simpleNomo: A Python Package of Making Nomograms for Visualizable Calculation of Logistic Regression Models

Cardiac murmur grading and risk analysis of cardiac diseases based on adaptable heterogeneous-modality multi-task learning

Cardiovascular disease (CVDs) has become one of the leading causes of death, posing a significant threat to human life. The development of reliable Artificial Intelligence (AI) assisted diagnosis algorithms for cardiac sounds is of great significance for early detection and treatment of CVDs. However, there is scarce research in this field. Existing research mainly faces three major challenges: (1) They mainly limited to murmur classification and cannot achieve murmur grading, but attempting both classification and grading may lead to negative effects between different multi-tasks. (2) They mostly pay attention to unstructured cardiac sound modality and do not consider the structured demographic modality, as it is difficult to balance the influence of heterogeneous modalities. (3) Deep learning methods lack interpretability, which makes it challenging to apply them clinically. To tackle these challenges, we propose a method for cardiac murmur grading and cardiac risk analysis based on heterogeneous modality adaptive multi-task learning. Specifically, a Hierarchical Multi-Task learning-based cardiac murmur detection and grading method (HMT) is proposed to prevent negative interference between different tasks. In addition, a cardiac risk analysis method based on Heterogeneous Multi-modal feature impact Adaptation (HMA) is also proposed, which transforms unstructured modality into structured modality representation, and utilizes an adaptive mode weight learning mechanism to balance the impact between unstructured modality and structured modality, thus enhancing the performance of cardiac risk prediction. Finally, we propose a multi-task interpretability learning module that incorporates an important evaluation using random masks. This module utilizes SHAP graphs to visualize crucial murmur segments in cardiac sound and employs a multi-factor risk decoupling model based on nomograms. And then we gain insights into the cardiac disease risk in both pre-decoupled multi-modality and post-decoupled single-modality scenarios, thus providing a solid foundation for AI assisted cardiac murmur grading and risk analysis. Experimental results on a large real-world CirCor DigiScope PCG dataset demonstrate that the proposed method outperforms the state-of-the-art (SOTA) method in murmur detection, grading, and cardiac risk analysis, while also providing valuable diagnostic evidence.

Machine learning to predict the occurrence of thyroid nodules: towards a quantitative approach for judicious utilization of thyroid ultrasonography

Introduction

Ultrasound is instrumental in the early detection of thyroid nodules, which is crucial for appropriate management and favorable outcomes. However, there is a lack of clinical guidelines for the judicious use of thyroid ultrasonography in routine screening. Machine learning (ML) has been increasingly used on big data to predict clinical outcomes. This study aims to leverage the ML approach in assessing the risk of thyroid nodules based on common clinical features.

Methods

Data were sourced from a Chinese cohort undergoing routine physical examinations including thyroid ultrasonography between 2013 and 2023. Models were established to predict the 3-year risk of thyroid nodules based on patients' baseline characteristics and laboratory tests. Four ML algorithms, including logistic regression, random forest, extreme gradient boosting, and light gradient boosting machine, were trained and tested using fivefold cross-validation. The importance of each feature was measured by the permutation score. A nomogram was established to facilitate risk assessment in the clinical settings.

Results

The final dataset comprised 4,386 eligible subjects. Thyroid nodules were detected in 54.8% (n=2,404) individuals within the 3-year observation period. All ML models significantly outperformed the baseline regression model, successfully predicting the occurrence of thyroid nodules in approximately two-thirds of individuals. Age, high-density lipoprotein, fasting blood glucose and creatinine levels exhibited the highest impact on the outcome in these models. The nomogram showed consistency and validity, providing greater net benefits for clinical decision-making than other strategies.

Conclusion

This study demonstrates the viability of an ML-based approach in predicting the occurrence of thyroid nodules. The findings highlight the potential of ML models in identifying high-risk individuals for personalized screening, thereby guiding the judicious use of ultrasound in this context.

