm showed a sensitivity of 72.8% and a positive predictive value of 64.4%. The complex cases presented here have higher incidence rates/100,000 (death 46.8; ER visits 223.2, hospitalisations 110.87, laboratory tests 1284.01, and specialist examinations 870.37) compared to the general population. Conclusions. The final validated algorithm showed acceptable sensitivity and positive predictive value.

scholarly journals Low Eosinophil Count : A Predictor of Inhospital Mortality in a Cohort of Cirrhosis Patients With Sepsis

2021 ◽  
Author(s):  
Anoop KV ◽  
jijo varghese ◽  
krishnadas devadas
Keyword(s):  
Positive Predictive Value ◽  
Negative Predictive Value ◽  
Predictive Value ◽  
Eosinophil Count ◽  
Meld Score ◽  
Inhospital Mortality ◽  
Absolute Eosinophil Count ◽  
High Dependency ◽  
Risk Patients ◽  
Ctp Score

Abstract Background and Aims:Eosinopenia has recently been associated with sepsis. Thus, eosinopenia can be used as a marker of the severity of sepsis and high mortality, which helps in early identification of high risk patients, so better management can be offered to such patients. Aim of the study was to assess whether Absolute Esoinophil Count (AEC) at the time of ICU admission can be used as a predictor of inhospital mortality in cirrhotics.Materials and Methods:This study was a retrospective cohort study. The study population included cirrhosis patients admitted in ICU and High Dependency Unit with sepsis and their absolute eosinophil counts were assessed on the day of hospital admission.Results: A total of 105 patients were enrolled in the study. Among the various parameters analyzed, MELD score, CTP score, Albumin levels, Total count, CRP, ESR, ALT, Bilirubin, Creatinine, Urea, SIRS and Absolute Eosinophil Count(AEC) were statistically significant in predicting the mortality. AUROC of AEC for predicting mortality was 0.881. Cutoff of AEC by Youden’s index was 110 cells/cumm (sensitivity 91.3%, specificity 89%, positive predictive value 87.5% and negative predictive value 93%) in predicting inhospital mortality. MELD AUROC was 0.78 with cut off of > 24 (sensitivity 89%, specificity 74.6%, positive predictive value 73% and negative predictive value 89%) to predict mortality. Conclusion:In critically ill cirrhosis patients, absolute eosinophil count less than 110 cells/cumm can predict inhospital mortality.

Sign in / Sign up

Export Citation Format

Share Document