Segmentation-Driven Deep Learning for Explainable and Automated Vocal Fold Disorder Classification

Purpose: High-speed videoendoscopy (HSV) is an emerging, but barely used, endoscopy technique in the clinic to assess and diagnose voice disorders because of the lack of dedicated software to analyze the data. HSV allows to quantify the vocal fold oscillations by segmenting the glottal area. This challenging task has been tackled by various studies; however, the proposed approaches are mostly limited and not suitable for daily clinical routine.Method: We developed a user-friendly software in C# that allows the editing, motion correction, segmentation, and quantitative analysis of HSV data. We further provide pretrained deep neural networks for fully automatic glottis segmentation.Results: We freely provide our software Glottis Analysis Tools (GAT). Using GAT, we provide a general threshold-based region growing platform that enables the user to analyze data from various sources, such as in vivo recordings, ex vivo recordings, and high-speed footage of artificial vocal folds. Additionally, especially for in vivo recordings, we provide three robust neural networks at various speed and quality settings to allow a fully automatic glottis segmentation needed for application by untrained personnel. GAT further evaluates video and audio data in parallel and is able to extract various features from the video data, among others the glottal area waveform, that is, the changing glottal area over time. In total, GAT provides 79 unique quantitative analysis parameters for video- and audio-based signals. Many of these parameters have already been shown to reflect voice disorders, highlighting the clinical importance and usefulness of the GAT software.Conclusion: GAT is a unique tool to process HSV and audio data to determine quantitative, clinically relevant parameters for research, diagnosis, and treatment of laryngeal disorders.Supplemental Material S1. Supplemental figures: Figure S1. Neural network training metrics.Figure S2. Neural network evaluation.Figure S3. Example segmentations using different backbones from various source data.Figure S4. Audio analysis platform.Supplemental Material S2. Endoscopic footage with semi-automatic and fully automatic segmentation methods, multiple examples.Supplemental Material S3. GAT manual. Kist, A. M., Gomez, P., Dubrovskiy, D., Schlegel, P., Kunduk, M., Echternach, M., Patel, R., Semmler, M., Bohr, C., Durr, S., Schutzenberger, A., & Dollinger, M. (2021). A deep learning enhanced novel software tool for laryngeal dynamics analysis. Journal of Speech, Language, and Hearing Research. Advance online publication. https://doi.org/10.1044/2021_JSLHR-20-00498

Efficacy of Videostroboscopy and High-Speed Videoendoscopy to Obtain Functional Outcomes From Perioperative Ratings in Patients With Vocal Fold Mass Lesions

In today’s digital world, Android phones play a vital part in a variety of facets of both professionals and individuals’ personal and professional lives. Android phones are great for getting things done faster and more organized. The proportionate increase in the number of malicious applications has also been seen to be expanding. Since the play store offers millions of apps, detection of malware apps is challenging task. In this paper, a methodology is introduced for detecting malware in Android applications through the utilization of global image shape transform (GIST) features extracted from grayscale images of the applications. The dataset comprises samples of both malware and benign apps collected from the virus share website. After converting the apps into grayscale images, GIST features are extracted to capture their global spatial layout. Various machine learning (ML) algorithms, such as logistic regression (LR), k-nearest neighbour (KNN), AdaBoost, decision tree (DT), Naïve Bayes (NB), random forest (RF), support vector machine (SVM), extra tree classifier (ETC), and gradient boosting (GB), are employed to classify the applications according to their GIST features. Furthermore, a feed forward neural network (FFNN) is utilized as a deep learning (DL) technique to further improve the accuracy of classification. The performance of each algorithm is evaluated using metrics such as accuracy, precision and recall. The results demonstrated that the FFNN achieves superior accuracy compared to traditional ML classifiers, indicating its effectiveness in detecting malware in Android apps.

