Introduction: The monitoring of respiratory patterns is crucial in the management of respiratory diseases, but in many cases, it still relies on subjective and visual assessment. The use of healthcare technologies based on artificial intelligence (AI) can, in these contexts, enhance clinical decision-making by providing a more objective and accurate analysis. Given the high prevalence of acute and chronic respiratory diseases, the implementation of a device capable of detecting variables such as flow, volume, and time becomes a priority for more effective diagnosis and therapeutic planning. Objective: Evaluate the accuracy, validity, and usability of an intelligent system for monitoring the respiratory pattern of patients at risk of acute respiratory failure. Methods: This is a prospective cohort study that will be conducted in the emergency departments of the Otávio de Freitas Hospital and Urgent Care Units (UPAs). The sample will consist of volunteers of both sexes, aged 18 years or older, breathing spontaneously, and suspected of having acute respiratory failure. Screening will be performed daily, where sociodemographic information, blood gas data, laboratory results, and additional information will be collected. When indicated, pulmonary function tests, respiratory muscle strength tests, and diaphragmatic ultrasound will be conducted. Respiratory pattern data will be collected using the Respiratory Diagnostic Assistant. Statistical analysis will be performed according to data modeling and treatment, adopting significant differences with p \< 0.05. Expected Results: It is expected that the results of this study will provide quantitative data on the respiratory pattern of volunteers suspected of having acute respiratory failure. This information will be integrated into a database with the aim of enhancing the device's ability to detect changes in respiratory patterns, as well as contributing to the development of artificial intelligence capable of accurately and efficiently identifying these changes.
Monitoring respiratory patterns is essential in the management of respiratory diseases, yet it often still relies on subjective and visual assessments. Health technologies based on artificial intelligence (AI) can enhance clinical decision-making by providing more objective and accurate analyses. Given the high prevalence of acute and chronic respiratory diseases, implementing devices capable of detecting variables such as flow, volume, and time has become a priority for enabling more effective diagnosis and therapeutic planning. This study aims to evaluate the accuracy, validity, and usability of an intelligent system for monitoring respiratory patterns in patients at risk of acute respiratory failure. This is a prospective cohort study to be conducted in the emergency departments of Hospital Otávio de Freitas and Urgent Care Units (UPAs), involving volunteers of both sexes, aged 18 years or older, breathing spontaneously, and under suspicion of acute respiratory failure. Daily screening will be performed, collecting sociodemographic, blood gas, laboratory, and additional clinical data. When indicated, pulmonary function tests, respiratory muscle strength assessments, and diaphragmatic ultrasonography will be performed. Respiratory patterns will be recorded using the Respiratory Diagnostic Assistant (RDA), with data collected directly at the patient's bedside, preferably in a seated position or, if not feasible, in the supine position with the head of the bed elevated to 30°. The device will be used with appropriate protective filters and a face mask properly fitted to the patient, preceded by a clinical evaluation that includes peripheral oxygen saturation, respiratory rate, and signs of respiratory distress. The protocol comprises three minutes of spontaneous basal breathing to record time, volume, and flow variables. Simultaneously with the RDA assessment, respiratory parameters will also be measured using conventional methods-manual or multiparameter monitor respiratory rate, arterial blood gas analysis (when clinically indicated), pulse oximetry, and spirometry-serving as reference standards for diagnostic accuracy analysis. The collected data will be analyzed using correlation coefficients, agreement tests, and ROC curves to assess the sensitivity, specificity, and overall performance of the RDA algorithm. In addition to accuracy, clinical usability of the device will be evaluated using the System Usability Scale (SUS) questionnaire, assessing interface clarity, ease of mask fitting, examination duration, data interpretation, and clinical applicability. The mean SUS score will be used as an indicator of acceptance, with values ≥68 considered satisfactory. All clinical and technical data will be securely stored on an encrypted server with access restricted to the research team, in compliance with the Declaration of Helsinki, Brazilian regulations, and the General Data Protection Law (LGPD). Participation will be voluntary, requiring the signing of an informed consent form (ICF) by patients or, when applicable, their legal representatives. Data will be stored in Microsoft Excel 2016 (Microsoft®, USA) and analyzed using SPSS Statistics v.22.0. Descriptive variables will be presented as means and standard deviations or as medians and interquartile ranges, depending on their distribution, assessed using the Kolmogorov-Smirnov test. The analysis will be guided by three main hypotheses: (1) Accuracy - to assess whether the intelligent monitoring system provides superior performance compared to conventional methods in detecting respiratory pattern alterations, using performance metrics such as accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and area under the ROC curve (AUC), with comparisons made using McNemar's test for paired binary data and AUC comparisons using the z-test; (2) Validation - to verify the system's precision and reliability using the Intraclass Correlation Coefficient (ICC) and Bland-Altman analysis, as well as Cohen's Kappa index for categorical variables, with ICC values above 0.75 indicating satisfactory validation; (3) Usability - to assess system acceptance based on SUS scores, complemented by analysis of average training time and operational error rates, using the Student's t-test or Mann-Whitney test depending on data distribution. The study is expected to generate robust quantitative data on the respiratory patterns of patients with suspected acute respiratory failure, contributing to the refinement of the device, the development of more accurate AI algorithms, and its safe and effective integration into clinical practice.