Development of a diagnostic prediction model for giant cell arteritis by sequential application of Southend Giant Cell Arteritis Probability Score and ultrasonography: a prospective multicentre study

BACKGROUND

Giant cell arteritis is a critically ischaemic disease with protean manifestations that require urgent diagnosis and treatment. European Alliance of Associations for Rheumatology (EULAR) recommendations advocate ultrasonography as the first investigation for suspected giant cell arteritis. We developed a prediction tool that sequentially combines clinical assessment, as determined by the Southend Giant Cell Arteritis Probability Score (SGCAPS), with results of quantitative ultrasonography.

METHODS

This prospective, multicentre, inception cohort study included consecutive patients with suspected new onset giant cell arteritis referred to fast-track clinics (seven centres in Italy, the Netherlands, Spain, and UK). Final clinical diagnosis was established at 6 months. SGCAPS and quantitative ultrasonography of temporal and axillary arteries with three scores (ie, halo count, halo score, and OMERACT GCA Score [OGUS]) were performed at diagnosis. We developed prediction models for diagnosis of giant cell arteritis by multivariable logistic regression analysis with SGCAPS and each of the three ultrasonographic scores as predicting variables. We obtained intraclass correlation coefficient for inter-rater and intra-rater reliability in a separate patient-based reliability exercise with five patients and five observers.

FINDINGS

Between Oct 1, 2019, and June 30, 2022, we recruited and followed up 229 patients (150 [66%] women and 79 [34%] men; mean age 71 years [SD 10]), of whom 84 were diagnosed with giant cell arteritis and 145 with giant cell arteritis mimics (controls) at 6 months. SGCAPS and all three ultrasonographic scores discriminated well between patients with and without giant cell arteritis. A reliability exercise showed that the inter-rater and intra-rater reliability was high for all three ultrasonographic scores. The prediction model combining SGCAPS with the halo count, which was termed HAS-GCA score, was the most accurate model, with an optimism-adjusted C statistic of 0·969 (95% CI 0·952 to 0·990). The HAS-GCA score could classify 169 (74%) of 229 patients into either the low or high probability groups, with misclassification observed in two (2%) of 105 patients in the low probability group and two (3%) of 64 of patients in the high probability group. A nomogram for easy application of the score in daily practice was created.

INTERPRETATION

A prediction tool for giant cell arteritis (the HAS-GCA score), combining SGCAPS and the halo count, reliably confirms and excludes giant cell arteritis from giant cell arteritis mimics in fast-track clinics. These findings require confirmation in an independent, multicentre study.

FUNDING

Royal College of Physicians of Ireland, FOREUM.

A machine learning driven monogram for predicting chronic kidney disease stages 3-5

Chronic kidney disease (CKD) remains one of the most prominent global causes of mortality worldwide, necessitating accurate prediction models for early detection and prevention. In recent years, machine learning (ML) techniques have exhibited promising outcomes across various medical applications. This study introduces a novel ML-driven monogram approach for early identification of individuals at risk for developing CKD stages 3-5. This retrospective study employed a comprehensive dataset comprised of clinical and laboratory variables from a large cohort of diagnosed CKD patients. Advanced ML algorithms, including feature selection and regression models, were applied to build a predictive model. Among 467 participants, 11.56% developed CKD stages 3-5 over a 9-year follow-up. Several factors, such as age, gender, medical history, and laboratory results, independently exhibited significant associations with CKD (p < 0.05) and were utilized to create a risk function. The Linear regression (LR)-based model achieved an impressive R-score (coefficient of determination) of 0.954079, while the support vector machine (SVM) achieved a slightly lower value. An LR-based monogram was developed to facilitate the process of risk identification and management. The ML-driven nomogram demonstrated superior performance when compared to traditional prediction models, showcasing its potential as a valuable clinical tool for the early detection and prevention of CKD. Further studies should focus on refining the model and validating its performance in diverse populations.