Assessment of the Risk of Venous Thromboembolism in Medical Inpatients using the Padua Prediction Score and Caprini Risk Assessment Model

Objective Inpatients with high risk of venous thromboembolism (VTE) usually face serious threats to their health and economic conditions. Many studies using machine learning (ML) models to predict VTE risk neglected an important statistical phenomenon, "fuzzy feature", and achieved inferior results. Considering the effect of "fuzzy feature", our study aims to develop a VTE risk assessment model suitable for Chinese medical inpatients. Materials and Methods Inpatients in the medical department of Peking Union Medical College Hospital (PUMCH) from January 2014 to June 2016 were collected. A new ML VTE risk assessment model was built through population splitting. First patients were classified into different groups based on values of VTE risk factors, then trustless groups were filtered out, and finally ML models were built on training data in unit of groups. Predictive performances of our method, five traditional ML models, and the Padua model were compared. Results The "fuzzy feature" was verified on the whole dataset. Compared with the Padua model, the proposed model showed higher sensitivities and specificities on training data, and higher specificities and similar sensitivities on test data. Standard deviations of predictive validity of five ML models were larger than the proposed model. Discussion The proposed model was the only one which showed advantages on both sensitivity and specificity over Padua model. Its robustness was better than traditional ML models. Conclusion This study built a population-split-based ML model of VTE for Chinese medical inpatients and it may help clinicians stratify VTE risk and guide prevention more efficiently.

Download Full-text

Potential Overuse of Primary Thromboprophylaxis in Medical Inpatients at Low Risk of Venous Thromboembolism

Blood ◽

10.1182/blood-2019-131827 ◽

2019 ◽

Vol 134 (Supplement_1) ◽

pp. 3385-3385

Author(s):

Mia Djulbegovic ◽

Kevin Chen ◽

Soundari Sureshanand ◽

Sarwat Chaudhry

Keyword(s):

Risk Assessment ◽

Venous Thromboembolism ◽

High Risk ◽

Clinical Pharmacy ◽

Low Risk ◽

Assessment Model ◽

Morbidity And Mortality ◽

Risk Assessment Model ◽

Medical Overuse ◽

Medical Inpatients

Background: Venous thromboembolism (VTE) is a common cause of morbidity and mortality in the United States. Annually, up to 1 in 120 people develop VTE, approximating the incidence of stroke. Given that hospitalization and acute medical illness increase the risk of VTE, hospital-associated VTE represents a preventable cause of morbidity and mortality. Accordingly, accreditation and regulatory agencies endorse inpatient pharmacologic VTE prophylaxis (PPX) as a quality measure. In order to raise rates of PPX prescribing, many health systems have adopted a default approach to electronic ordering, in which clinicians must "opt-out" of PPX prescription. However, this strategy may cause medical overuse and avoidable harms, which has prompted the American Society of Hematology (ASH) to recommend a risk-adapted approach to PPX. One risk model endorsed by ASH is the IMPROVE-VTE risk assessment model, which can identify patients who are at low risk for VTE and therefore may not warrant pharmacologic PPX. We therefore sought to compare the actual practice of PPX prescribing to the guideline-recommended strategy according the IMPROVE-VTE model in a large, contemporary population of medical inpatients. Methods: In this observational study, we used electronic health record data to identify adult, medical inpatients hospitalized on general medical and subspecialty services at Yale-New Haven Hospital from 1/1/14-12/31/18. We excluded patients who were pregnant, admitted for VTE, taking full dose anticoagulation on admission, admitted for bleeding, or had a platelet count of < 50,000/µL. For each patient, we calculated the IMPROVE-VTE score using the previously validated model weights: 3 points for a prior history of VTE; 2 points for known thrombophilia, lower limb paralysis, or active cancer; 1 point for immobilization, admission to the intensive care unit, or age ≥ 60 years. For each component other than age, we used ICD-9 and ICD-10 codes that were billed either prior to or upon admission to determine the presence of these risk factors. In order to simulate the decision to initiate PPX on hospital admission, we calculated each patient's IMPROVE-VTE score at the time of admission. In accordance with the ASH guidelines, we used an IMPROVE-VTE score of <2 to differentiate patients at low-risk of hospital-associated VTE from those at high-risk. We used inpatient medication order history data to determine receipt of pharmacologic PPX. We used χ2 testing to compare the relative frequency of PPX prescribing on admission between patients at low-risk and high-risk for VTE. Results: We identified 135,288 medical inpatients during the study period, of whom 99,380 met inclusion criteria. The average age was 63.5 years-old (standard deviation 18 years); 51% of patients were female; 68% of patients were white. Of all the included patients, 81% received pharmacologic prophylaxis; of these patients, 78% received unfractionated heparin subcutaneously and 22% received low molecular weight heparin subcutaneously. Among all hospitalized patients, 78% had an IMPROVE-VTE score of <2 (32% had a score of 0 and 46% had a score of 1). Among these patients at low risk of hospital-associated VTE, 81% received pharmacologic PPX. Differences in prophylaxis rates between patients at low vs high risk of VTE were statistically significant (p<0.001). Conclusion: In this contemporary cohort of adult, medical inpatients, >80% of patients who were at low risk of hospital-associated VTE received pharmacologic PPX, representing a group in whom PPX may be unnecessary. Using a risk-adapted approach such as the IMPROVE-VTE risk assessment model, rather than default PPX ordering, may reduce medical overuse and avoidable harms. Disclosures Chaudhry: CVS State of CT Clinical Pharmacy Program: Other: Paid Reviewer for CVS State of CT Clinical Pharmacy Program.

