Automatic ICD-10 multi-class classification of cause of death from plaintext autopsy reports through expert-driven feature selection

Using Natural Language Processing to Predict Fatal Drug Overdose From Autopsy Narrative Text: Algorithm Development and Validation Study

BACKGROUND

Fatal drug overdose surveillance informs prevention but is often delayed because of autopsy report processing and death certificate coding. Autopsy reports contain narrative text describing scene evidence and medical history (similar to preliminary death scene investigation reports) and may serve as early data sources for identifying fatal drug overdoses. To facilitate timely fatal overdose reporting, natural language processing was applied to narrative texts from autopsies.

OBJECTIVE

This study aimed to develop a natural language processing-based model that predicts the likelihood that an autopsy report narrative describes an accidental or undetermined fatal drug overdose.

METHODS

Autopsy reports of all manners of death (2019-2021) were obtained from the Tennessee Office of the State Chief Medical Examiner. The text was extracted from autopsy reports (PDFs) using optical character recognition. Three common narrative text sections were identified, concatenated, and preprocessed (bag-of-words) using term frequency-inverse document frequency scoring. Logistic regression, support vector machine (SVM), random forest, and gradient boosted tree classifiers were developed and validated. Models were trained and calibrated using autopsies from 2019 to 2020 and tested using those from 2021. Model discrimination was evaluated using the area under the receiver operating characteristic, precision, recall, F1-score, and F2-score (prioritizes recall over precision). Calibration was performed using logistic regression (Platt scaling) and evaluated using the Spiegelhalter z test. Shapley additive explanations values were generated for models compatible with this method. In a post hoc subgroup analysis of the random forest classifier, model discrimination was evaluated by forensic center, race, age, sex, and education level.

RESULTS

A total of 17,342 autopsies (n=5934, 34.22% cases) were used for model development and validation. The training set included 10,215 autopsies (n=3342, 32.72% cases), the calibration set included 538 autopsies (n=183, 34.01% cases), and the test set included 6589 autopsies (n=2409, 36.56% cases). The vocabulary set contained 4002 terms. All models showed excellent performance (area under the receiver operating characteristic ≥0.95, precision ≥0.94, recall ≥0.92, F1-score ≥0.94, and F2-score ≥0.92). The SVM and random forest classifiers achieved the highest F2-scores (0.948 and 0.947, respectively). The logistic regression and random forest were calibrated (P=.95 and P=.85, respectively), whereas the SVM and gradient boosted tree classifiers were miscalibrated (P=.03 and P<.001, respectively). "Fentanyl" and "accident" had the highest Shapley additive explanations values. Post hoc subgroup analyses revealed lower F2-scores for autopsies from forensic centers D and E. Lower F2-score were observed for the American Indian, Asian, ≤14 years, and ≥65 years subgroups, but larger sample sizes are needed to validate these findings.

CONCLUSIONS

The random forest classifier may be suitable for identifying potential accidental and undetermined fatal overdose autopsies. Further validation studies should be conducted to ensure early detection of accidental and undetermined fatal drug overdoses across all subgroups.

Performance evaluation of machine learning and Computer Coded Verbal Autopsy (CCVA) algorithms for cause of death determination: A comparative analysis of data from rural South Africa

Computer Coded Verbal Autopsy (CCVA) algorithms are commonly used to determine the cause of death (CoD) from questionnaire responses extracted from verbal autopsies (VAs). However, they can only operate on structured data and cannot effectively harness information from unstructured VA narratives. Machine Learning (ML) algorithms have also been applied successfully in determining the CoD from VA narratives, allowing the use of auxiliary information that CCVA algorithms cannot directly utilize. However, most ML-based studies only use responses from the structured questionnaire, and the results lack generalisability and comparability across studies. We present a comparative performance evaluation of ML methods and CCVA algorithms on South African VA narratives data, using data from Agincourt Health and Demographic Surveillance Site (HDSS) with physicians' classifications as the gold standard. The data were collected from 1993 to 2015 and have 16,338 cases. The random forest and extreme gradient boosting classifiers outperformed the other classifiers on the combined dataset, attaining accuracy of 96% respectively, with significant statistical differences in algorithmic performance (p < 0.0001). All our models attained Area Under Receiver Operating Characteristics (AUROC) of greater than 0.884. The InterVA CCVA attained 83% Cause Specific Mortality Fraction accuracy and an Overall Chance-Corrected Concordance of 0.36. We demonstrate that ML models could accurately determine the cause of death from VA narratives. Additionally, through mortality trends and pattern analysis, we discovered that in the first decade of the civil registration system in South Africa, the average life expectancy was approximately 50 years. However, in the second decade, life expectancy significantly dropped, and the population was dying at a much younger average age of 40 years, mostly from the leading HIV related causes. Interestingly, in the third decade, we see a gradual improvement in life expectancy, possibly attributed to effective health intervention programmes. Through a structure and semantic analysis of narratives where experts disagree, we also demonstrate the most frequent terms of traditional healer consultations and visits. The comparative approach also makes this study a baseline that can be used for future research enforcing generalization and comparability. Future study will entail exploring deep learning models for CoD classification.

