Developing a Novel, Highly Accurate, Chronic Obstructive Pulmonary Disease (COPD) Machine Learning (ML) Model

UK COPD treatment: failing to progress

Integrating machine learning (ML) models into healthcare systems is a rapidly evolving field with the potential to revolutionize care delivery. This study aimed to classify fertility rates and identify significant predictors using ML models among reproductive women in Ethiopia. This study utilized eight ML models in 5864 reproductive-age women using Ethiopian Demographic Health Survey (EDHS), 2019 data. Phyton programming language was used to develop these models. Predictors of fertility rate were determined using the feature important techniques. The performance of models was evaluated using accuracy, area under the curve (AUC), precision, recall, F1-score, specificity, and sensitivity. The mean age of participants was 32.7 (± 5.6) years. The random forest classifier (accuracy = 0.901 and AUC = 0.961) followed by a one-dimensional convolutional neural network (accuracy = 0.899 and AUC = 0.958), logistic regression (accuracy = 0.874 and AUC = 0.937), and gradient boost classifier (accuracy = 0.851 and AUC 0.927) were the top performing ML models. Family size, age, occupation, and education with an average importance score of 0.198, 0.151, 0.118, and 0.081, respectively were the top significant predictors of the fertility rate. The best ML models to classify and predict fertility rates were random forest, one-dimensional convolutional neural network, logistic regression, and gradient boost classifier. The findings on important factors of fertility rate can inform targeted public health, programs that address disparities related to family size, occupation, education, and other socioeconomic factors.

The objective of this study was to develop a machine learning (ML) application to determine the optimal dosage of sodium hypochlorite (NaOCl) to curtail corrosion and odor by H2 S in the headworks of a water resource recovery facility (WRRF) without overly consuming volatile fatty acids (VFAs) that are essential for the enhanced biological phosphorus removal. Given the highly diverse datasets available, three subproblems were formulated, and three cascaded ML modules were developed accordingly. The final ML models, chosen based on performance, were able to predict various targeted variables. More specifically, in Module 1, a recurrent neural network (RNN) was designed to predict wastewater characteristics. In Module 2, a random forest (RF) classifier and a support vector machine (SVM) classifier were built with the information from Module 1 along with other datasets to predict the concentrations of VFAs and H2 S, respectively. Finally, in Module 3, with the information obtained from Module 2, another RF classifier was developed to predict NaOCl dosage to reduce H2 S but keeping VFAs within the target range. These efforts are relevant and informative for WRRFs that are considering developing Intelligent Water Systems to predict the wastewater characteristics to make operational improvements. PRACTITIONER POINTS: A recurrent neural network (RNN) using long short-term memory (LSTM) successfully predicted influent wastewater parameters. A support vector machine classifier predicted hydrogen sulfide (H2 S) with 97.6% accuracy. The concentration of VFAs, an important parameter in EBPR, was predicted using a random forest classifier with 93.4% accuracy. The optimal NaOCl dosage for H2 S control can be predicted with a random forest classifier using H2 S, VFAs, and flow.

P125. Development of a novel ensemble machine learning algorithm for prediction of complications and readmission after anterior cervical spinal fusion