Download Full-text

Risk assessment model for venous thromboembolism in hospitalized surgical and non-surgical patients in the 4th Hungarian Antithrombotic Guidelines entitled “Diminution and Treatment of Venous Thromboembolism”

Orvosi Hetilap ◽

10.1556/oh.2010.28944 ◽

2010 ◽

Vol 151 (34) ◽

pp. 1365-1374 ◽

Cited By ~ 1

Author(s):

Marianna Dávid ◽

Hajna Losonczy ◽

Miklós Udvardy ◽

Zoltán Boda ◽

György Blaskó ◽

...

Keyword(s):

Risk Assessment ◽

Venous Thromboembolism ◽

Assessment Model ◽

Surgical Patients ◽

Risk Assessment Model

A kórházban kezelt sebészeti és belgyógyászati betegekben jelentős a vénásthromboembolia-rizikó. Profilaxis nélkül, a műtét típusától függően, a sebészeti beavatkozások kapcsán a betegek 15–60%-ában alakul ki mélyvénás trombózis vagy tüdőembólia, és az utóbbi ma is vezető kórházi halálok. Bár a vénás thromboemboliát leggyakrabban a közelmúltban végzett műtéttel vagy traumával hozzák kapcsolatba, a szimptómás thromboemboliás események 50–70%-a és a fatális tüdőembóliák 70–80%-a nem a sebészeti betegekben alakul ki. Nemzetközi és hazai felmérések alapján a nagy kockázattal rendelkező sebészeti betegek többsége megkapja a szükséges trombózisprofilaxist. Azonban profilaxis nélkül marad a rizikóval rendelkező belgyógyászati betegek jelentős része, a konszenzuson alapuló nemzetközi és hazai irányelvi ajánlások ellenére. A belgyógyászati betegek körében növelni kell a profilaxisban részesülők arányát és el kell érni, hogy trombózisrizikó esetén a betegek megkapják a hatásos megelőzést. A beteg trombóziskockázatának felmérése fontos eszköze a vénás thromboembolia által veszélyeztetett betegek felderítésének, megkönnyíti a döntést a profilaxis elrendeléséről és javítja az irányelvi ajánlások betartását. A trombózisveszély megállapításakor, ha nem ellenjavallt, profilaxist kell alkalmazni. „A thromboemboliák kockázatának csökkentése és kezelése” című, 4. magyar antithromboticus irányelv felhívja a figyelmet a vénástrombózis-rizikó felmérésének szükségességére, és elsőként tartalmazza a kórházban fekvő belgyógyászati és sebészeti betegek kockázati kérdőívét. Ismertetjük a kockázatbecslő kérdőíveket és áttekintjük a kérdőívekben szereplő rizikófaktorokra vonatkozó bizonyítékokon alapuló adatokat.