A keyphrase-based approach for interpretable ICD-10 code classification of Spanish medical reports

BACKGROUND AND OBJECTIVES

The 10th version of International Classification of Diseases (ICD-10) codification system has been widely adopted by the health systems of many countries, including Spain. However, manual code assignment of Electronic Health Records (EHR) is a complex and time-consuming task that requires a great amount of specialised human resources. Therefore, several machine learning approaches are being proposed to assist in the assignment task. In this work we present an alternative system for automatically recommending ICD-10 codes to be assigned to EHRs.

METHODS

Our proposal is based on characterising ICD-10 codes by a set of keyphrases that represent them. These keyphrases do not only include those that have literally appeared in some EHR with the considered ICD-10 codes assigned, but also others that have been obtained by a statistical process able to capture expressions that have led the annotators to assign the code.

RESULTS

The result is an information model that allows to efficiently recommend codes to a new EHR based on their textual content. We explore an approach that proves to be competitive with other state-of-the-art approaches and can be combined with them to optimise results.

CONCLUSIONS

In addition to its effectiveness, the recommendations of this method are easily interpretable since the phrases in an EHR leading to recommend an ICD-10 code are known. Moreover, the keyphrases associated with each ICD-10 code can be a valuable additional source of information for other approaches, such as machine learning techniques.

A pilot study for investigating the feasibility of supervised machine learning approaches for the classification of pedestrians struck by vehicles

This research focuses on the application of Artificial Intelligence (AI) methodologies to the problem of classifying vehicles involved in lethal pedestrian collisions. Specifically, the vehicle type is predicted on the basis of traumatic injury suffered by casualties, exploiting machine learning algorithms. In the present study, AI-assisted diagnosis was shown to have correct prediction about 70% of the time. In pedestrians struck by trucks, more severe injuries were appreciated in the facial skeleton, lungs, major airways, liver, and spleen as well as in the sternum/clavicle/rib complex, whereas the lower extremities were more affected by fractures in pedestrians struck by cars. Although the distinction of the striking vehicle should develop beyond autopsy evidence alone, the presented approach which is novel in the realm of forensic science, is shown to be effective in building automated decision support systems. Outcomes from this system can provide valuable information after the execution of autoptic examinations supporting the forensic investigation. Preliminary results from the application of machine learning algorithms with real-world datasets seem to highlight the efficacy of the proposed approach, which could be used for further studies concerning this topic.

The Application of Projection Word Embeddings on Medical Records Scoring System

Medical records scoring is important in a health care system. Artificial intelligence (AI) with projection word embeddings has been validated in its performance disease coding tasks, which maintain the vocabulary diversity of open internet databases and the medical terminology understanding of electronic health records (EHRs). We considered that an AI-enhanced system might be also applied to automatically score medical records. This study aimed to develop a series of deep learning models (DLMs) and validated their performance in medical records scoring task. We also analyzed the practical value of the best model. We used the admission medical records from the Tri-Services General Hospital during January 2016 to May 2020, which were scored by our visiting staffs with different levels from different departments. The medical records were scored ranged 0 to 10. All samples were divided into a training set (n = 74,959) and testing set (n = 152,730) based on time, which were used to train and validate the DLMs, respectively. The mean absolute error (MAE) was used to evaluate each DLM performance. In original AI medical record scoring, the predicted score by BERT architecture is closer to the actual reviewer score than the projection word embedding and LSTM architecture. The original MAE is 0.84 ± 0.27 using the BERT model, and the MAE is 1.00 ± 0.32 using the LSTM model. Linear mixed model can be used to improve the model performance, and the adjusted predicted score was closer compared to the original score. However, the project word embedding with the LSTM model (0.66 ± 0.39) provided better performance compared to BERT (0.70 ± 0.33) after linear mixed model enhancement (p < 0.001). In addition to comparing different architectures to score the medical records, this study further uses a mixed linear model to successfully adjust the AI medical record score to make it closer to the actual physician's score.