Machine learning (ML) models provide more choices to patients with diabetes mellitus (DM) to more properly manage blood glucose (BG) levels. However, because of numerous types of ML algorithms, choosing an appropriate model is vitally important. In a systematic review and network meta-analysis, this study aimed to comprehensively assess the performance of ML models in predicting BG levels. In addition, we assessed ML models used to detect and predict adverse BG (hypoglycemia) events by calculating pooled estimates of sensitivity and specificity. PubMed, Embase, Web of Science, and Institute of Electrical and Electronics Engineers Explore databases were systematically searched for studies on predicting BG levels and predicting or detecting adverse BG events using ML models, from inception to November 2022. Studies that assessed the performance of different ML models in predicting or detecting BG levels or adverse BG events of patients with DM were included. Studies with no derivation or performance metrics of ML models were excluded. The Quality Assessment of Diagnostic Accuracy Studies tool was applied to assess the quality of included studies. Primary outcomes were the relative ranking of ML models for predicting BG levels in different prediction horizons (PHs) and pooled estimates of the sensitivity and specificity of ML models in detecting or predicting adverse BG events. In total, 46 eligible studies were included for meta-analysis. Regarding ML models for predicting BG levels, the means of the absolute root mean square error (RMSE) in a PH of 15, 30, 45, and 60 minutes were 18.88 (SD 19.71), 21.40 (SD 12.56), 21.27 (SD 5.17), and 30.01 (SD 7.23) mg/dL, respectively. The neural network model (NNM) showed the highest relative performance in different PHs. Furthermore, the pooled estimates of the positive likelihood ratio and the negative likelihood ratio of ML models were 8.3 (95% CI 5.7-12.0) and 0.31 (95% CI 0.22-0.44), respectively, for predicting hypoglycemia and 2.4 (95% CI 1.6-3.7) and 0.37 (95% CI 0.29-0.46), respectively, for detecting hypoglycemia. Statistically significant high heterogeneity was detected in all subgroups, with different sources of heterogeneity. For predicting precise BG levels, the RMSE increases with a rise in the PH, and the NNM shows the highest relative performance among all the ML models. Meanwhile, current ML models have sufficient ability to predict adverse BG events, while their ability to detect adverse BG events needs to be enhanced. PROSPERO CRD42022375250; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=375250.