Download Full-text

AB0809 PADUA PREDICTION SCORE COMBINED WITH SERUM ALBUMIN FOR THE IDENTIFICATION OF VENOUS THROMBOEMBOLISM OF HOSPITALIZED PATIENTS IN THE DEPARTMENT OF RHEUMATOLOGY

Annals of the Rheumatic Diseases ◽

10.1136/annrheumdis-2021-eular.3729 ◽

2021 ◽

Vol 80 (Suppl 1) ◽

pp. 1429.1-1429

Author(s):

Q. Peng ◽

L. Long ◽

J. Liu

Keyword(s):

Risk Factors ◽

Venous Thromboembolism ◽

Serum Albumin ◽

Risk Group ◽

Assessment Model ◽

Prediction Score ◽

Risk Assessment Model ◽

Systemic Autoimmune Diseases ◽

Independent Risk Factors ◽

The Difference

Background:Venous thromboembolism (VTE) includes thrombotic disease of venous system, but primarily includes lower extremity deep vein thrombosis (DVT) and pulmonary embolism (PE). Population-based epidemiological studies have shown an association between systemic autoimmune diseases and VTE[1]. The Padua prediction score(PPS) is a new 20-point risk assessment model proposed by Professor Barbar et al[2] in 2010. A large number of researches have shown that low serum albumin concentration is associated with an increased risk of VTE [3],but there is a lack of studies on serum albumin in VTE, and there are no reports on PPS in rheumatology inpatients.Objectives:To investigate the status of VTE in patients in the department of rheumatology, and to explore the value of PPS combined with serum albumin in the identification of VTE in this patient population.Methods:Baseline data of inpatients in rheumatology department were collected at Sichuan Provincial People’s Hospital from September 2018 to September 2020. Occurrence of VTE was compared between high and low risk groups. PPSs were analyzed in VTE and non-VTE patients. Multivariate logistic regression was used to analyze the independent risk factors of VTE. The receiver operating characteristic curve was used to evaluate the probablity of value of rheumatic inpatients with VTE assessed by PPS,serum albumin and PPS with serum albumin. P<0.05 indicates that the difference was statistically significant.Results:A total of 2282 patients were included in this study, and 50(2.2%) had symptomatic VTE. Among the symptomatic VTE cases,38(1.6%) had DVT only,8(0.4%) had PE only, and 4(0.2%) were diagnosed with DVT and PE. PPSs in VTE and non-VTE groups were 3.00(2.00~6.00) and2.00(1.00~2.00) respectively (P< 0.05). One hundred and eighty-eight cases was divided into high-risk group of VTE (PPS≥4), while 2094 cases (PPS<4) were in the low-risk group. Logistic regression analysis showed that known thrombophilic condition, history of VTE, reduced mobility, and D-dimer were independent risk factors of VTE in rheumatology patients, the odd ration(OR) values were 161.90, 26.08, 8.73,and1.04. Serum albumin was the independent protection factor [OR= 0.92(95%CI:0.87~0.98)]. The AUC of PPS model, serum albumin model and the combined predictive model were 0.77, 0.75, 0.84, respectively. The difference between the combined prediction model and PPS model was statistically significant (Z=3.813, P<0.05). The optimal sensitivity of PPS and serum albumin models is 60%, 82%, respectively, and the optimal specificity of is 82.5%,58.6%, respectively. The combination model corresponds to a sensitivity of 62% and a specificity of 90.4%.Conclusion:The incidence of symptomatic VTE was relatively higher in hospitalized patients in rheumatology department. Serum albumin was the protective factor. The combination of albumin and PPS can improve the accuracy of screening for VTE in rheumatology in-patients.References:[1]Tamaki H,Khasnis A.Venous thromboembolism in systemic autoimmune diseases: A narrative review with emphasis on primary systemic vasculitides.[J].Vasc Med, 2015, 20: 369-76.[2]Barbar S, Noventa F, Rossetto V,et al. A risk assessment model for the identification of hospitalized medical patients at risk for venous thromboembolism: the Padua Prediction Score[J]. J Thromb Haemost,2010,8(11):2450–2457.[3]Kunutsor SK,Seidu S,Katechia DT et al. Inverse association between serum albumin and future risk of venous thromboembolism: interrelationship with high sensitivity C-reactive protein.[J].Ann Med, 2018, 50: 240-248.Disclosure of Interests:None declared

Download Full-text