Spatial Segmentation for Laryngeal High-Speed Videoendoscopy in Connected Speech

Laryngeal high-speed videoendoscopy (HSV) is a powerful tool to study the detailed vibratory characteristics of the vocal folds. The use of HSV in connected speech enables us to study the transitory behaviors of the vocal folds during different vocalizations. The onset and offset of voicing contain critical information about the health and function of the vocal folds. In this work, HSV is used to study how the voicing begins/ends at the laryngeal level at the onset/offset of phonation. HSV data were obtained during production of connected speech from participants with non-pathological voices and patients with different neurogenic voice disorders. The data collection was performed using a Photron FASTCAM mini AX200 high-speed camera coupled with a flexible nasolaryngoscope. The glottal attack time and glottal offset time were measured at the onset and offset of different vocalizations, respectively, from the HSV data. The findings show differences in the onset and offset measures between the two groups of participants. The vocal fold vibratory behaviors will be discussed qualitatively and quantitatively using these measures. The use of HSV in connected speech could help us develop accurate voice assessment procedures to assess the vocal folds function during connected speech.

Utility of Laryngeal High-speed Videoendoscopy in Clinical Voice Assessment

<br><b>Introduction:</b> Advances in computer image analysis have enabled the use of new functional imaging methods in the diagnosis of laryngeal diseases. Particularly interesting techniques of dynamic laryngeal imaging involve High Speed Videoendoscopy (HSV). This still-developed technique allows to overcome the limitations of laryngovideostroboscopy (LVS) and a more detailed analysis of the glottal function based on the image of the actual vibrations of the vocal folds. It also enables the determination of objective coefficients parameterizing phonatory vibrations of the vocal folds.</br> <br><b>Aim:</b> The aim of this pilot study was to evaluate the use of a high-speed videoendoscopy set with laser illumination for the diagnosis of glottic pathology in ENT practice.</br> <br><b>Material and methods:</b> The study included 40 patients who underwent LVS followed by HSV. The modern HSV examination kit - Advanced Larynx Imager System (ALIS), used for the first time in a clinical setting in Poland, is characterized by significantly improved, compared to the previously used high-speed cameras, operational parameters - a light head, the possibility of continuous lighting operation without excessive heating of the head tip, registration of the image in full color scale. Thanks to such modernization, the safety and course of the examination do not differ from laryngoscopy conducted with commonly used recorders. The device owes some of these improvements to a laser illuminator which was used for the first time as the main light source in a high-speed camera. In the study, two cases were selected to present the results of HSV and the analysis of the generated kymograms - a woman with no glottic pathology and a man with a polyp of the right vocal fold. In the first case, the HSV examination compared with the LVS revealed a discrete glottis functional disorder in the form of a tendency to hyperphonation. The patient with an organic lesion had a clearly visible irregularity of vocal fold vibrations, which also allowed to trace mucosal wave disturbances related to its reflection from the pathological structure of the glottis and the formation of a return wave, both on the fold affected by the lesion and, to a lesser extent, contralaterally. The glottic dysfunctions observed in the studied patients were confirmed in the generated kymograms and the graphs of the glottal width waveform (GWW), as well as in the parameters calculated on their basis, assessing the frequency and amplitude of phonatory vibrations.</br> <br><b>Conclusions:</b> The use of high-speed videoendoscopy allows for a much more accurate assessment of the phonatory function of the glottis than in laryngovideostroboscopy. The presented HSV system allows for obtaining high quality kinematic images of the larynx, color fidelity, and contrast. The use of this technology in laryngological practice enables precise structural and functional assessment of the glottis and detection of discrete phonation disorders that elude the techniques used so far.</br&gt.

Laryngeal burns cause long-term voice disorders due to mucosal changes of the vocal folds. Inhalation injuries affect voice production and result in changes in the mucosal thickness and voice quality. A 47-year-old woman was transferred to our department with laryngeal burns sustained during a house fire. On laryngoscopic examination, mucosal waves of both vocal folds were not visualized due to the injury caused by inhalation of high-temperature toxic smoke. Hence, voice analysis, laryngoscopic examinations, and high-speed videoendoscopy (HSV) were performed to evaluate vocal fold vibrations. An absence of mucosal waves and a breathy and strained voice with a severe grade were noted. We report that voice quality was recovered to close to the normal state through multiple treatments such as medication, voice therapy, and counseling. This paper presents the unique case of a patient with laryngeal burns, in which vibrations of the vocal folds were observed using laryngoscopic examination and HSV. Voice samples before and after treatment were also analyzed. By observing the vibration pattern of the injured vocal fold, it is expected that appropriate diagnosis and treatment planning can be established in clinical practice.

