Extensive phenotype data and machine learning in prediction of mortality in acute coronary syndrome – the MADDEC study

Hernesniemi, Jussi; Mahdiani, Shadi; Tynkkynen, Juho; Lyytikäinen, Leo-Pekka; Mishra, Pashupati P.; Lehtimäki, Terho; Eskola, Markku; Nikus, Kjell; Antila, Kari; Oksala, Niku

doi:10.1080/07853890.2019.1596302

Cited by 51 publications

(40 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ML has been shown to achieve the same or better prognostic definition in several clinical conditions, as compared to conventional statistical methods. In particular, ML can better predict clinical deterioration in the ward [ 26 ], mortality in acute coronary syndrome [ 27 ], survival in patients with epithelial ovarian cancer [ 28 ], complications of bariatric surgery [ 29 ], and risk of metabolic syndrome [ 30 ]. On the other hand, other studies reported that ML and conventional statistical methods have similar prognostic usefulness in predicting mortality in intensive care units [ 31 ], readmission in patients hospitalized for heart failure [ 32 ], and all-cause mortality and cardiovascular events [ 33 ].…”

Section: Applications Of ML In Medicinementioning

confidence: 99%

Comparison of Conventional Statistical Methods with Machine Learning in Medicine: Diagnosis, Drug Development, and Treatment

et al. 2020

View full text Add to dashboard Cite

Futurists have anticipated that novel autonomous technologies, embedded with machine learning (ML), will substantially influence healthcare. ML is focused on making predictions as accurate as possible, while traditional statistical models are aimed at inferring relationships between variables. The benefits of ML comprise flexibility and scalability compared with conventional statistical approaches, which makes it deployable for several tasks, such as diagnosis and classification, and survival predictions. However, much of ML-based analysis remains scattered, lacking a cohesive structure. There is a need to evaluate and compare the performance of well-developed conventional statistical methods and ML on patient outcomes, such as survival, response to treatment, and patient-reported outcomes (PROs). In this article, we compare the usefulness and limitations of traditional statistical methods and ML, when applied to the medical field. Traditional statistical methods seem to be more useful when the number of cases largely exceeds the number of variables under study and a priori knowledge on the topic under study is substantial such as in public health. ML could be more suited in highly innovative fields with a huge bulk of data, such as omics, radiodiagnostics, drug development, and personalized treatment. Integration of the two approaches should be preferred over a unidirectional choice of either approach.

show abstract

Section: Applications Of ML In Medicinementioning

confidence: 99%

Comparison of Conventional Statistical Methods with Machine Learning in Medicine: Diagnosis, Drug Development, and Treatment

et al. 2020

View full text Add to dashboard Cite

show abstract

“…In MADDEC, conventional electronic health record (EHR) data are combined with clinical cardiovascular phenotype data collected by treating physicians into a dedicated KARDIO registry. The register contains high-quality phenotype data for risk prediction, with added information over generic hospital EHRs, such as detailed information on patients' hospitalizations, invasive and non-invasive procedures, as well as outpatient visits [20][21][22].…”

Section: Methodsmentioning

confidence: 99%

Prehospital Adenosine Diphosphate Receptor Blocker Use, Culprit Artery Flow, and Mortality in STEMI: The MADDEC Study

et al. 2021

Self Cite

View full text Add to dashboard Cite

Background and ObjectiveThe newer adenosine diphosphate (ADP) receptor blockers ticagrelor and prasugrel are superior to clopidogrel in the long-term management of acute coronary syndrome (ACS). We evaluated the acute performance (prehospital loading) of these ADP receptor blockers in a primary percutaneous coronary intervention (PCI) for an ST-elevation myocardial infarction (STEMI). Methods In a retrospective, single-center registry study, data on all STEMI patients admitted for their first primary PCI between January 2007 and April 2020 were analyzed (n = 3218). The three ADP receptor blockers were mainly used during consecutive periods (clopidogrel 2007-2010, prasugrel 2011-2014, and ticagrelor 2014-2020), and were compared with risk factor-adjusted multivariate logistic regression for acute 3-and 7-day mortality and culprit artery flow before and after PCI. Results Of the 3218 total patients, 47.6% (n = 1532) were treated with ticagrelor, 22.1% (n = 711) were treated with prasugrel, and 30.3% (n = 975) were treated with clopidogrel. The use of ticagrelor or prasugrel as opposed to clopidogrel was associated with better culprit artery flow before PCI (odds ratio [OR] 1.21 for moderate or good flow, 95% confidence interval [CI] 1.03-1.42, p = 0.022), as well as lower acute mortality (OR 0.66 for 3-day mortality, 95% CI 0.46-0.95, p = 0.025; and OR 0.71 for 7-day mortality, 95% CI 0.52-0.98, p = 0.039). The results in regard to acute mortality were highlighted among patients with short treatment delays (disappearing with longer treatment delays; p < 0.05 for interaction). Conclusions The newer ADP receptor blockers are associated with lower mortality and better culprit artery flow at presentation when compared with clopidogrel. There are no significant differences between the two newer drugs. As the drugs were mainly used during three consecutive periods, unmeasured confounding related to the development of cardiac care and changes in the population may contribute to the results.

