PubMed Health⌕ Search

Biomedical subjects

David J Annibale

Publications and source records attributed to David J Annibale.

10 recordsLinked to original sources
PubMed2006

Parameter selection for and implementation of a web-based decision-support tool to predict extubation outcome in premature infants.

BACKGROUND: Approximately 30% of intubated preterm infants with respiratory distress syndrome (RDS) will fail attempted extubation, requiring reintubation and mechanical ventilation. Although ventilator technology and monitoring of premature infants have improved over time, optimal extubation remains challenging. Furthermore, extubation decisions for premature infants require complex informational processing, techniques implicitly learned through clinical practice. Computer-aided decision-support tools would benefit inexperienced clinicians, especially during peak neonatal intensive care unit (NICU) census. METHODS: A five-step procedure was developed to identify predictive variables. Clinical expert (CE) thought processes comprised one model. Variables from that model were used to develop two mathematical models for the decision-support tool: an artificial neural network (ANN) and a multivariate logistic regression model (MLR). The ranking of the variables in the three models was compared using the Wilcoxon Signed Rank Test. The best performing model was used in a web-based decision-support tool with a user interface implemented in Hypertext Markup Language (HTML) and the mathematical model employing the ANN. RESULTS: CEs identified 51 potentially predictive variables for extubation decisions for an infant on mechanical ventilation. Comparisons of the three models showed a significant difference between the ANN and the CE (p = 0.0006). Of the original 51 potentially predictive variables, the 13 most predictive variables were used to develop an ANN as a web-based decision-tool. The ANN processes user-provided data and returns the prediction 0-1 score and a novelty index. The user then selects the most appropriate threshold for categorizing the prediction as a success or failure. Furthermore, the novelty index, indicating the similarity of the test case to the training case, allows the user to assess the confidence level of the prediction with regard to how much the new data differ from the data originally used for the development of the prediction tool. CONCLUSION: State-of-the-art, machine-learning methods can be employed for the development of sophisticated tools to aid clinicians' decisions. We identified numerous variables considered relevant for extubation decisions for mechanically ventilated premature infants with RDS. We then developed a web-based decision-support tool for clinicians which can be made widely available and potentially improve patient care world wide.

Birth Weight↗
PubMed2004

Predicting extubation outcome in preterm newborns: a comparison of neural networks with clinical expertise and statistical modeling.

Even though ventilator technology and monitoring of premature infants has improved immensely over the past decades, there are still no standards for weaning and determining optimal extubation time for those infants. Approximately 30% of intubated preterm infants will fail attempted extubation, requiring reintubation and resuming of mechanical ventilation. A machine-learning approach using artificial neural networks (ANNs) to aid in extubation decision making is hereby proposed. Using expert opinion, 51 variables were identified as being relevant for the decision of whether to extubate an infant who is on mechanical ventilation. The data on 183 premature infants, born between 1999 and 2002, were collected by review of medical charts. The ANN extubation model was compared with alternative statistical modeling using multivariate logistic regression and also with the clinician's own predictive insight using sensitivity analysis and receiver operating characteristic curves. The optimal ANN model used 13 parameters and achieved an area under the receiver operating characteristic curve of 0.87 (out-of-sample validation), comparing favorably with multivariate logistic regression. It also compared well with the clinician's expertise, which raises the possibility of being useful as an automated alert tool. Because an ANN learns directly from previous data obtained in the institution where it is to be used, this makes it particularly amenable for application to evidence-based medicine. Given the variety of practices and equipment being used in different hospitals, this may be particularly relevant in the context of caring for preterm newborns who are on mechanical ventilation.

Decision Making↗
PubMed2003

Web-based prediction of extubation outcome in premature infants on mechanical ventilation using an artificial neural network.

The web-based implementation of a decision-support tool for the prediction of extubation outcome in mechanically ventilated premature infants enables the integration of advanced and computationally intensive modeling approaches with easy-usage, no maintenance requirements and wide availability. Accordingly, the artificial neural network predictive tool developed provides decision-support in determining whether to extubate a premature infant to clinicians in NICUs anywhere with access to the Internet.

Decision Making, Computer-Assisted↗
PubMed2002

Albuterol delivery with conventional and synchronous ventilation in a neonatal lung model.