Unilateral Vocal Fold Paralysis: Does the Paralyzed Vocal Fold Oscillate Slower or Faster Than the Healthy One?

SummaryIntroduction: The effects of voiced vibration technique can be assessed by laryngeal imaging. Kymographic images derived from high-speed videoendoscopy allow actual visualization of vocal folds vibration.Purpose: The aim of this study is to identify the immediate effects of the voiced vibration technique in healthy vocal folds using high-speed digital laryngeal imaging.Methods: Samples were obtained from 15 healthy subjects with no history of voice disorders (6 men and 9 women aged 21 to 43 years). High-speed videoendoscopy recordings were performed before and after the voiced vibration technique. Kymographic images were obtained using high-speed videoendoscopy. The vocal folds were examined in their open and closed positions and the characteristics of the opening and closing phases were determined. A customize computational routine was used quantify these parameters. The closing, opening, and speed quotients were also calculated.Results: In this study, women displayed statistically significant differences in opened phase (P = 0.05*), closed phase (P = 0.046*), and closing phase (P = 0.026*) phase characteristics. Men displayed the highest difference rate in opening time characteristics (P = 0.06). The closing and opening quotients for the female group showed significant differences (P = 0.029* and P = 0.049*, respectively). The speed quotient exhibited statistically significant differences in the male group (P = 0.048*). Conclusion: The kymographic images indicated that the immediate effect of the voiced vibration technique was smooth contact in healthy vocal fold vibration.

Lung cancer is one of the three deadliest diseases in the world and has rapidly developed. Based on this, researchers conducted research to predict the factors that influence lung cancer. One method to identify this is using data mining methods and classification techniques. Researchers used several popular algorithms in classification to make comparisons of the most accurate algorithms for lung cancer classification. The algorithms used include K-Nearest Neighbor, Random Forest Classifier, Logistic Regression, Linear SVM, Naïve Bayes, Decision Tree, Random Forest, Gradient Boosting, Kernel SVM, and MLPClassifier. The researcher used this algorithm because, in the research that the researcher found on the Kaggle platform, he examined the comparison of the algorithm using the breast cancer dataset. In previous studies, their researchers used SVM, which obtained an accuracy of 96.47%, Neural Networks of 97.06%, and Naïve Bayes with an accuracy of 91.18% to study breast cancer. The difference from previous research is that this study uses several existing algorithms in Machine Learning such as K-Nearest Neighbor, Random Forest Classifier, Logistic Regression, Linear SVM, Naïve Bayes, Decision Tree, Random Forest, Gradient Boosting, Kernel SVM, and MLPClassifier. In addition, this research was conducted to see whether the results of the accuracy of the algorithm that the researchers carried out using the lung cancer dataset had different results. The results of this study found that the more accurate algorithms were Random Forest and Gradient Boosting with an accuracy value of 100%, whereas in previous studies, it was the same. Still, Gradient Boosting had a higher accuracy value than Random Forest. Then, based on the data used in this study, the most influencing factors in predicting a diagnosis of lung cancer are obesity and coughing up blood. The results of this study found that the more accurate algorithms were Random Forest and Gradient Boosting with an accuracy value of 100%, whereas in previous studies, it was the same. Still, Gradient Boosting had a higher accuracy value than Random Forest. Then, based on the data used in this study, the most influencing factors in predicting a diagnosis of lung cancer are obesity and coughing up blood. The results of this study found that the more accurate algorithms were Random Forest and Gradient Boosting with an accuracy value of 100%, whereas in previous studies, it was the same. Still, Gradient Boosting had a higher accuracy value than Random Forest. Then, based on the data used in this study, the most influencing factors in predicting a diagnosis of lung cancer are obesity and coughing up blood.