Automated Machine Learning for Healthcare and Clinical Notes Analysis

Machine learning (ML) has been slowly entering every aspect of our lives and its positive impact has been astonishing. To accelerate embedding ML in more applications and incorporating it in real-world scenarios, automated machine learning (AutoML) is emerging. The main purpose of AutoML is to provide seamless integration of ML in various industries, which will facilitate better outcomes in everyday tasks. In healthcare, AutoML has been already applied to easier settings with structured data such as tabular lab data. However, there is still a need for applying AutoML for interpreting medical text, which is being generated at a tremendous rate. For this to happen, a promising method is AutoML for clinical notes analysis, which is an unexplored research area representing a gap in ML research. The main objective of this paper is to fill this gap and provide a comprehensive survey and analytical study towards AutoML for clinical notes. To that end, we first introduce the AutoML technology and review its various tools and techniques. We then survey the literature of AutoML in the healthcare industry and discuss the developments specific to clinical settings, as well as those using general AutoML tools for healthcare applications. With this background, we then discuss challenges of working with clinical notes and highlight the benefits of developing AutoML for medical notes processing. Next, we survey relevant ML research for clinical notes and analyze the literature and the field of AutoML in the healthcare industry. Furthermore, we propose future research directions and shed light on the challenges and opportunities this emerging field holds. With this, we aim to assist the community with the implementation of an AutoML platform for medical notes, which if realized can revolutionize patient outcomes.

Identification of Malignancies from Free-Text Histopathology Reports Using a Multi-Model Supervised Machine Learning Approach

We explored various Machine Learning (ML) models to evaluate how each model performs in the task of classifying histopathology reports. We trained, optimized, and performed classification with Stochastic Gradient Descent (SGD), Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbor (KNN), Adaptive Boosting (AB), Decision Trees (DT), Gaussian Naïve Bayes (GNB), Logistic Regression (LR), and Dummy classifier. We started with 60,083 histopathology reports, which reduced to 60,069 after pre-processing. The F1-scores for SVM, SGD KNN, RF, DT, LR, AB, and GNB were 97%, 96%, 96%, 96%, 92%, 96%, 84%, and 88%, respectively, while the misclassification rates were 3.31%, 5.25%, 4.39%, 1.75%, 3.5%, 4.26%, 23.9%, and 19.94%, respectively. The approximate run times were 2 h, 20 min, 40 min, 8 h, 40 min, 10 min, 50 min, and 4 min, respectively. RF had the longest run time but the lowest misclassification rate on the labeled data. Our study demonstrated the possibility of applying ML techniques in the processing of free-text pathology reports for cancer registries for cancer incidence reporting in a Sub-Saharan Africa setting. This is an important consideration for the resource-constrained environments to leverage ML techniques to reduce workloads and improve the timeliness of reporting of cancer statistics.

Construction of a semi-automatic ICD-10 coding system

Background

The International Classification of Diseases, 10th Revision (ICD-10) has been widely used to describe the diagnosis information of patients. Automatic ICD-10 coding is important because manually assigning codes is expensive, time consuming and error prone. Although numerous approaches have been developed to explore automatic coding, few of them have been applied in practice. Our aim is to construct a practical, automatic ICD-10 coding machine to improve coding efficiency and quality in daily work.

Methods

In this study, we propose the use of regular expressions (regexps) to establish a correspondence between diagnosis codes and diagnosis descriptions in outpatient settings and at admission and discharge. The description models of the regexps were embedded in our upgraded coding system, which queries a diagnosis description and assigns a unique diagnosis code. Like most studies, the precision (P), recall (R), F-measure (F) and overall accuracy (A) were used to evaluate the system performance. Our study had two stages. The datasets were obtained from the diagnosis information on the homepage of the discharge medical record. The testing sets were from October 1, 2017 to April 30, 2018 and from July 1, 2018 to January 31, 2019.