OBJECTIVE: To compare the percentage of nebulized albuterol delivered with conventional (intermittent mandatory ventilation) vs. synchronous (assist-control and assist-control with flow synchronization) ventilation in a neonatal lung model. DESIGN: Prospective in vitro laboratory study. SETTING: Research laboratory. SUBJECT: Neonatal lung model. INTERVENTIONS: The model simulated an intubated neonate with a spontaneous respiratory rate of 40, 60, or 80 breaths per minute and compliance and resistance values of bronchopulmonary dysplasia. A VIP Bird ventilator was used for all ventilator modes. Albuterol 2.5 mg was administered with a T Up-Draft II Neb-U-Mist nebulizer attached to a 12.75-cm (10-mL) reservoir of circuit tubing. Albuterol was collected onto a filter (particle retention .05, two-factor analysis of variance). CONCLUSIONS: The percentage of nebulized albuterol delivered to the end of the endotracheal tube in a mechanically ventilated neonatal model was not affected by mode of ventilation under the conditions studied. Further clinical studies are needed to determine whether lung deposition and distribution or clinical efficacy of albuterol is influenced by synchronous ventilation in this patient population.

Journal Article↗
PubMed2002

Effects of changing health care financial policy on very low birthweight neonatal outcomes.

BACKGROUND: Our objective was to determine whether perinatal referral patterns and clinical outcomes for very low birthweight infants changed in relation to changing Medicaid financial policies in coastal South Carolina. METHODS: Referral patterns and outcome indicators for very low birthweight infants were compared during two periods in a cohort design. RESULTS: A total of 520 infants were identified over two funding periods. A decrease in the proportion of nonwhite very low birthweight infants was identified. There was an increase in very low birthweight infants with Medicaid funding born outside our level III center. CONCLUSIONS: Changes in financial public policy have been successful in the movement of low risk pregnancies into the private sector. However, an increased proportion of deliveries of very low birthweight infants occurred outside the level III center.

Apgar Score↗
PubMed2002

Neonatal sepsis: evaluation and management.

Bacterial antigenic challenge presents a difficult fight for the neonatal immune system, and they have a smaller arsenal of weapons to fight bacterial infections than adults and older children. The baby's own systemic inflammatory response may have detrimental effects on several organs and longer lasting effects on the developing brain. Neurodevelopmental outcomes after maternal chorioamnionitis are worse than neonates without a contaminated intrauterine environment, regardless of gestation age and the baby's culture results. Successes with intrapartum antibiotic prophylaxis decreasing rates of GBS sepsis and maternal chorioamnionitis, have heartened care providers and parents. These results demonstrate the advances possible when specific diseases are made a national health priority, and good clinical trial work is applied to clinical practice.

Humans↗
PubMed2002

Preparation of the critically ill neonate for transport.

Transport of a critically ill neonate is stressful for all involved. Adequate communication and stabilization will reduce stresses and improve outcomes. Periodic review of the stabilization and care provided to neonates prior to transport can help in further improving the process. Such reviews can be done in conjunction with the Regional Perinatal Center.

Critical Care↗
PubMed2002

Discharge planning for very low birthweight infants.

As discharge approaches, usually indicated by feeding progression, thermoregulation and other events, it is important for the medical team to develop a plan of action and stick with it, assuming that nothing untoward happens. Experience tells us that families of infants with special needs at discharge cope better and maintain a more positive attitude if plans are clearly defined and followed consistently. A coordinated team approach is also helpful for personnel responsible for arranging equipment, training, and home health services.

Humans↗
PubMed2002

Breastfeeding rates at an urban medical university after initiation of an educational program.

BACKGROUND: Our objective was to improve breastfeeding initiation rates at an urban medical center. METHODS: A breastfeeding educational program for health care providers was developed and implemented in 1995. The outcome variable of interest was the change in breastfeeding initiation rate during 2 periods, 1993-1994 and 1996 to 1999, stratified by weight (> 2,000, 1,500 to 2,000, and < 1,500 g). RESULTS: The breastfeeding initiation rate in 1996 to 1999 for all mothers of newborns admitted to the hospital was 47.1% (4,107/8,724), compared with the 1993-1994 rate of 18.9% (816/4,315). During the second period, the breastfeeding rate among mothers of infants < 1,500 g was 60.8% (468/770), compared with 19.2% (56/293) during the earlier study period. Stratified by weight, the greatest improvement in rates of breastfeeding initiation and at discharge was seen with mothers of preterm infants. CONCLUSION: A breastfeeding educational program that interfaced with medical staff and mothers at an urban medical university was associated with increased rates of breastfeeding initiation.

Academic Medical Centers↗