You have accessThe ASHA LeaderWorld Beat1 May 2006Voice Research and Treatment in the Czech Republic Jan G. Svec and Frantisek Sram Jan G. Svec Google Scholar More articles by this author and Frantisek Sram Google Scholar More articles by this author https://doi.org/10.1044/leader.WB5.11062006.30 SectionsAbout ToolsAdd to favorites ShareFacebookTwitterLinked In The Czech Republic has a long tradition of voice research and voice treatment. In the 1850s the Czech-born physician J. N. Czermak played a crucial role in introducing the laryngeal mirror to clinical practice for diagnostics of voice disorders (Czermak, 1858). In 1922, M. Seeman, another prominent Czech physician, co-founded the field of phoniatrics-the medical specialty for voice, speech, and hearing disorders. In that decade, he introduced systematic preventive voice examinations for students of singing and acting and started to use laryngostroboscopy clinically. The activities of M. Seeman and his pupils gradually evolved into an educational system, called the “Prague Phoniatric School,” which since 1967 has had its center at the Phoniatric Clinic in Prague. The Prague Phoniatric School trained high-quality phoniatricians in former Czechoslovakia (K. Sedlácek, E. Sedlácková, F. Brohm, M. Sovák, A. Novák, F. Sram, I. Supácek, K. Vrticka, and many others) and in other countries behind the Iron Curtain (Hungary, Poland, Soviet Union, and Yugoslavia, among others). The phoniatric research activities in Czechoslovakia were numerous (for more information see, e.g., Sram, 1980 or Dlouhá, 2001). However, for political reasons, the results were rarely published in other than the Czech language and access to scientific literature written in English was limited. In 1945, the phoniatrician M. Sovák, the author of the now-classic Czech two-volume monograph on laryngostroboscopy (Sovák, 1945a; 1945b), established in Czechoslovakia the official field of logopedics-the pedagogical specialty dealing with care of people with communication disorders. After the “Velvet Revolution” in 1989 and the fall of the Iron Curtain, international collaboration with free-economy countries developed rapidly and the access to scientific information and literature published in English greatly improved. In 1993 Czechoslovakia was peacefully divided into the Czech Republic and Slovakia. Privatization led to improvement of the outpatient care of voice, modernization of ambulances (e.g., videolaryngostroboscopy is not uncommon), and assured individual care of patients in which prevention, early diagnostics, and treatment are the goals. The restructuring, however, also led to systemic problems in financing the outpatient care of voice and communication disorders. Rather than quality of medical care, the current insurance system emphasizes quantity, which is limited by regulation mechanisms. The grant support system suffers from extensive bureaucracy and the research budget is limited when compared with the world’s most developed countries. The Clinical System The Czech Phoniatric School views effective communication as an inseparable unity of voice, speech, and hearing processes. In clinical practice, this view implies that patients with voice problems automatically undergo basic hearing tests also in order to investigate the potential negative influence of impaired perception on voice. Preventive examination, diagnostics, medical treatment, as well as the voice rehabilitation in patients with voice disorders are the responsibility of phoniatricians, who collaborate with psychologists and voice pedagogues. Outpatient care is provided by a network of phoniatric ambulances distributed across the country. If phonosurgery is needed, the patient is referred to laryngologists at otolaryngologic clinics. Special diagnostic and therapeutic procedures are provided by phoniatric departments and otolaryngologic and related clinics. Speech rehabilitation is done mostly by logopedists. The field of phoniatrics, which is an independent medical subspecialty of otorhinolaryngology, is organized in the Czech Republic around the “Czech Phoniatric and Pedaudiologic Society.” The field of logopedics is organized around two separate societies, “The Association of Clinical Logopedics” and “The Logopedic Society of Milos Sovák,” the first of which is oriented clinically and the second one pedagogically. Current Research In 1994, collaboration of Czech and Dutch scientists led to development of videokymography, a low-cost, high-speed imaging method for examination of vocal fold vibrations (Svec & Schutte, 1996). After its development in the Netherlands, the method was introduced to clinical practice in Prague where it has become a routine complementary method to videostroboscopy for early diagnostics of voice disorders and for therapy evaluation at the Center for Communication Disorders, Medical Healthcom (Sram et al., 1997; Schutte et al., 1998; Svec, 2000). Since then, videokymography has spread as a clinical and research tool to clinics around the world, and kymographic display was adopted also for digital high-speed endoscopy. Czech institutes have been involved in large European projects, such as the Eureka!, “artificial larynx” and “NewVoice” projects, devoted to development of implantable prosthetic devices for patients after laryngectomy (Sram, 2005). Besides clinically oriented research, an interdisciplinary collaboration has been established between several clinical and technical institutes in the Czech Republic performing basic voice research. These efforts brought new information on spontaneous pitch jumps between chest and falsetto voice registers (Svec et al., 1999; Horácek et al., 2004), on resonance properties of the vocal folds (Svec et al., 2000), and led to the development of a new mathematical model for studying the effect of vocal-fold collisions (Horácek et al., 2005). Also, first finite-element models of the vocal tract were developed for Czech vowels (Dedouch et al., 2001; Dedouch et al., 2002) and used for quantifying the effect of cleft palate on voice quality (Vohradník