Results

The values of P were 89.27 and 88.38% in the first testing phase and the second testing phase, respectively, which demonstrate high precision. The automatic ICD-10 coding system completed more than 160,000 codes in 16 months, which reduced the workload of the coders. In addition, a comparison between the amount of time needed for manual coding and automatic coding indicated the effectiveness of the system-the time needed for automatic coding takes nearly 100 times less than manual coding.

Conclusions

Our automatic coding system is well suited for the coding task. Further studies are warranted to perfect the description models of the regexps and to develop synthetic approaches to improve system performance.

Multi-sensor fusion based on multiple classifier systems for human activity identification

Multimodal sensors in healthcare applications have been increasingly researched because it facilitates automatic and comprehensive monitoring of human behaviors, high-intensity sports management, energy expenditure estimation, and postural detection. Recent studies have shown the importance of multi-sensor fusion to achieve robustness, high-performance generalization, provide diversity and tackle challenging issue that maybe difficult with single sensor values. The aim of this study is to propose an innovative multi-sensor fusion framework to improve human activity detection performances and reduce misrecognition rate. The study proposes a multi-view ensemble algorithm to integrate predicted values of different motion sensors. To this end, computationally efficient classification algorithms such as decision tree, logistic regression and k-Nearest Neighbors were used to implement diverse, flexible and dynamic human activity detection systems. To provide compact feature vector representation, we studied hybrid bio-inspired evolutionary search algorithm and correlation-based feature selection method and evaluate their impact on extracted feature vectors from individual sensor modality. Furthermore, we utilized Synthetic Over-sampling minority Techniques (SMOTE) algorithm to reduce the impact of class imbalance and improve performance results. With the above methods, this paper provides unified framework to resolve major challenges in human activity identification. The performance results obtained using two publicly available datasets showed significant improvement over baseline methods in the detection of specific activity details and reduced error rate. The performance results of our evaluation showed 3% to 24% improvement in accuracy, recall, precision, F-measure and detection ability (AUC) compared to single sensors and feature-level fusion. The benefit of the proposed multi-sensor fusion is the ability to utilize distinct feature characteristics of individual sensor and multiple classifier systems to improve recognition accuracy. In addition, the study suggests a promising potential of hybrid feature selection approach, diversity-based multiple classifier systems to improve mobile and wearable sensor-based human activity detection and health monitoring system.

Projection Word Embedding Model With Hybrid Sampling Training for Classifying ICD-10-CM Codes: Longitudinal Observational Study

BACKGROUND

Most current state-of-the-art models for searching the International Classification of Diseases, Tenth Revision Clinical Modification (ICD-10-CM) codes use word embedding technology to capture useful semantic properties. However, they are limited by the quality of initial word embeddings. Word embedding trained by electronic health records (EHRs) is considered the best, but the vocabulary diversity is limited by previous medical records. Thus, we require a word embedding model that maintains the vocabulary diversity of open internet databases and the medical terminology understanding of EHRs. Moreover, we need to consider the particularity of the disease classification, wherein discharge notes present only positive disease descriptions.

OBJECTIVE

We aimed to propose a projection word2vec model and a hybrid sampling method. In addition, we aimed to conduct a series of experiments to validate the effectiveness of these methods.

METHODS

We compared the projection word2vec model and traditional word2vec model using two corpora sources: English Wikipedia and PubMed journal abstracts. We used seven published datasets to measure the medical semantic understanding of the word2vec models and used these embeddings to identify the three-character-level ICD-10-CM diagnostic codes in a set of discharge notes. On the basis of embedding technology improvement, we also tried to apply the hybrid sampling method to improve accuracy. The 94,483 labeled discharge notes from the Tri-Service General Hospital of Taipei, Taiwan, from June 1, 2015, to June 30, 2017, were used. To evaluate the model performance, 24,762 discharge notes from July 1, 2017, to December 31, 2017, from the same hospital were used. Moreover, 74,324 additional discharge notes collected from seven other hospitals were tested. The F-measure, which is the major global measure of effectiveness, was adopted.

RESULTS

In medical semantic understanding, the original EHR embeddings and PubMed embeddings exhibited superior performance to the original Wikipedia embeddings. After projection training technology was applied, the projection Wikipedia embeddings exhibited an obvious improvement but did not reach the level of original EHR embeddings or PubMed embeddings. In the subsequent ICD-10-CM coding experiment, the model that used both projection PubMed and Wikipedia embeddings had the highest testing mean F-measure (0.7362 and 0.6693 in Tri-Service General Hospital and the seven other hospitals, respectively). Moreover, the hybrid sampling method was found to improve the model performance (F-measure=0.7371/0.6698).