Study Type
OBSERVATIONAL
Enrollment
300
Respiratory pattern assessment and continuous monitoring will be conducted utilizing the Respiratory Diagnostic Assistant, a device capable of providing comprehensive quantitative evaluation of respiratory variables including frequency, volume, flow rates, inspiratory/expiratory timing parameters, and respiratory entropy analysis, as well as qualitative analysis of respiratory pattern curves for volume and flow dynamics, incorporating entropy measurements for assessment of respiratory pattern complexity and variability.
Diaphragmatic mobility assessment will be conducted using diaphragmatic ultrasonography, a method capable of providing comprehensive quantitative evaluation of diaphragmatic excursion parameters including range of motion, contraction velocity, muscle thickening during inspiration and expiration, as well as qualitative analysis of diaphragm muscle morphology and echogenicity, incorporating craniocaudal displacement measurements for assessment of contractile function and early detection of diaphragmatic dysfunction."
espiratory muscle electrical activity assessment will be conducted using surface electromyography, a method capable of providing comprehensive quantitative evaluation of muscle activation parameters including electrical signal amplitude, firing frequency, muscle recruitment patterns during inspiration and expiration, as well as qualitative analysis of synchronization and coordination between respiratory muscles, incorporating Root Mean Square (RMS) measurements and spectral analysis for assessment of respiratory neuromuscular function and detection of muscle fatigue.
Respiratory muscle strength assessment will be conducted using manovacuometry, a method capable of providing comprehensive quantitative evaluation of respiratory muscle force parameters including maximal inspiratory pressure (MIP) and maximal expiratory pressure (MEP), as well as qualitative analysis of contractile capacity and muscle endurance, incorporating peak pressure measurements and performance indices for assessment of global respiratory muscle function and early detection of muscle weakness
Pulmonary function assessment will be conducted using spirometry, a method capable of providing comprehensive quantitative evaluation of respiratory function parameters including forced vital capacity (FVC), forced expiratory volume in one second (FEV1), FEV1/FVC ratio, and forced expiratory flow 25-75% (FEF25-75%), as well as qualitative analysis of flow-volume and volume-time curves, incorporating lung capacity and volume measurements for assessment of respiratory mechanics and early detection of obstructive and restrictive ventilatory disorders."
The PowerLab C is a biomedical data acquisition system used as an auxiliary tool for physiological monitoring. In this study, it will be employed to collect respiratory signals and diaphragmatic excursion data through specific sensors, integrated with LabChart software for data visualization and analysis. The device is not considered an investigational intervention, but a supporting tool for data collection.
The Nijmegen Questionnaire is a standardized self-report instrument designed to assess symptoms related to dysfunctional breathing and hyperventilation. In this study, it will be administered to evaluate respiratory symptoms and their impact on participants' daily life. The questionnaire is used solely for data collection and is not considered a therapeutic intervention.
The System Usability Scale (SUS) is a standardized questionnaire used to evaluate the usability and user experience of systems and devices. In this study, it will be applied to assess participants' perceptions of the usability of an intelligent respiratory monitoring system. The SUS will be used solely as a data collection tool and does not constitute a therapeutic intervention.
The Borg Scale is a standardized self-report instrument used to assess perceived exertion and breathlessness during physical activity. In this study, it will be applied to evaluate participants' perception of respiratory effort. The scale is used solely for data collection and is not considered a therapeutic intervention.
The Patient Identification Questionnaire is a standardized form used to collect sociodemographic and basic clinical information from participants, such as age, sex, and medical history. In this study, it will serve solely for data collection and will not constitute a therapeutic intervention.