show abstract

“…Before training, the synthetic minority oversampling technique was adopted to deal with the unbalanced issue of the training data set [34]. XGBoost (Extreme Gradient Boosting), an ensemble tree-based model, has been shown to be more likely to achieve better model performance and to be more interpretable than other ML models, such as logistic regression or support vector machine [35][36][37][38][39]. Therefore, we choose the XGBoost algorithm to develop the prediction model for each outcome.…”

Section: Model Buildingmentioning

confidence: 99%

An Application of Machine Learning to Etiological Diagnosis of Secondary Hypertension: Retrospective Study Using Electronic Medical Records

Diao¹,

Huo²,

Yan³

et al. 2021

JMIR Med Inform

View full text Add to dashboard Cite

Background Secondary hypertension is a kind of hypertension with a definite etiology and may be cured. Patients with suspected secondary hypertension can benefit from timely detection and treatment and, conversely, will have a higher risk of morbidity and mortality than those with primary hypertension. Objective The aim of this study was to develop and validate machine learning (ML) prediction models of common etiologies in patients with suspected secondary hypertension. Methods The analyzed data set was retrospectively extracted from electronic medical records of patients discharged from Fuwai Hospital between January 1, 2016, and June 30, 2019. A total of 7532 unique patients were included and divided into 2 data sets by time: 6302 patients in 2016-2018 as the training data set for model building and 1230 patients in 2019 as the validation data set for further evaluation. Extreme Gradient Boosting (XGBoost) was adopted to develop 5 models to predict 4 etiologies of secondary hypertension and occurrence of any of them (named as composite outcome), including renovascular hypertension (RVH), primary aldosteronism (PA), thyroid dysfunction, and aortic stenosis. Both univariate logistic analysis and Gini Impurity were used for feature selection. Grid search and 10-fold cross-validation were used to select the optimal hyperparameters for each model. Results Validation of the composite outcome prediction model showed good performance with an area under the receiver-operating characteristic curve (AUC) of 0.924 in the validation data set, while the 4 prediction models of RVH, PA, thyroid dysfunction, and aortic stenosis achieved AUC of 0.938, 0.965, 0.959, and 0.946, respectively, in the validation data set. A total of 79 clinical indicators were identified in all and finally used in our prediction models. The result of subgroup analysis on the composite outcome prediction model demonstrated high discrimination with AUCs all higher than 0.890 among all age groups of adults. Conclusions The ML prediction models in this study showed good performance in detecting 4 etiologies of patients with suspected secondary hypertension; thus, they may potentially facilitate clinical diagnosis decision making of secondary hypertension in an intelligent way.

show abstract

Extensive phenotype data and machine learning in prediction of mortality in acute coronary syndrome – the MADDEC study

Cited by 51 publications

References 29 publications

Comparison of Conventional Statistical Methods with Machine Learning in Medicine: Diagnosis, Drug Development, and Treatment

Comparison of Conventional Statistical Methods with Machine Learning in Medicine: Diagnosis, Drug Development, and Treatment

Prehospital Adenosine Diphosphate Receptor Blocker Use, Culprit Artery Flow, and Mortality in STEMI: The MADDEC Study

An Application of Machine Learning to Etiological Diagnosis of Secondary Hypertension: Retrospective Study Using Electronic Medical Records

Contact Info

Product

Resources

About