CONCLUSIONS

The word embeddings trained using EHR and PubMed could understand medical semantics better, and the proposed projection word2vec model improved the ability of medical semantics extraction in Wikipedia embeddings. Although the improvement from the projection word2vec model in the real ICD-10-CM coding task was not substantial, the models could effectively handle emerging diseases. The proposed hybrid sampling method enables the model to behave like a human expert.

Cardiology record multi-label classification using latent Dirichlet allocation

BACKGROUND AND OBJECTIVES

Electronic health records (EHRs) convey vast and valuable knowledge about dynamically changing clinical practices. Indeed, clinical documentation entails the inspection of massive number of records across hospitals and hospital sections. The goal of this study is to provide an efficient framework that will help clinicians explore EHRs and attain alternative views related to both patient-segments and diseases, like clustering and statistical information about the development of heart diseases (replacement of pacemakers, valve implantation etc.) in co-occurrence with other diseases. The task is challenging, dealing with lengthy health records and a high number of classes in a multi-label setting.

METHODS

LDA is a statistical procedure optimized to explain a document by multinomial distributions on their latent topics and the topics by distributions on related words. These distributions allow to represent collections of texts into a continuous space enabling distance-based associations between documents and also revealing the underlying topics. The topic models were assessed by means of four divergence metrics. In addition, we applied LDA to the task of multi-label document classification of EHRs according to the International Classification of Diseases 10th Clinical Modification (ICD-10). The set of EHRs had assigned 7 codes on average over 970 different codes corresponding to cardiology.

RESULTS

First, the discriminative ability of topic models was assessed using dissimilarity metrics. Nevertheless, there was an open question regarding the interpretability of automatically discovered topics. To address this issue, we explored the connection between the latent topics and ICD-10. EHRs were represented by means of LDA and, next, supervised classifiers were inferred from those representations. Given the low-dimensional representation provided by LDA, the search was computationally efficient compared to symbolic approaches such as TF-IDF. The classifiers achieved an average AUC of 77.79. As a side contribution, with this work we released the software implemented in Python and R to both train and evaluate the models.

CONCLUSIONS

Topic modeling offers a means of representing EHRs in a small dimensional continuous space. This representation conveys relevant information as hidden topics in a comprehensive manner. Moreover, in practice, this compact representation allowed to extract the ICD-10 codes associated to EHRs.

Classification of forensic autopsy reports through conceptual graph-based document representation model

Text categorization has been used extensively in recent years to classify plain-text clinical reports. This study employs text categorization techniques for the classification of open narrative forensic autopsy reports. One of the key steps in text classification is document representation. In document representation, a clinical report is transformed into a format that is suitable for classification. The traditional document representation technique for text categorization is the bag-of-words (BoW) technique. In this study, the traditional BoW technique is ineffective in classifying forensic autopsy reports because it merely extracts frequent but discriminative features from clinical reports. Moreover, this technique fails to capture word inversion, as well as word-level synonymy and polysemy, when classifying autopsy reports. Hence, the BoW technique suffers from low accuracy and low robustness unless it is improved with contextual and application-specific information. To overcome the aforementioned limitations of the BoW technique, this research aims to develop an effective conceptual graph-based document representation (CGDR) technique to classify 1500 forensic autopsy reports from four (4) manners of death (MoD) and sixteen (16) causes of death (CoD). Term-based and Systematized Nomenclature of Medicine-Clinical Terms (SNOMED CT) based conceptual features were extracted and represented through graphs. These features were then used to train a two-level text classifier. The first level classifier was responsible for predicting MoD. In addition, the second level classifier was responsible for predicting CoD using the proposed conceptual graph-based document representation technique. To demonstrate the significance of the proposed technique, its results were compared with those of six (6) state-of-the-art document representation techniques. Lastly, this study compared the effects of one-level classification and two-level classification on the experimental results. The experimental results indicated that the CGDR technique achieved 12% to 15% improvement in accuracy compared with fully automated document representation baseline techniques. Moreover, two-level classification obtained better results compared with one-level classification. The promising results of the proposed conceptual graph-based document representation technique suggest that pathologists can adopt the proposed system as their basis for second opinion, thereby supporting them in effectively determining CoD.

