Description:FIELD OF THE INVENTION
This invention relates to fetal health prediction using machine learning algorithms
BACKGROUND OF THE INVENTION
To ensure the health of the mother and the unborn child, fetal health assessment is essential. Due to its manual interpretation, traditional cardiotocography (CTG) analysis is sensitive to subjectivity and human error. If fetal health concerns are misclassified, medical action may be delayed, which raises the risk of consequences like stillbirth, hypoxia, or fetal distress. Even with advances in machine learning (ML), problems with imbalanced datasets, poor feature selection, and limited generalizability across clinical situations plague current models. It is clear that a classification system that is automated, effective, and extremely accurate is required.
Feature Previous Work Present Work
Classification Method Traditional ML models (Logistic Regression, Decision Trees, Naïve Bayes) Advanced ensemble models (LightGBM, XGBoost, Random Forest)
Handling of Imbalanced Data Limited or no balancing techniques SMOTE applied for better classification of minority classes
Accuracy Moderate (80-90%) High (99.42%)
Feature Selection Manual selection or none Automated feature selection (RFE, Mutual Information)
Hyperparameter Optimization Default settings or limited tuning Extensive tuning with Grid Search and Random Search
Interpretability Basic model explanations Explainable AI techniques (SHAP, LIME) for transparency
Clinical Applicability Less reliable due to lower accuracy and lack of real-time processing More reliable and adaptable for real-world use in medical diagnostics

SUMMARY OF THE INVENTION
This summary is provided to introduce a selection of concepts, in a simplified format, that are further described in the detailed description of the invention.
This summary is neither intended to identify key or essential inventive concepts of the invention and nor is it intended for determining the scope of the invention.
To further clarify advantages and features of the present invention, a more particular description of the invention will be rendered by reference to specific embodiments thereof, which is illustrated in the appended drawings. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting of its scope. The invention will be described and explained with additional specificity and detail with the accompanying drawings.
The proposed invention is an advanced machine learning-based fetal health classification system designed to enhance prenatal care by automating the diagnosis of fetal conditions. Traditional methods of fetal health monitoring rely on manual interpretation of cardiotocography (CTG) data, which can be subjective and prone to human error. This invention addresses these limitations by leveraging machine learning algorithms, such as LightGBM, XGBoost, and Random Forest, to classify fetal health into three categories: Normal, Suspect, and Pathological. The system integrates robust data preprocessing techniques, including feature scaling, outlier removal, and Synthetic Minority Over-sampling Technique (SMOTE), to handle imbalanced datasets effectively. Additionally, hyperparameter tuning is applied to optimize model performance, ensuring high classification accuracy.
BRIEF DESCRIPTION OF THE DRAWINGS
The illustrated embodiments of the subject matter will be understood by reference to the drawings, wherein like parts are designated by like numerals throughout. The following description is intended only by way of example, and simply illustrates certain selected embodiments of devices, systems, and methods that are consistent with the subject matter as claimed herein, wherein:
FIGURE 1: SYSTEM ARCHITECTURE
FIGURE 2: MODEL ACCURACY TREND
The figures depict embodiments of the present subject matter for the purposes of illustration only. A person skilled in the art will easily recognize from the following description that alternative embodiments of the structures and methods illustrated herein may be employed without departing from the principles of the disclosure described herein.
DETAILED DESCRIPTION OF THE INVENTION
The detailed description of various exemplary embodiments of the disclosure is described herein with reference to the accompanying drawings. It should be noted that the embodiments are described herein in such details as to clearly communicate the disclosure. However, the amount of details provided herein is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the scope of the present disclosure as defined by the appended claims.
It is also to be understood that various arrangements may be devised that, although not explicitly described or shown herein, embody the principles of the present disclosure. Moreover, all statements herein reciting principles, aspects, and embodiments of the present disclosure, as well as specific examples, are intended to encompass equivalents thereof.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms “a",” “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises,” “comprising,” “includes” and/or “including,” when used herein, specify the presence of stated features, integers, steps, operations, elements and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and/or groups thereof.