Introduction. Chronic obstructive pulmonary disease (COPD) is one of the most important problems of modern health care byall over the world [55.67], cause of the prevalence, frequency of complications of this disease and mortality from it constantly increasing. The relevance of COPD is evidenced by the results of modern epidemiological studies, which indicates that over the past few decades, the incidence, mortality and disability rates have increased significantly. [70]. According to publishing journal Lancet in 2020 "Global burden of 369 diseases and injuries in 204 countries and territories in 1990-2019" COPD among all age groups by cause of mortality ranks 6th in the world and 4th in the age group from 50 to 74 years, about 2.8 million people die from COPD annually, which is 4.8% of all causes of death [22.49]. In 2021, it claimed the lives of 3.5 million people, it is approximately 5% of all deaths worldwide.[62] In 2021 it took the lives of 3.5 million people - this is approximately 5% of all deaths in the world. Thus, due to the increasing of frequency rates, mortality and disabilityin COPD, this disease is a medical and social problem of modern healthcare. Objective: to analyze the prevalence and risk factors for the development of chronic obstructive pulmonary disease (COPD). Search strategy.A literature search was conducted in the following databases: PubMed, Medline, eLibrary, Google Scholar. Search depth was 10 years.263 sources were found totally.70 publications were selected for analysis. Inclusion criteria: publications in Russian and English, since 2014 to 2024, the results of authentic research, meta-analyses, clinical cases, dissertations on the research topic and sources were found manually; Exclusion criteria: publications without clear formulation of results and conclusions; articles, abstracts with paid access. Several sources published earlier than the given period (1999, 1990) were also taken for analysis in 10 years, due to the content of the necessary data to make comparison. Results and conclusions. The literature analysis showed that the high prevalence of COPD is becoming a heavy burden for society and is a socio-economic evil for most developed countries. According to the forecasts of WHO experts, COPD will take the 3rd place among other causes of mortality by 2030 and will overtake mortality from injuries and accidents. Risk factors are the spreading epidemic of smoking,stable environmental pollution and recurring respiratory infectious diseases. According to scientists, COPD is the only disease, the mortality rate from which has increased by 25.5% over the past 10 years. Consequently, COPD is currently becoming a global international health problem. Актуальность:Хроническая обструктивная болезнь легких (ХОБЛ) - одна из важнейших проблем современного здравоохранения во всем мире [55,67], т. к. распространенность, частота осложнений этой болезни и смертность от нее постоянно возрастает. Доказательством актуальности ХОБЛ, являются результаты современных эпидемиологических исследований, которые свидетельствуют о том, что за последние нескольких десятилетий значительно выросли показатели частоты, смертности и инвалидности. [70].В журнале Lancet опубликованные данные в 2020 г. «Глобальное бремя 369 болезней и травм в 204 странах и территориях 1990-2019» ХОБЛ среди всех возрастных групп по причине смертности занимает 6 место в мире и 4 место в возрастной группе от 50 до 74 лет, ежегодно от ХОБЛ умирает около 2.8 млн человек, что составляет 4.8% всех причин смерти [22, 49]. В 2021 г. унесла жизни 3,5млн человек – это примерно 5% всех случаев смерти в мире. [62] Таким образом в связи с возрастанием показателей частоты, смертности и инвалидности при ХОБЛ, это заболевания является медико-социальной проблемой современного здравоохранения. Цель: анализраспространенности и факторов риска развития хронической обструктивной болезни легких (ХОБЛ) Стратегия поиска.Поиск литературы проведен в базах данных: PubMed, Medline, eLibrary, Google Scholar. Глубина поиска - 10 лет. Всего было найдено 263 источника. Для анализа были отобраны 70 публикаций. Критерии включения: публикации на русском и английском языках, с 2014 года по 2024 год, результаты оригинальных исследований, мета анализы, клин.случаи, диссертации по теме исследования и источники, найденные ручным способом. Критерии исключения: публикации без четкого формулирования результатов и выводов; статьи, тезисы, имеющие платный доступ. Также были взяты для анализа несколько источников, опубликованных ранее указанного периода (1999, 1990), в 10 лет, поскольку содержали необходимые данные для проведения сравнения. Результаты и выводы.Анализ литературы показал, что высокая распространенность ХОБЛ становится тяжелым бременем для общества и несет социально-экономическое зло большинству развитых стран мира. По прогнозам Экспертов ВОЗ ХОБЛ к 2030 году среди других причин летальности будет занимать 3-е место и опередит летальность от травм и несчастных случаев. Факторами риска являются распространяющаяся эпидемия курения, непрекращающиеся загрязнения окружающей среды и повторяющиеся респираторные инфекционные заболевания. По мнению ученых, ХОБЛ является единственной болезнью, летальность от которой, за последние 10 лет, выросла на 25,5%. Следовательно, ХОБЛ в настоящее время становиться глобальной международной проблемой здравоохранения. Өзектілігі:Өкпенің созылмалы обструктивті ауруы (ӨСОА) дүниежүзіндегізаманауиденсаулықсақтаудыңмаңыздымәселелерініңбіріболыптабылады [55.67], өйткенібұлаурудыңтаралуы, асқынужиілігіжәнеоданболатынөлім-жітімүнемі өсіпкеледі. ӨСОАөзектілігінқазіргіэпидемиологиялықзерттеулердіңнәтижелерідәлелдейді, бұлсоңғыбірнешеонжылдықтасырқаттанушылық, өлім-жітімжәнемүгедектіккөрсеткіштеріайтарлықтай өскенінкөрсетеді. [70]. Lancet журналында 2020 жылы жарияланған «204 ел мен аумақтағы 369 ауруменжарақаттыңжаһандықауыртпалығы 1990–2019»ӨСОАөлімсебебібойыншабарлықжастоптарыарасындаәлемде 6-шыжәне 50-ден 74 жасқадейінгі 4-шіорында, жылсайыншамамен 2,8 миллионадамқайтысболады. өлім [22.49]. 2021 жылы ол 3,5 миллион адамныңөмірінқиды, бұлдүниежүзіндегібарлықөлімнің шамамен 5%-ын құрады.[62] Осылайша, ӨСОА-дағыаурушаңдық, өлімжәнемүгедектіккөрсеткіштерініңартуынабайланыстыбұлаурузаманауиденсаулықсақтаудыңмедициналық-әлеуметтік мәселесіболыптабылады.. Мақсаты: Өкпенің созылмалы обструктивті ауруларының (ӨСОА) таралуыменқауіпфакторларынталдау. Іздеу стратегиясы.Келесі дерекқорлардаәдебиеттердііздеужүргізілді: PubMed, Medline, eLibrary, Google Scholar. Іздеутереңдігі– 10 жыл. Барлығы 263 дереккөзтабылды. Талдауүшін 70 басылымтаңдалды. Қосылукритерийлері: 2014 жылдан 2024 жылғадейінорысжәнеағылшынтілдеріндегіжарияланымдар, түпнұсқазерттеулердіңнәтижелері, мета-талдаулар, клиникалықжағдайлар, зерттеутақырыбы бойынша диссертациялар жәнеқолментабылғандереккөздер; Алыптастаукритерийлері: нәтижелерменқорытындыларнақтытұжырымдалмағанжарияланымдар; ақылықолжетімдімақалалар, тезистер. Көрсетілгенмерзімненбұрын (1999, 1990 ж.) жарияланғанбірнешедереккөздер де 10 жыл ішінде талдауғаалынды, өйткеніолардасалыстыруүшінқажеттідеректерболды. Нәтижелерменқорытындылар. Нәтижелерменқорытындылар. Әдебиеттергешолу COPD-ныңжоғарытаралуықоғамғаауыржүкжәнеәлемніңкөптегендамығанелдеріүшінәлеуметтік-экономикалықауыртпалықекенінкөрсетті. ДДҰсарапшыларыныңпікірінше, ӨСОА 2030 жылғақарайжарақаттарменжазатайымоқиғаларданболатынөлім-жітімненасыптүсетінөлімніңүшіншісебебіболады. Тәуекелфакторларынатемекішегуэпидемиясыныңтаралуы, қоршағанортаныңтұрақтыластануыжәнеқайталанатынреспираторлықинфекцияларжатады. Ғалымдардыңайтуынша, ӨСОА–соңғы 10 жылдаөлімкөрсеткіші 25,5%-ғаөскенжалғызауру. Демек, COPD қазіржаһандықхалықаралықденсаулықмәселесінеайналуда.

