Multi-class classification algorithms for the diagnosis of anemia in an outpatient clinical setting

Real-time non-invasive hemoglobin prediction using deep learning-enabled smartphone imaging

BACKGROUND

Accurate measurement of hemoglobin concentration is essential for various medical scenarios, including preoperative evaluations and determining blood loss. Traditional invasive methods are inconvenient and not suitable for rapid, point-of-care testing. Moreover, current models, due to their complex parameters, are not well-suited for mobile medical settings, which limits the ability to conduct frequent and rapid testing. This study aims to introduce a novel, compact, and efficient system that leverages deep learning and smartphone technology to accurately estimate hemoglobin levels, thereby facilitating rapid and accessible medical assessments.

METHODS

The study employed a smartphone application to capture images of the eye, which were subsequently analyzed by a deep neural network trained on data from invasive blood test data. Specifically, the EGE-Unet model was utilized for eyelid segmentation, while the DHA(C3AE) model was employed for hemoglobin level prediction. The performance of the EGE-Unet was evaluated using statistical metrics including mean intersection over union (MIOU), F1 Score, accuracy, specificity, and sensitivity. The DHA(C3AE) model's performance was assessed using mean absolute error (MAE), mean-square error (MSE), root mean square error (RMSE), and R^2.

RESULTS

The EGE-Unet model demonstrated robust performance in eyelid segmentation, achieving an MIOU of 0.78, an F1 Score of 0.87, an accuracy of 0.97, a specificity of 0.98, and a sensitivity of 0.86. The DHA(C3AE) model for hemoglobin level prediction yielded promising outcomes with an MAE of 1.34, an MSE of 2.85, an RMSE of 1.69, and an R^2 of 0.34. The overall size of the model is modest at 1.08 M, with a computational complexity of 0.12 FLOPs (G).

CONCLUSIONS

This system presents a groundbreaking approach that eliminates the need for supplementary devices, providing a cost-effective, swift, and accurate method for healthcare professionals to enhance treatment planning and improve patient care in perioperative environments. The proposed system has the potential to enable frequent and rapid testing of hemoglobin levels, which can be particularly beneficial in mobile medical settings.

TRIAL REGISTRATION

The clinical trial was registered on the Chinese Clinical Trial Registry (No. ChiCTR2100044138) on 20/02/2021.

Detection of anemic condition in patients from clinical markers and explainable artificial intelligence

BACKGROUND

Anaemia is a commonly known blood illness worldwide. Red blood cell (RBC) count or oxygen carrying capability being insufficient are two ways to describe anaemia. This disorder has an impact on the quality of life. If anaemia is detected in the initial stage, appropriate care can be taken to prevent further harm.

OBJECTIVE

This study proposes a machine learning approach to identify anaemia from clinical markers, which will help further in clinical practice.

METHODS

The models are designed with a dataset of 364 samples and 12 blood test attributes. The developed algorithm is expected to provide decision support to the clinicians based on blood markers. Each model is trained and validated on several performance metrics.

RESULTS

The accuracy obtained by the random forest, K nearest neighbour, support vector machine, Naive Bayes, xgboost, and catboost are 97%, 98%, 95%, 95%, 98% and 97% respectively. Four explainers such as Shapley Additive Values (SHAP), QLattice, Eli5 and local interpretable model-agnostic explanations (LIME) are explored for interpreting the model predictions.

CONCLUSION

The study provides insights into the potential of machine learning algorithms for classification and may help in the development of automated and accurate diagnostic tools for anaemia.

Tracking Health, Performance and Recovery in Athletes Using Machine Learning

Training and competitive periods can temporarily impair the performance of an athlete. This disruption can be short- or long-term, lasting up to several days. We analyzed the health indicators of 3661 athletes during an in-depth medical examination. At the time of inclusion in the study, the athletes were healthy. Instrumental examinations (fluorography, ultrasound examination of the abdominal cavity and pelvic organs, echocardiography, electrocardiography, and stress testing “to failure”), laboratory examinations (general urinalysis and biochemical and general clinical blood analysis), and examinations by specialists (ophthalmologist, otolaryngologist, surgeon, cardiologist, neurologist, dentist, gynecologist (women), endocrinologist, and therapist) were performed. This study analyzed the significance of determining the indicators involved in the implementation of the “catabolism” and “anabolism” phenotypes using the random forest and multinomial logistic regression machine learning methods. The use of decision forest and multinomial regression models made it possible to identify the most significant indicators of blood and urine biochemistry for the analysis of phenotypes as a characterization of the effectiveness of recovery processes in the post-competitive period in athletes. We found that the parameters of muscle metabolism, such as aspartate aminotransferase, creatine kinase, lactate dehydrogenase, and alanine aminotransferase levels, and the parameters of the ornithine cycle, such as creatinine, urea acid, and urea levels, made the most significant contribution to the classification of two types of metabolism: catabolism and anabolism.