Peak Expiratory Flow (PEF) measurement is a rapid and noninvasive method to assess the maximum expiratory volume a participant can achieve after a full inhalation. In this study, participants will be seated upright and use a mouthpiece connected to a peak flow meter. After a deep inspiration, they will exhale forcefully, and three measurements will be taken with at least one minute between attempts; the highest value will be recorded. PEF values provide an objective measure of airflow limitation, correlate with asthma symptoms, and will be used solely for data collection, not as a therapeutic intervention
Emergency Care Unit from Engenho Velho
Jaboatão dos Guararapes, Pernambuco, Brazil
Department of Physical Therapy
Recife, Pernambuco, Brazil
Otávio de Freitas Hospital
Recife, Pernambuco, Brazil
Respiratory Pattern Assessment using Respiratory Diagnostic Assistant (RDA)
The Respiratory Diagnostic Assistant (RDA) is a portable, non-invasive device providing qualitative and quantitative data on respiratory variables. Participants are assessed seated (or supine 30º if needed) through three stages: baseline respiration (3 min), slow vital capacity, and inspiratory capacity maneuvers (3 repetitions each, 1-min intervals). Measured variables include respiratory rate (breaths per minute), mean inspiratory/expiratory flow (L/s), TI (s), TE (s), tidal volumes (mL), minute volumes (L/min). Data are analyzed qualitatively and quantitatively, with graphical representation. Respiratory patterns may be compared with conventional monitoring (pulse oximetry, respiratory rate, or arterial blood gas).
Time frame: For an average period of four months, until the conclusion of the studies
System Usability Scale
The System Usability Scale (SUS) is a 10-item standardized questionnaire designed to assess usability and user experience of systems. Participants respond on a 5-point Likert scale (1 = strongly disagree to 5 = strongly agree), generating a total score ranging from 0 to 100. In this study, the SUS will evaluate participants' perceptions of the intelligent respiratory monitoring system, including ease of use, learnability, and satisfaction. The instrument is used solely for data collection and does not constitute a therapeutic intervention."
Time frame: For an average period of four months, until the conclusion of the studies
Peak Expiratory Flow (PEF) Data
Peak Expiratory Flow (PEF) data will be collected to explore correlations with asthma symptoms. Measurements will be performed according to standardized procedures, and the highest value of three attempts will be recorded. These data are used solely for analysis and do not constitute a therapeutic intervention
Time frame: For an average period of four months, until the conclusion of the studies
Diaphragmatic Excursion Assessment
Diaphragmatic excursion will be assessed using ultrasound to measure the amplitude of diaphragm movement during respiratory cycles, providing information on respiratory function and diaphragm mobility. Measurements will be performed in a standardized seated position, following consistent protocols to ensure accuracy and reproducibility. Data will be analyzed quantitatively and qualitatively and used solely for research purposes; this does not constitute a therapeutic intervention.
Time frame: For an average period of four months, until the conclusion of the studies
Self-reported Dysfunctional Breathing and Hyperventilation Symptoms (Nijmegen Questionnaire)
The Nijmegen Questionnaire is a 16-item self-report instrument assessing symptoms associated with dysfunctional breathing and hyperventilation. Each item is scored 0-4, producing a total score from 0 to 64, with higher scores indicating greater symptom burden. In this study, it will be used to evaluate participants' respiratory symptoms, including dyspnea, chest tightness, and air hunger. The questionnaire is used solely for data collection and does not constitute a therapeutic intervention
Time frame: For an average period of four months, until the conclusion of the studies
Sociodemographic and Clinical Baseline Data Collection (Patient Identification Questionnaire)
The Patient Identification Questionnaire is a standardized form used to collect sociodemographic and basic clinical information, including age, sex, medical history, and relevant comorbidities. It provides baseline characterization of participants and will serve solely for data collection, not constituting a therapeutic intervention
Time frame: Completed once per participant at baseline to collect sociodemographic and basic clinical data
Pulmonary Function Assessment (Spirometry)
Spirometry will be performed according to ATS/ERS standards to assess pulmonary function, measuring FVC (L), FEV1 (L), FEV1/FVC ratio (%), and PEF (L/s). Values will be expressed as absolute and percent predicted. Spirometry will provide quantitative evaluation of ventilatory function and is used solely for data collection, not as a therapeutic intervention
Time frame: For an average period of four months, until the conclusion of the studies
Respiratory Muscle Strength Assessment (Manovacuometry)
Manovacuometry will assess respiratory muscle strength by measuring maximal inspiratory (MIP) (cmH₂O) and expiratory pressures (MEP) (cmH₂O) using a manometer. Values will be recorded in cmH2O. This test provides quantitative evaluation of respiratory muscle performance and is used solely for data collection, not as a therapeutic intervention.
Time frame: For an average period of four months, until the conclusion of the studies
Respiratory Muscle Activity and Coordination (Surface Electromyography, sEMG)
Surface electromyography (sEMG) will continuously record the electrical activity of respiratory muscles, including the diaphragm, intercostals, and accessory muscles, during baseline breathing and standardized respiratory maneuvers. Recorded signals will be processed to extract amplitude (mV), frequency (Hz), and activation patterns, providing an objective assessment of muscle recruitment, coordination, and respiratory effort. The sEMG will be used solely for data collection and does not constitute a therapeutic intervention.
Time frame: For an average period of four months, until the conclusion of the studies
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.