Wear mechanisms and severity level classification in iron ore transfer chute linings by propagating regional labels coded as embedding deep learning vectors

IntroductionThere has been an increased demand for more accurate prediction tools to aid clinical decision-making regarding disease diagnosis prognosis for coronary artery disease(CAD) patients. Patients undergoing CABG surgery are older and a larger number have had previous heart surgery. Consequently, mortality after CABG is expected to increase despite procedural advances.
 Objectives and ApproachThis study aims to compare the predictive performance of random forest(RF) and logistic regression(LR) classifiers for predicting 30-day and 1-year post-operative mortality risk in CAD patients who underwent CABG. Data was obtained by linking the Alberta Provincial Project for Outcome Assessment in Coronary Heart Disease(APPROACH) registry, a prospective longitudinal data of patients undergoing cardiac catheterization in Alberta, Canada, to vital statistics database. All patients who underwent first-time isolated CABG between January 1, 2007 and December 31, 2012 were included in the analysis. Area under the receiver operating curve(AUC) was used to compare the predictive performance of LR and RF regression.
 ResultsOf the 4,908 eligible subjects who underwent isolated CABG during the study period, mortality estimates of 30-day and 1-year post CABG surgery were 1.59% and 3.85%, respectively. Descriptive analysis revealed that age, sex, hypertension, dialysis, cerebrovascular disease, chronic obstructive pulmonary disease, and chronic heart failure were associated with 30-day and 1-year mortality. The accuracy of the LR and RF regression classifiers in predicting 30-day mortality were 74.1, and 99.7%, respectively. While the accuracy of the former and latter classifiers in predicting 1-year post CABG mortality were 74% and 97.4%, respectively.
 Conclusion/ImplicationsThis study shows that RF classifier results in better predictive accuracy than LR in predicting post-operating mortality risk in CAD patients. Machine learning models are potentially usefully for developing clinical prediction models that can be used to aid the monitoring of post-discharge outcomes in the management of cardiovascular diseases.

