RESUMEN
BACKGROUND: Expert systems can help alleviate problems related to the shortage of human resources in critical care, offering expert advice in complex situations. Expert systems use contextual information to provide advice to staff. In mechanical ventilation, it is crucial for an expert system to be able to determine the ventilatory mode in use. Different manufacturers have assigned different names to similar or even identical ventilatory modes so an expert system should be able to detect the ventilatory mode. The aim of this study is to evaluate the accuracy of an algorithm to detect the ventilatory mode in use. METHODS: We compared the results of a two-step algorithm designed to identify seven ventilatory modes. The algorithm was built into a software platform (BetterCare® system, Better Care SL; Barcelona, Spain) that acquires ventilatory signals through the data port of mechanical ventilators. The sample analyzed compared data from consecutive adult patients who underwent >24 h of mechanical ventilation in intensive care units (ICUs) at two hospitals. We used Cohen's kappa statistics to analyze the agreement between the results obtained with the algorithm and those recorded by ICU staff. RESULTS: We analyzed 486 records from 73 patients. The algorithm correctly labeled the ventilatory mode in 433 (89 %). We found an unweighted Cohen's kappa index of 84.5 % [CI (95 %) = (80.5 %: 88.4 %)]. CONCLUSIONS: The computerized algorithm can reliably identify ventilatory mode.
Asunto(s)
Diseño de Equipo/métodos , Respiración Artificial/instrumentación , Respiración Artificial/métodos , Ventiladores Mecánicos/tendencias , Algoritmos , Automatización/instrumentación , Automatización/métodos , Sistemas de Apoyo a Decisiones Clínicas/instrumentación , Sistemas de Apoyo a Decisiones Clínicas/normas , Sistemas de Apoyo a Decisiones Clínicas/tendencias , Diseño de Equipo/tendencias , Humanos , Unidades de Cuidados Intensivos/organización & administración , Respiración Artificial/enfermería , España , Recursos HumanosRESUMEN
In mechanical ventilation, it is paramount to ensure the patient's ventilatory demand is met while minimizing asynchronies. We aimed to develop a model to predict the likelihood of asynchronies occurring. We analyzed 10,409,357 breaths from 51 critically ill patients who underwent mechanical ventilation >24 h. Patients were continuously monitored and common asynchronies were identified and regularly indexed. Based on discrete time-series data representing the total count of asynchronies, we defined four states or levels of risk of asynchronies, z1 (very-low-risk) - z4 (very-high-risk). A Poisson hidden Markov model was used to predict the probability of each level of risk occurring in the next period. Long periods with very few asynchronous events, and consequently very-low-risk, were more likely than periods with many events (state z4). States were persistent; large shifts of states were uncommon and most switches were to neighbouring states. Thus, patients entering states with a high number of asynchronies were very likely to continue in that state, which may have serious implications. This novel approach to dealing with patient-ventilator asynchrony is a first step in developing smart alarms to alert professionals to patients entering high-risk states so they can consider actions to improve patient-ventilator interaction.
Asunto(s)
Monitoreo Fisiológico , Ventilación Pulmonar , Respiración Artificial/efectos adversos , Respiración Artificial/métodos , Anciano , Bioestadística , Enfermedad Crítica , Femenino , Humanos , Masculino , Persona de Mediana EdadRESUMEN
PURPOSE: This study aimed to assess the prevalence and time course of asynchronies during mechanical ventilation (MV). METHODS: Prospective, noninterventional observational study of 50 patients admitted to intensive care unit (ICU) beds equipped with Better Care™ software throughout MV. The software distinguished ventilatory modes and detected ineffective inspiratory efforts during expiration (IEE), double-triggering, aborted inspirations, and short and prolonged cycling to compute the asynchrony index (AI) for each hour. We analyzed 7,027 h of MV comprising 8,731,981 breaths. RESULTS: Asynchronies were detected in all patients and in all ventilator modes. The median AI was 3.41 % [IQR 1.95-5.77]; the most common asynchrony overall and in each mode was IEE [2.38 % (IQR 1.36-3.61)]. Asynchronies were less frequent from 12 pm to 6 am [1.69 % (IQR 0.47-4.78)]. In the hours where more than 90 % of breaths were machine-triggered, the median AI decreased, but asynchronies were still present. When we compared patients with AI > 10 vs AI ≤ 10 %, we found similar reintubation and tracheostomy rates but higher ICU and hospital mortality and a trend toward longer duration of MV in patients with an AI above the cutoff. CONCLUSIONS: Asynchronies are common throughout MV, occurring in all MV modes, and more frequently during the daytime. Further studies should determine whether asynchronies are a marker for or a cause of mortality.
Asunto(s)
Enfermedad Crítica/terapia , Respiración Artificial/efectos adversos , Mecánica Respiratoria , Enfermedad Crítica/mortalidad , Mortalidad Hospitalaria , Humanos , Unidades de Cuidados Intensivos , Estudios Prospectivos , Ventilación Pulmonar , Respiración Artificial/mortalidad , Volumen de Ventilación Pulmonar , Factores de TiempoRESUMEN
BACKGROUND: New home ventilators are able to provide clinicians data of interest through built-in software. Monitoring of tidal volume (VT) is a key point in the assessment of the efficacy of home mechanical ventilation. OBJECTIVE: To assess the reliability of the VT provided by 5 ventilators in a bench test. METHODS: Five commercial ventilators from 4 different manufacturers were tested in pressure support mode with the help of a breathing simulator under different conditions of mechanical respiratory pattern, inflation pressure, and intentional leakage. Values provided by the built-in software of each ventilator were compared breath to breath with the VT monitored through an external pneumotachograph. Ten breaths for each condition were compared for every tested situation. RESULTS: All tested ventilators underestimated VT (ranges of -21.7 mL to -83.5 mL, which corresponded to -3.6% to -14.7% of the externally measured VT). A direct relationship between leak and underestimation was found in 4 ventilators, with higher underestimations of the VT when the leakage increased, ranging between -2.27% and -5.42% for each 10 L/min increase in the leakage. A ventilator that included an algorithm that computes the pressure loss through the tube as a function of the flow exiting the ventilator had the minimal effect of leaks on the estimation of VT (0.3%). In 3 ventilators the underestimation was also influenced by mechanical pattern (lower underestimation with restrictive, and higher with obstructive). CONCLUSIONS: The inclusion of algorithms that calculate the pressure loss as a function of the flow exiting the ventilator in commercial models may increase the reliability of VT estimation.