et al., 2003; Vampola et al., 2005). The Group for Study of Voice and Speech was established at the Palacky University in Olomouc, organizing seminars and performing research in voice physiology and stuttering (e.g., Pesák, 2002; PeSák & Jindra, 2005). An increasing number of Czech participants were evident in the last five years at interdisciplinary events on voice, such as the Pan European Voice Conference (PEVOC), the Annual Voice Foundation’s Symposium “Care of the Professional Voice,” or the International Conference on Voice Physiology and Biomechanics. References Czermak J. N. (1858). Über den Kehlkopfspiegel.Wiener MedizinischeWochenschrift, 7, 196–198. Google Scholar Dedouch K., Horácek J., Vampola T., Kršek P., & Švec J. G. (2001). Mathematical modelling of male vocal tract.In Proceedings of the 2nd International Workshop on Models and Analysis of Vocal Emissions for Biomedical Applications. Firenze, Italy, Sept. 13–15, 2001 (CD ROM, 6p.). Firenze: University of Firenze, Department of Electronics and Telecommunications and Department of Physics. Google Scholar Dedouch K., Horácek J., Vampola T., Švec J. G., Kršek P., & Havlík R. (2002). Acoustic modal analysis of male vocal tract for Czech vowels.In Zolotarev I. (Ed.), Proceedings Interaction and Feedbacks 2002 (pp. 13–20). Prague: Institute of Thermomechanics AS CR. Google Scholar Dlouhá O. (2001). Phoniatrics: Czechoslovakia. Google Scholar Horácek J., Šidlof P., & Švec J. G. (2005). Numerical simulation of self-oscillations of human vocal folds with Hertz model of impact forces.Journal of Fluids and Structures, 20, 853–869. CrossrefGoogle Scholar Horácek J., Švec J. G., Veselý J., & Vilkman E. (2004). Bifurcations in excised larynges caused by vocal fold elongation.In International Conference on Voice Physiology and Biomechanics. Marseille, France. Aug. 18–20, 2004 (pp. 87–89). Google Scholar Pešák J. (2002). Pneumoobstruction of the tracheobronchial tree as a hypothetical cause of balbuties.Medical Hypotheses, 59, 458–461. CrossrefGoogle Scholar Pešák J., & Jindra P. (2005). Shortening of the front vibrating part of the vocal folds in phonation.Folia Phoniatrica et Logopaedica, 57, 1–8. CrossrefGoogle Scholar Schutte H. K., Švec J. G., & Šram F. (1998). First results of clinical application of videokymography.The Laryngoscope, 108, 1206–1210. CrossrefGoogle Scholar Sovák M. (1945a). Kmitání hlasivek ve svetle laryngostroboskopie [Vocal fold vibration in the light of laryngostroboscopy]. Praha: Ceská akademie ved a umení. Google Scholar Sovák M. (1945b). Stroboskopický výzkum hlasové pathologie [Stroboscopic research in voice pathology]. Praha: Ceská akademie ved a umení. Google Scholar Šram F. (1980). Tschechoslowakische Sozialistische Republik.In Wendler J. (Ed.), 75 Jahre Phoniatrie. Festschrift zu Ehren von Hermann Gutzmann sen. (pp. 186–206). Berlin: Humboldt-Universität. Google Scholar Šram F. (2005). Improving citizens’ well-being.EurekaNews, 69, 7. Google Scholar Šram F., Schutte H. K., & Švec J. G. (1997). Clinical applications of videokymography.In McCafferty G., Coman W., & Carroll R. (Eds.), XVI. World Congress of Otorhinolaryngology Head and Neck Surgery, Sydney 1997. Proceedings, vol. 2 (pp. 1681–1684). Bologna: Monduzzi Editore. Google Scholar Švec J. G. (2000). On vibration properties of human vocal folds: Voice registers, bifurcations, resonance characteristics, development and application of videokymography. (Doctoral Dissertation). Groningen, the Netherlands: University of Groningen. (http://dissertations.ub.rug.nl/faculties/medicine/2000/j.svec/) Google Scholar Švec J. G., Horácek J., Šram F., & Veselý J. (2000). Resonance properties of the vocal folds: In vivo laryngoscopic investigation of the externally excited laryngeal vibrations.Journal of the Acoustical Society of America, 108, 1397–1407. CrossrefGoogle Scholar Švec J. G., & Schutte H. K. (1996). Videokymography: High-speed line scanning of vocal fold vibration.Journal of Voice, 10, 201–205. CrossrefGoogle Scholar Švec J. G., Schutte H. K., & Miller D. G. (1999). On pitch jumps between chest and falsetto registers in voice: Data from living and excised human larynges.Journal of the Acoustical Society of America, 106, 1523–1531. CrossrefGoogle Scholar Vampola T., Horácek J., Veselý J., & Vokrál J. (2005). Modelling of influence of velopharyngeal insufficiency on phonation of vowel /a/.In Manfredi C. (Ed.), 4th International Workshop: Models and Analysis of Vocal Emissions for Biomedical Applications. Oct. 29–31, 2005, Firenze, Italy (pp. 43–46). Firenze, Italy: Firenze University Press. Google Scholar Vohradník M., Dedouch K., Vokrál J., & Švec J. G. (2003). Finite element model of supraglottal space in cleft palate.International Congress Series, 1240, 1145–1149. CrossrefGoogle Scholar Author Notes Jan G. Svec, a physicist and voice scientist, is currently at the Groningen Voice Research Lab, Department of Biomedical Engineering, University of Groningen in the Netherlands. He is also the current chairman of the Voice Committee of the International Association of Logopedics and Phoniatrics (IALP). Contact him at [email protected]. Frantisek Sram, is an otolaryngologist, phoniatrician, and a prominent representative of the Prague Phoniatric School (pupil of Seeman and Sedlácková). Currently, he is the director of the Centre for Communication Disorders, Medical Healthcom, Ltd. in Prague, the Czech Republic. He is a former board member of the International Association of Logopedics and Phoniatrics (IALP) and a recipient of the “Gutzmann Medal” for scientific work and international cooperation in phoniatrics. Contact him at [email protected]. Advertising Disclaimer | Advertise With Us Advertising Disclaimer | Advertise With Us Additional Resources FiguresSourcesRelatedDetails Volume 11Issue 6May 2006 Get Permissions Add to your Mendeley library History Published in print: May 1, 2006 Metrics Downloaded 293 times Topicsasha-topicsleader_do_tagleader-topicsasha-article-typesCopyright & Permissions© 2006 American Speech-Language-Hearing AssociationLoading ...