Chronic obstructive pulmonary disease (COPD), an incurable chronic respiratory disease, has become a major public health problem. The relationship between the composition of intestinal microbiota and the important clinical factors affecting COPD remains unclear. This study aimed to identify specific intestinal microbiota with high clinical diagnostic value for COPD. The fecal microbiota of patients with COPD and healthy individuals were analyzed by 16S rDNA sequencing. Random forest classification was performed to analyze the different intestinal microbiota. Spearman correlation was conducted to analyze the correlation between different intestinal microbiota and clinical characteristics. A microbiota-disease network diagram was constructed using the gut MDisorder database to identify the possible pathogenesis of intestinal microorganisms affecting COPD, screen for potential treatment, and guide future research. No significant difference in biodiversity was shown between the two groups but significant differences in microbial community structure. Fifteen genera of bacteria with large abundance differences were identified, including Bacteroides, Prevotella, Lachnospira, and Parabacteroides. Among them, the relative abundance of Lachnospira and Coprococcus was negatively related to the smoking index and positively related to lung function results. By contrast, the relative abundance of Parabacteroides was positively correlated with the smoking index and negatively correlated with lung function findings. Random forest classification showed that Lachnospira was the genus most capable of distinguishing between patients with COPD and healthy individuals suggesting it may be a potential biomarker of COPD. A Lachnospira disease network diagram suggested that Lachnospira decreased in some diseases, such as asthma, diabetes mellitus, and coronavirus disease 2019 (COVID-19), and increased in other diseases, such as irritable bowel syndrome, hypertension, and bovine lichen. The dominant intestinal microbiota with significant differences is related to the clinical characteristics of COPD, and the Lachnospira has the potential value to identify COPD.

AimsThe aim of this study was to clarify the effect of β-blockers (BBs) on respiratory function and survival in patients with chronic obstructive pulmonary disease with cardiovascular disease (CVD), as well as the difference between the effects of cardioselective and noncardioselective BBs.Methods and resultsWe searched for relevant literature in four electronic databases, namely, PubMed, EMBASE, Cochrane Library, and Web of Science, and compared the differences in various survival indicators between patients with chronic obstructive pulmonary disease taking BBs and those not taking BBs. Forty-nine studies were included, with a total sample size of 670 594. Among these, 12 studies were randomized controlled trials (RCTs; seven crossover and five parallel RCTs) and 37 studies were observational (including four post hoc analyses of data from RCTs). The hazard ratios (HRs) of chronic obstructive pulmonary disease exacerbation between patients with chronic obstructive pulmonary disease who were not treated with BBs and those who were treated with BBs, cardioselective BBs, and noncardioselective BBs were 0.77 [95% confidence interval (CI) 0.67, 0.89], 0.72 [95% CI 0.56, 0.94], and 0.98 [95% CI 0.71, 1.34, respectively] (HRs <1 indicate favouring BB therapy). The HRs of all-cause mortality between patients with chronic obstructive pulmonary disease who were not treated with BBs and those who were treated with BBs, cardioselective BBs, and noncardioselective BBs were 0.70 [95% CI 0.59, 0.83], 0.60 [95% CI 0.48, 0.76], and 0.74 [95% CI 0.60, 0.90], respectively (HRs <1 indicate favouring BB therapy). Patients with Chronic obstructive pulmonary disease treated with cardioselective BBs showed no difference in ventilation effect after the use of an agonist, in comparison with placebo. The difference in mean change in forced expiratory volume in 1 s was 0.06 [95% CI −0.02, 0.14].ConclusionThe use of BBs in patients with chronic obstructive pulmonary disease is not only safe but also reduces their all-cause and in-hospital mortality. Cardioselective BBs may even reduce chronic obstructive pulmonary disease exacerbations. In addition, cardioselective BBs do not affect the action of bronchodilators. Importantly, BBs reduce the heart rate acceleration caused by bronchodilators. BBs should be prescribed freely when indicated in patients with chronic obstructive pulmonary disease and heart disease.