It should also be noted that in some alternative implementations, the functions/acts noted may occur out of the order noted in the figures. For example, two figures shown in succession may, in fact, be executed concurrently or may sometimes be executed in the reverse order, depending upon the functionality/acts involved.
In addition, the descriptions of "first", "second", “third”, and the like in the present invention are used for the purpose of description only, and are not to be construed as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Thus, features defining "first" and "second" may include at least one of the features, either explicitly or implicitly.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which example embodiments belong. It will be further understood that terms, e.g., those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The proposed invention is an advanced machine learning-based fetal health classification system designed to enhance prenatal care by automating the diagnosis of fetal conditions. Traditional methods of fetal health monitoring rely on manual interpretation of cardiotocography (CTG) data, which can be subjective and prone to human error. This invention addresses these limitations by leveraging machine learning algorithms, such as LightGBM, XGBoost, and Random Forest, to classify fetal health into three categories: Normal, Suspect, and Pathological. The system integrates robust data preprocessing techniques, including feature scaling, outlier removal, and Synthetic Minority Over-sampling Technique (SMOTE), to handle imbalanced datasets effectively. Additionally, hyperparameter tuning is applied to optimize model performance, ensuring high classification accuracy.
By automating fetal health assessment, this invention provides an objective, data-driven solution that improves early detection of fetal distress and minimizes the risks associated with misdiagnosis. The model achieves 99.42% accuracy, outperforming traditional statistical approaches. Key features include feature importance analysis, explainability techniques like SHAP (Shapley Additive Explanations), and real-time applicability, making it a reliable decision-support tool for healthcare professionals. The system's scalability allows integration into clinical settings for continuous fetal health monitoring, ultimately contributing to reducing neonatal mortality rates and enhancing maternal-fetal healthcare.
NOVELTY:
The suggested method achieves 99.42% accuracy by combining hyperparameter turning, data balancing (SMOTE), and sophisticated ensemble learning (LightGBM, XGBoost). By automating diagnosis, decreasing human error, and enhancing clinical decision-making, it improves the classification of fetal health.
The proposed methodology utilizes machine learning algorithms to classify fetal health into Normal, Suspect, and Pathological categories based on CTG data. Data preprocessing techniques, including feature scaling, outlier removal, and SMOTE, ensure improved model performance. Various ML models like Random Forest, XGBoost, and LightGBM are trained and optimized using hyperparameter tuning. Performance is evaluated using accuracy, precision, recall, and F1-score, with LightGBM achieving the highest accuracy (99.42%). The final model provides an automated, reliable, and scalable decision-support system for fetal health monitoring.
ADVANTAGES OF THE INVENTION
Greater Accuracy—The Finest The performing model (LightGBM) outperformed conventional statistical models such as Naïve Bayes (80.83%) and Logistic Regression (86%) with an accuracy of 99.42%.
Better Generalization-Ensemble techniques provide consistent performance across many datasets by minimizing overfitting.
Automated and Scalable: This method helps with extensive fetal health monitoring by providing real-time forecasts, in contrast to manual CTG analysis.
Improved Handling of Unbalanced Data: Methods such as SMOTE improve the classification of uncommon cases by addressing the skewed distribution of fetal health problems.
Objective & Reliable: This ensures more consistent medical decision-making by removing human subjectivity from fetal health assessment.
, Claims:1. A machine learning-based fetal health prediction system for classifying fetal health conditions, comprising:
a) input module configured to receive cardiotocography (CTG) data;
b) a preprocessing module configured to perform data preprocessing operations including feature scaling, outlier removal, and application of Synthetic Minority Over-sampling Technique (SMOTE) for handling imbalanced datasets;
c) a classification module comprising one or more machine learning algorithms selected from the group consisting of LightGBM, XGBoost, and Random Forest;
d) a training module configured to apply hyperparameter tuning on the said machine learning algorithms to optimize classification performance; and
e) an output module configured to classify fetal health into categories of Normal, Suspect, or Pathological based on the processed input data.
2. The system as claimed in claim 1, wherein the classification module is configured to achieve a classification accuracy of at least 99.42%.
3. The system as claimed in claim 1, wherein the preprocessing module utilizes SMOTE to synthetically balance minority class samples in the CTG dataset.