Background: Stroke remains a critical global health concern, disproportionately affecting individuals with hypertension which is a well-established, modifiable risk factor. Traditional risk scoring systems often fall short in accurately predicting stroke onset due to their reliance on fixed clinical thresholds and limited variable interaction modeling. As the complexity of health data increases, machine learning (ML) and explainable artificial intelligence (XAI) present powerful tools to uncover hidden patterns and enable precision risk stratification. Objectives: This study proposes a novel, interpretable machine learning framework that uses ensemble learning and SHapley Additive exPlanations (SHAP) to enhance stroke risk prediction in hypertensive patients. The objective is twofold: to improve the predictive power of stroke models and to provide clinically relevant insights that support real-time, data-driven decisions in preventive care. Methods: We utilized a real-world clinical dataset encompassing demographic, physiological, and behavioral variables associated with stroke. Data preprocessing included k-nearest neighbor imputation for missing values, normalization of continuous features, and class balancing via Synthetic Minority Oversampling Technique (SMOTE). A hybrid feature selection pipeline, combining the sparsityenforcing capabilities of LASSO regression with the iterative refinement of Recursive Feature Elimination (RFE), was employed to identify the most salient predictors. Multiple ML models, including logistic regression, deep neural networks, random forests, and gradient boosting machines, were trained and validated using cross-validation. SHAP values were computed post-training to enable individualized, interpretable model outputs. Results: Ensemble models, particularly Gradient Boosting and Random Forest, demonstrated superior discriminative performance, achieving AUC-ROC scores above 0.78 following class balancing. The integrated LASSO-RFE approach revealed age, hypertension status, and average glucose levels as dominant predictors across models. SHAP visualizations confirmed the influence of these features, while also highlighting nuanced interactions involving lifestyle and socioeconomic variables. Logistic Regression, when optimized for recall, achieved the highest balanced accuracy (0.77), reinforcing the clinical utility of simpler models when interpretability is paramount. Conclusion: This study introduces a transparent and high-performing machine learning framework for stroke risk prediction in hypertensive individuals. By integrating ensemble learning, hybrid feature selection, and explainable AI, the framework bridges the gap between predictive modeling and clinical applicability. These findings support the deployment of interpretable ML tools in routine care, enabling proactive interventions, personalized patient education, and ultimately, reduced stroke incidence.