Asunto(s)
Ventilación no Invasiva/instrumentación , Respiración , Programas Informáticos , Ventiladores Mecánicos , Algoritmos , Diseño de Equipo , Monitoreo Fisiológico , Presión , Reproducibilidad de los Resultados , Volumen de Ventilación PulmonarRESUMEN
UNLABELLED: BACKGROUND PATIENT: ventilator dyssynchrony is common and may influence patients' outcomes. Detection of such dyssynchronies relies on careful observation of patients and airway flow and pressure measurements. Given the shortage of specialists, critical care nurses could be trained to identify dyssynchronies. OBJECTIVE: To evaluate the accuracy of specifically trained critical care nurses in detecting ineffective inspiratory efforts during expiration. METHODS: We compared 2 nurses' evaluations of measurements from 1007 breaths in 8 patients with the evaluations of experienced critical care physicians. Sensitivity, specificity, positive predictive value, negative predictive value, and the Cohen κ for interobserver agreement were calculated. RESULTS: For the first nurse, sensitivity was 92.5%, specificity was 98.3%, positive predictive value was 95.4%, negative predictive value was 97.1%, and κ was 0.92 (95% CI, 0.89-0.94). For the second nurse, sensitivity was 98.5%, specificity was 84.7%, positive predictive value was 70.7%, negative predictive value was 99.3%, and κ was 0.74 (95% CI, 0.70-0.78). CONCLUSION: Specifically trained nurses can reliably detect ineffective inspiratory efforts during expiration.
Asunto(s)
Unidades de Cuidados Intensivos , Diagnóstico de Enfermería/normas , Respiración Artificial/enfermería , Insuficiencia Respiratoria/enfermería , Instrucción por Computador/métodos , Humanos , Inhalación/fisiología , Cuerpo Médico de Hospitales/provisión & distribución , Personal de Enfermería en Hospital/educación , Observación , Evaluación de Programas y Proyectos de Salud , Respiración Artificial/efectos adversos , Insuficiencia Respiratoria/diagnóstico , Ruidos Respiratorios/diagnóstico , Sensibilidad y Especificidad , Recursos HumanosRESUMEN
PURPOSE: Ineffective respiratory efforts during expiration (IEE) are a problem during mechanical ventilation (MV). The goal of this study is to validate mathematical algorithms that automatically detect IEE in a computerized (Better Care®) system that obtains and processes data from intensive care unit (ICU) ventilators in real time. METHODS: The Better Care® system, integrated with ICU health information systems, synchronizes and processes data from bedside technology. Algorithms were developed to analyze airflow waveforms during expiration to determine IEE. Data from 2,608,800 breaths from eight patients were recorded. From these breaths 1,024 were randomly selected. Five experts independently analyzed the selected breaths and classified them as IEE or not IEE. Better Care® evaluated the same 1,024 breaths and assigned a score to each one. The IEE score cutoff point was determined based on the experts' analysis. The IEE algorithm was subsequently validated using the electrical activity of the diaphragm (EAdi) signal to analyze 9,600 breaths in eight additional patients. RESULTS: Optimal sensitivity and specificity were achieved by setting the cutoff point for IEE by Better Care® at 42%. A score >42% was classified as an IEE with 91.5% sensitivity, 91.7% specificity, 80.3% positive predictive value (PPV), 96.7% negative predictive value (NPV), and 79.7% Kappa index [confidence interval (CI) (95%) = (75.6%; 83.8%)]. Compared with the EAdi, the IEE algorithm had 65.2% sensitivity, 99.3% specificity, 90.8% PPV, 96.5% NPV, and 73.9% Kappa index [CI (95%) = (71.3%; 76.3%)]. CONCLUSIONS: In this pilot, Better Care® classified breaths as IEE in close agreement with experts and the EAdi signal.
Asunto(s)
Espiración , Monitoreo Fisiológico/instrumentación , Monitoreo Fisiológico/normas , Respiración Artificial/normas , Adolescente , Anciano , Anciano de 80 o más Años , Algoritmos , Espiración/fisiología , Femenino , Humanos , Unidades de Cuidados Intensivos , Masculino , Persona de Mediana Edad , Proyectos Piloto , Estudios Prospectivos , EspañaRESUMEN
Critical care medicine is the specialty that cares for patients with acute life-threatening illnesses where intensivists look after all aspects of patient care. Nevertheless, shortage of physicians and nurses, the relationship between high costs and economic restrictions, and the fact that critical care knowledge is only available at big hospitals puts the system on the edge. In this scenario, telemedicine might provide solutions to improve availability of critical care knowledge where the patient is located, improve relationship between attendants in different institutions and education material for future specialist training. Current information technologies and networking capabilities should be exploited to improve intensivist coverage, advanced alarm systems and to have large critical care databases of critical care signals.