Concussion injuries remain a significant public health challenge. A significant unmet clinical need remains for tools that allow related physiological impairments and longer-term health risks to be identified earlier, better quantified, and more easily monitored over time. We address this challenge by combining a head-mounted wearable inertial motion unit (IMU)-based physiological vibration acceleration (“phybrata”) sensor and several candidate machine learning (ML) models. The performance of this solution is assessed for both binary classification of concussion patients and multiclass predictions of specific concussion-related neurophysiological impairments. Results are compared with previously reported approaches to ML-based concussion diagnostics. Using phybrata data from a previously reported concussion study population, four different machine learning models (Support Vector Machine, Random Forest Classifier, Extreme Gradient Boost, and Convolutional Neural Network) are first investigated for binary classification of the test population as healthy vs. concussion (Use Case 1). Results are compared for two different data preprocessing pipelines, Time-Series Averaging (TSA) and Non-Time-Series Feature Extraction (NTS). Next, the three best-performing NTS models are compared in terms of their multiclass prediction performance for specific concussion-related impairments: vestibular, neurological, both (Use Case 2). For Use Case 1, the NTS model approach outperformed the TSA approach, with the two best algorithms achieving an F1 score of 0.94. For Use Case 2, the NTS Random Forest model achieved the best performance in the testing set, with an F1 score of 0.90, and identified a wider range of relevant phybrata signal features that contributed to impairment classification compared with manual feature inspection and statistical data analysis. The overall classification performance achieved in the present work exceeds previously reported approaches to ML-based concussion diagnostics using other data sources and ML models. This study also demonstrates the first combination of a wearable IMU-based sensor and ML model that enables both binary classification of concussion patients and multiclass predictions of specific concussion-related neurophysiological impairments.

Low nuclear grade ductal carcinoma in situ (DCIS) patients can adopt proactive management strategies to avoid unnecessary surgical resection. Different personalized treatment modalities may be selected based on the expression status of molecular markers, which is also predictive of different outcomes and risks of recurrence. DCIS ultrasound findings are mostly non mass lesions, making it difficult to determine boundaries. Currently, studies have shown that models based on deep learning radiomics (DLR) have advantages in automatic recognition of tumor contours. Machine learning models based on clinical imaging features can explain the importance of imaging features. The available ultrasound data of 349 patients with pure DCIS confirmed by surgical pathology [54 low nuclear grade, 175 positive estrogen receptor (ER+), 163 positive progesterone receptor (PR+), and 81 positive human epidermal growth factor receptor 2 (HER2+)] were collected. Radiologists extracted ultrasonographic features of DCIS lesions based on the 5th Edition of Breast Imaging Reporting and Data System (BI-RADS). Patient age and BI-RADS characteristics were used to construct clinical machine learning (CML) models. The RadImageNet pretrained network was used for extracting radiomics features and as an input for DLR modeling. For training and validation datasets, 80% and 20% of the data, respectively, were used. Logistic regression (LR), support vector machine (SVM), random forest (RF), and eXtreme Gradient Boosting (XGBoost) algorithms were performed and compared for the final classification modeling. Each task used the area under the receiver operating characteristic curve (AUC) to evaluate the effectiveness of DLR and CML models. In the training dataset, low nuclear grade, ER+, PR+, and HER2+ DCIS lesions accounted for 19.20%, 65.12%, 61.21%, and 30.19%, respectively; the validation set, they consisted of 19.30%, 62.50%, 57.14%, and 30.91%, respectively. In the DLR models we developed, the best AUC values for identifying features were 0.633 for identifying low nuclear grade, completed by the XGBoost Classifier of ResNet50; 0.618 for identifying ER, completed by the RF Classifier of InceptionV3; 0.755 for identifying PR, completed by the XGBoost Classifier of InceptionV3; and 0.713 for identifying HER2, completed by the LR Classifier of ResNet50. The CML models had better performance than DLR in predicting low nuclear grade, ER+, PR+, and HER2+ DCIS lesions. The best AUC values by classification were as follows: for low nuclear grade by RF classification, AUC: 0.719; for ER+ by XGBoost classification, AUC: 0.761; for PR+ by XGBoost classification, AUC: 0.780; and for HER2+ by RF classification, AUC: 0.723. Based on small-scale datasets, our study showed that the DLR models developed using RadImageNet pretrained network and CML models may help predict low nuclear grade, ER+, PR+, and HER2+ DCIS lesions so that patients benefit from hierarchical and personalized treatment.