Deep neural models for ICD-10 coding of death certificates and autopsy reports in free-text

We address the assignment of ICD-10 codes for causes of death by analyzing free-text descriptions in death certificates, together with the associated autopsy reports and clinical bulletins, from the Portuguese Ministry of Health. We leverage a deep neural network that combines word embeddings, recurrent units, and neural attention, for the generation of intermediate representations of the textual contents. The neural network also explores the hierarchical nature of the input data, by building representations from the sequences of words within individual fields, which are then combined according to the sequences of fields that compose the inputs. Moreover, we explore innovative mechanisms for initializing the weights of the final nodes of the network, leveraging co-occurrences between classes together with the hierarchical structure of ICD-10. Experimental results attest to the contribution of the different neural network components. Our best model achieves accuracy scores over 89%, 81%, and 76%, respectively for ICD-10 chapters, blocks, and full-codes. Through examples, we also show that our method can produce interpretable results, useful for public health surveillance.

Artificial Intelligence Learning Semantics via External Resources for Classifying Diagnosis Codes in Discharge Notes

Background

Automated disease code classification using free-text medical information is important for public health surveillance. However, traditional natural language processing (NLP) pipelines are limited, so we propose a method combining word embedding with a convolutional neural network (CNN).

Objective

Our objective was to compare the performance of traditional pipelines (NLP plus supervised machine learning models) with that of word embedding combined with a CNN in conducting a classification task identifying International Classification of Diseases, Tenth Revision, Clinical Modification (ICD-10-CM) diagnosis codes in discharge notes.

Methods

We used 2 classification methods: (1) extracting from discharge notes some features (terms, n-gram phrases, and SNOMED CT categories) that we used to train a set of supervised machine learning models (support vector machine, random forests, and gradient boosting machine), and (2) building a feature matrix, by a pretrained word embedding model, that we used to train a CNN. We used these methods to identify the chapter-level ICD-10-CM diagnosis codes in a set of discharge notes. We conducted the evaluation using 103,390 discharge notes covering patients hospitalized from June 1, 2015 to January 31, 2017 in the Tri-Service General Hospital in Taipei, Taiwan. We used the receiver operating characteristic curve as an evaluation measure, and calculated the area under the curve (AUC) and F-measure as the global measure of effectiveness.

Results

In 5-fold cross-validation tests, our method had a higher testing accuracy (mean AUC 0.9696; mean F-measure 0.9086) than traditional NLP-based approaches (mean AUC range 0.8183-0.9571; mean F-measure range 0.5050-0.8739). A real-world simulation that split the training sample and the testing sample by date verified this result (mean AUC 0.9645; mean F-measure 0.9003 using the proposed method). Further analysis showed that the convolutional layers of the CNN effectively identified a large number of keywords and automatically extracted enough concepts to predict the diagnosis codes.

Conclusions

Word embedding combined with a CNN showed outstanding performance compared with traditional methods, needing very little data preprocessing. This shows that future studies will not be limited by incomplete dictionaries. A large amount of unstructured information from free-text medical writing will be extracted by automated approaches in the future, and we believe that the health care field is about to enter the age of big data.

Recognition of Traffic Sign Based on Bag-of-Words and Artificial Neural Network

The traffic sign recognition system is a support system that can be useful to give notification and warning to drivers. It may be effective for traffic conditions on the current road traffic system. A robust artificial intelligence based traffic sign recognition system can support the driver and significantly reduce driving risk and injury. It performs by recognizing and interpreting various traffic sign using vision-based information. This study aims to recognize the well-maintained, un-maintained, standard, and non-standard traffic signs using the Bag-of-Words and the Artificial Neural Network techniques. This research work employs a Bag-of-Words model on the Speeded Up Robust Features descriptors of the road traffic signs. A robust classifier Artificial Neural Network has been employed to recognize the traffic sign in its respective class. The proposed system has been trained and tested to determine the suitable neural network architecture. The experimental results showed high accuracy of classification of traffic signs including complex background images. The proposed traffic sign detection and recognition system obtained 99.00% classification accuracy with a 1.00% false positive rate. For real-time implementation and deployment, this marginal false positive rate may increase reliability and stability of the proposed system.