A machine learning‐based risk scoring system for infertility considering different age groups

Liao, Shujie; Jin, Lei; Dai, Wan-Qiang; Huang, Guocheng; Pan, Wei; Hu, Cheng; Pan, Wei

doi:10.1002/int.22344

Cited by 6 publications

(9 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this model [4], a machine learning based risk point system for infertility was created to aid clinicians in better understanding the patient's condition in context of the intricacy of infertility management and therapy. First, feature selection excludes eight crucial indicators of infertility.…”

Section: Shujie Liaomentioning

confidence: 99%

A Review on AI methods for the Prediction of Infertility in Women

Koshy¹,

Anuradha²

2022

IJETMS

View full text Add to dashboard Cite

Around the world 8 to 15 percent of couples in their reproductive age have infertility problem. According to WHO estimates, there are 60-80 million infertile couples globally, with some parts of population having the greatest rate. Significant social, emotional and psychological stress has been brought on by infertility among couples, families, the individual in question, and the larger society. Few researches have used Artificial Intelligence (AI) techniques in the field of reproduction, despite the fact that the use of AI techniques in the medical profession is growing every year. In order to assist couples with unexplained infertility, this review study develops and assesses multiple artificial intelligence models that can differentiate infertile/fertile couples based on a variety of characteristics.

show abstract

Section: Shujie Liaomentioning

confidence: 99%

A Review on AI methods for the Prediction of Infertility in Women

Koshy¹,

Anuradha²

2022

IJETMS

View full text Add to dashboard Cite

show abstract

“…The existing outcome prediction methods based on EHR data can be roughly divided into two categories, that is, the traditional machine learning-based methods and the deep learning-based methods. Traditional machine learning-based methods first extract handcrafted features from the EHR data, and then adopt algorithms such as logistic regression, 11,12 support vector machine, 13,14 and random forest [15][16][17] to train the outcome prediction models. However, traditional machine learningbased methods have the following drawbacks.…”

Section: Related Workmentioning

confidence: 99%

“…Traditional machine learning‐based methods first extract handcrafted features from the EHR data, and then adopt algorithms such as logistic regression, 11,12 support vector machine, 13,14 and random forest 15–17 to train the outcome prediction models. However, traditional machine learning‐based methods have the following drawbacks.…”

Section: Related Workmentioning

confidence: 99%

“…In traditional machine learning-based methods, features are typically extracted based on domain knowledge. [11][12][13][14][15][16][17] However, EHR data are extremely complex due to the unique characteristics of heterogeneity, temporality, and high-dimensionality. Heterogeneity indicates that EHR data consist of various formats, such as discrete data (e.g., diagnosis codes, procedures), continuous data (e.g., vital signs), and textual data (e.g., medication notes).…”

Section: Introductionmentioning

confidence: 99%

“…The most important step of building an outcome prediction model is to extract appropriate features from EHR data. In traditional machine learning‐based methods, features are typically extracted based on domain knowledge 11–17 . However, EHR data are extremely complex due to the unique characteristics of heterogeneity, temporality, and high‐dimensionality.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An interpretable outcome prediction model based on electronic health records and hierarchical attention

Zeng

Zhao

et al. 2021

Int J of Intelligent Sys

View full text Add to dashboard Cite

Outcome prediction aims to predict the future health condition of patients from Electronic Health Record (EHR) data. Because of the sequential characteristic of EHR data, recurrent neural network (RNN)‐based outcome prediction methods have achieved state‐of‐the‐art results. However, the major drawback of RNN‐based outcome prediction methods is lack of interpretability, which would lead to trust issues. Aiming at this problem, this paper proposes interpretable outcome prediction model with hierarchical attention (IoHAN), an interpretable outcome prediction model by leveraging attention mechanism. The main novelty of IoHAN is that it can pinpoint the fine‐grained influence on the final prediction result of each medical component by decomposing the attention weights hierarchically into hospital visits, medical variables, and interactions between medical variables. We evaluated IoHAN on MIMIC‐III, a large real‐world EHR data set. The experiment results demonstrate that IoHAN can achieve higher prediction accuracy than state‐of‐the‐art outcome prediction models. In addition, the hierarchical decomposed attention weights can interpret the prediction results in a more natural and understandable way.

show abstract

A hybrid adaptive approach for instance transfer learning with dynamic and imbalanced data

Zhang

Liu

Yuan

et al. 2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

Machine learning has demonstrated success in clinical risk prediction modeling with complex electronic health record (EHR) data. However, the evolving nature of clinical practices can dynamically change the underlying data distribution over time, leading to model performance drift. Adopting an outdated model is potentially risky and may result in unintentional losses. In this paper, we propose a novel Hybrid Adaptive Boosting approach (HA‐Boost) for transfer learning. HA‐Boost is characterized by the domain similarity‐based and class imbalance‐based adaptation mechanisms, which simultaneously address two critical limitations of the classical TrAdaBoost algorithm. We validated HA‐Boost in predicting hospital‐acquired acute kidney injury using real‐world longitudinal EHRs data. The experiment results demonstrate that HA‐Boost stably outperforms the competing baselines in terms of both Area Under Receiver Operating Characteristic and Area Under Precision‐Recall Curve across a 7‐year time span. This study has confirmed the effectiveness of transfer learning as a superior model updating approach in a dynamic environment.

show abstract

A machine learning‐based risk scoring system for infertility considering different age groups

Abstract: The application of artificial intelligence (AI) methods in medical field is increasing year by year; however, few studies have applied AI methods in the reproductive field. In view of the complexity of infertility diagnosis and treatment, a machine learning-based

Cited by 6 publications

References 33 publications

A Review on AI methods for the Prediction of Infertility in Women

A Review on AI methods for the Prediction of Infertility in Women

An interpretable outcome prediction model based on electronic health records and hierarchical attention

A hybrid adaptive approach for instance transfer learning with dynamic and imbalanced data

Contact Info

Product

Resources

About