In this article, we explore to what extent it is possible to leverage on very small data to build machine learning (ML) models that predict acute exacerbations of chronic obstructive pulmonary disease (AECOPD). We build ML models using the small data collected during the eHealth Diary telemonitoring study between 2013 and 2017 in Sweden. This data refers to a group of multimorbid patients, namely 18 patients with chronic obstructive pulmonary disease (COPD) as the major reason behind previous hospitalisations. The telemonitoring was supervised by a specialised hospital-based home care (HBHC) unit, which also was responsible for the medical actions needed. We implement two different ML approaches, one based on time-dependent covariates and the other one based on time-independent covariates. We compare the first approach with standard COX Proportional Hazards (CPH). For the second one, we use different proportions of synthetic data to build models and then evaluate the best model against authentic data. To the best of our knowledge, the present ML study shows for the first time that the most important variable for an increased risk of future AECOPDs is "maintenance medication changes by HBHC". This finding is clinically relevant since a sub-optimal maintenance treatment, requiring medication changes, puts the patient in risk for future AECOPDs. The experiments return useful insights about the use of small data for ML.

Acute ischemic stroke (AIS) is a leading cause of global mortality and disability worldwide. Machine learning (ML) models enhance prognostic accuracy by analysing complex, multidimensional clinical data. The aim of this systematic review and meta-analysis is to identify the gaps in the current ML models, along with methodological and performance outcomes in AIS. Further, the study objective was to identify the most frequently used algorithms and compare their relative effectiveness, thereby supporting future research to develop novel ML-based predictive models for stroke care management. The systematic review followed PRISMA guidelines with PROSPERO registration. A comprehensive search was performed in PubMed, Scopus, and Web of Science using MeSH keywords. Data extraction captured study characteristics, ML algorithms, and outcome metrics. We used the PROBAST and TRIPOD-AI to assess the qualities and bias of included studies. Meta-analysis of AUC values across ML models were conducted to synthesize model performance used a random-effects model to summarize and analyse the data and assessed heterogeneity (I 2) statistic using SPSS-29 and R-Studio-4.2.0. A total of 14 studies were included in the systematic review, with 12 eligible for meta-analysis. The pooled AUC of ML models was 0.87 (95% CI, 0.83-0.91), demonstrating strong predictive performance despite substantial heterogeneity (I 2 = 99%). Random forest (RF) (AUC = 0.85) and SVM (AUC = 0.82) outperformed logistic regression (LR) (AUC = 0.75), while XGBoost showed stable performance (AUC = 0.82); heterogeneity was mainly driven by study design, publication year, and algorithm type (p < 0.001). ML-based models show potential for improving prognostic assessment in AIS; however, substantial heterogeneity and methodological limitations across studies limit the generalizability of pooled performance estimates. https://www.crd.york.ac.uk/PROSPERO/view/CRD420251033217, (Registration number: CRD420251033217).

Chronic obstructive pulmonary disease (COPD) remains underdiagnosed and undertreated. Because screening asymptomatic individuals for COPD is not recommended, several case-finding tools have been explored. The COPD Assessment in Primary Care to Identify Undiagnosed Respiratory Disease and Exacerbation Risk (CAPTURE) questionnaire and peak expiratory flow (PEF) rate (CAPTURE tool) have been tested in the primary care setting, with disappointing results. We hypothesized that these tools could yield better results in a computed tomography lung screening (CTLS) program, where individuals have a history of cigarette smoking and higher prevalence of COPD. We recruited 67 patients referred to a CTLS program at a single institution. Participants completed the CAPTURE and COPD Assessment Test (CAT) questionnaires. Spirometric testing was completed with a portable device and low-dose chest computed tomography (CT) was performed according to a standard protocol. The group's mean age was 66 ±7 years, 43% were male, with a 37 pack-year smoking history. Eighteen (27%) had COPD (forced expiratory volume in 1 second of 60 ±22% predicted) and a higher CAT score (12 [interquartile range (IQR) 6-15]) compared to the nonobstructed group (CAT=7 [IQR 3-10]), p<0.02. Combining the CAPTURE questionnaire with PEF generated the best COPD diagnostic criteria (sensitivity=0.82, specificity=0.73, area under the receiver operating curve [AUROC]=0.784), followed by combining the CAPTURE questionnaire and emphysema presence (sensitivity=0.73, specificity=0.71, AUROC=0.779). The CAPTURE questionnaire alone had a sensitivity=0.766, specificity=0.616, and AUROC=0.669. The CAPTURE tool is an effective method to find COPD cases in lung cancer screenings. A CT diagnosis of emphysema can substitute peak flow in this population.