Wideostrobokimografia w praktyce foniatrycznej

The prediction of wind energy generation is important to enhance the performance and dependability of renewable energy systems due to the rising demand for wind-generated electricity and advancements in wind energy technology competitiveness. This study leverages advanced machine learning (ML) and some other statistical and deep learning based time series forecasting models to enhance the accuracy of wind energy predictions. This comprehensive analysis includes nine ML models—Linear Regression, Random Forests (RF), Gradient Boosting Machines (GBM), Support Vector Machines (SVM), K-Nearest Neighbors (KNN), AdaBoost, XGBoost, Support Vector Regression (SVR), and Neural Networks—as well as Four time-series forecasting models—ARIMA, Temporal Convolutional Networks (TCNs), Long Short-Term Memory (LSTM) networks and GRU. Each ML model underwent rigorous cross-validation to ensure optimal performance. The assessment criteria utilized here comprised the Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and the R² Score. It was found that among the nine ML models, Random Forests, GBM and KNN consistently provided superior accuracy and robustness, making them the top choices for wind energy prediction whereas the performance of linear regression, SVM and SVR were very poor for the considered dataset. From the experiment, Random Forest, GBM, and KNN showed the best performance with low MSE values of 0.77, 1.95, and 1.51 respectively, while other models had MSEs above 7.5, with AdaBoost reaching 30. Their RMSEs (0.88, 1.40, 1.23) and MAEs (0.093, 0.73, 0.10) also indicate strong predictive accuracy compared to the rest.In this paper, time series forecasting, TCNs, LSTM and GRU networks showed strong capabilities in capturing temporal dependencies and trends within the wind energy data. Visualization techniques were employed to compare model performances comprehensively, providing clear insights into their predictive power. Therefore, this present study offers a robust framework for researchers and practitioners aiming to leverage machine learning and time series forecasting in the realm of renewable energy prediction.