Development of a predictive inpatient falls risk model using machine learning.

AIM: The aims of this study were to create a model that detects the population at risk of falls taking into account a fall prevention variable and to know the effect on the model's performance when not considering it. BACKGROUND: Traditionally, instruments for detecting fall risk are based on risk factors, not mitigating factors. Machine learning, which allows working with a wider range of variables, could improve patient risk identification. METHODS: The sample was composed of adult patients admitted to the Internal Medicine service (total, n = 22,515; training, n = 11,134; validation, n = 11,381). A retrospective cohort design was used and we applied machine learning technics. Variables were extracted from electronic medical records electronic medical records. RESULTS: The Two-Class Bayes Point Machine algorithm was selected. Model-A (with a fall prevention variable) obtained better results than Model-B (without it) in sensitivity (0.74 vs. 0.71), specificity (0.82 vs. 0.74), and AUC (0.82 vs. 0.78). CONCLUSIONS: Fall prevention was a key variable. The model that included it detected the risk of falls better than the model without it. IMPLICATIONS FOR NURSING MANAGEMENT: We created a decision-making support tool that helps nurses to identify patients at risk of falling. When it is integrated in the electronic medical records, it decreases nurses' workloads by not having to collect information manually.

Predictive Modeling of Pressure Injury Risk in Patients Admitted to an Intensive Care Unit.

BACKGROUND: Pressure injuries are an important problem in hospital care. Detecting the population at risk for pressure injuries is the first step in any preventive strategy. Available tools such as the Norton and Braden scales do not take into account all of the relevant risk factors. Data mining and machine learning techniques have the potential to overcome this limitation. OBJECTIVES: To build a model to detect pressure injury risk in intensive care unit patients and to put the model into production in a real environment. METHODS: The sample comprised adult patients admitted to an intensive care unit (N = 6694) at University Hospital of Torrevieja and University Hospital of Vinalopó. A retrospective design was used to train (n = 2508) and test (n = 1769) the model and then a prospective design was used to test the model in a real environment (n = 2417). Data mining was used to extract variables from electronic medical records and a predictive model was built with machine learning techniques. The sensitivity, specificity, area under the curve, and accuracy of the model were evaluated. RESULTS: The final model used logistic regression and incorporated 23 variables. The model had sensitivity of 0.90, specificity of 0.74, and area under the curve of 0.89 during the initial test, and thus it outperformed the Norton scale. The model performed well 1 year later in a real environment. CONCLUSIONS: The model effectively predicts risk of pressure injury. This allows nurses to focus on patients at high risk for pressure injury without increasing workload.

[Knowledge and attitudes of health professionals towards advance directives]. / Grado de conocimiento y actitudes de los profesionales sanitarios sobre el documento de voluntades anticipadas.

OBJECTIVE: To evaluate the degree of knowledge and attitudes of medical and nursing professionals in two health departments to advance directives, as well as to examine their association with the sociodemographic and occupational variables of the professionals. METHODS: A cross-sectional survey on 329 health professionals was carried out through the internet and a standardised procedure. The knowledge and attitudes of the professionals about advance directives were examined using two validated questionnaires of 17 and 12 items, respectively. Sociodemographic and professional data were also collected from the participants. RESULTS: 45% of the professionals were physicians, with X¯=13,1 (SD: 8.3) years of professional experience. Sixty-seven point five percent were women and the mean age was 38.9 (SD: 9.2) years. Professionals had very positive attitudes towards the advance directives document (X¯=75.37;SD: 11.97;R=0-90), although their level of knowledge about them was medium-low (X¯=9.31;SD: 2.73;R=0-18). Both the level of knowledge and self-perception were associated with previous training in palliative care, experience with document management, reading, or the demand for information. Completing the document related to self-perception of knowledge. Attitudes towards the document related to experience in its use and a positive attitude toward training. CONCLUSIONS: The professionals showed positive attitudes towards the advance directive document although low knowledge about it. Experience with the document was the only variable associated with both the knowledge and the attitudes of the professionals.

Variability in management of implantable ports in oncology outpatients.

PURPOSE OF THE RESEARCH: To describe the variability in practice regarding the management of vascular access ports in adult oncology patients at Spanish outpatient clinics and to evaluate its compliance with the recommended procedural guidelines. METHODS AND SAMPLE: Three e-mailings or three postal mail-outs were sent to all Spanish outpatient clinics, in accordance with the hospital's preference. An additional fourth postal mail-out was made to all units. In total 185 units at Spanish outpatient clinics out of a total 256 completed the survey questionnaire. KEY RESULTS: A number of variations exist in the techniques used for insertion, withdrawal of needle from vascular access ports, blood sampling and unblocking procedure. There is considerable agreement in relation to the use of a special beveled needle, the use of gloves in the access and withdrawal procedures and checking of reservoir permeability by aspirating blood. In most cases, sterile gloves are used but there is a lesser occurrence of both scrubbed hands and correct antiseptic use. CONCLUSIONS: There are considerable differences in the management of the vascular access ports in terms of the recommendations published in the main international guidelines, though these are based on low level evidence. The results highlight the need for further quality studies in ports use and manipulation to lessen the variability between published recommendations and clinical practice.

Variabilidad de la práctica clínica en enfermería: una revisión integradora / Variability of clinical practice in nursing: an integrative review

OBJETIVO: El objetivo de esta revisión de la literatura es examinar qué se ha publicado sobre variabilidad de la práctica clínica desde el enfoque de la enfermería. MÉTODOS: Se realizó una búsqueda bibliográfica en las principales bases de datos internacionales seleccionando aquellos trabajos más relevantes. RESULTADOS: Los resultados se han agrupado en 5 grupos: estudios sobre variaciones respecto a guías y protocolos, estudios que analizan práctica enfermera y de otros profesionales sanitarios, variaciones en procedimientos y cuidados de enfermería, variaciones en la práctica entre enfermeras y médicos y estudios que relacionan la variabilidad con características de profesionales, unidades o centros sanitarios. CONCLUSIÓN: La mayoría de los trabajos encontrados se han limitado a mostrar la existencia de variabilidad pero pocos han buscado variables que predigan ésta. Futuras investigaciones deberían centrarse en la búsqueda de variables predictivas de la variabilidad para hacer frente a las variaciones injustificadas que se detecten.

OBJETIVO: O objetivo desta revisão foi examinar o que foi publicado sobre a variabilidade na prática clínica com base no foco de enfermagem. MÉTODOS: Pesquisa bibliográfica realizada nas principais bases internacionais, seleccionando as obras mais relevantes. RESULTADOS: Os resultados foram agrupados em cinco grupos: estudo sobre as variações com relação às diretrizes e protocolo, estudos que analisam a prática da enfermagem e de outros profissionais de saúde; variações nos procedimentos e cuidados de enfermagem; variações na prática, entre enfermeiros e médicos e estudos de variabilidade relacionada com características de profissionais, unidades ou centros de saúde. CONCLUSÃO: A maioria dos artigos encontrados limitou-se a relatar a existência de variabilidade, mas algunas variáveis que buscou, previam. Futuras investigações devem concentrar-se no encontro de preditores de variabilidade para enfrentar variáveis injustificadas que são detectadas.

OBJECTIVE: The objective of this literature review was to examine what has been published about variability in clinical practice from the focus of nursing. METHODS: We performed a literature search in the principal international databases, selecting those most relevant works. RESULTS: The results were clustered into five groups: studies about variations with respect to guidelines and protocols; studies that analyze nursing practice and that of other health professionals; variations in procedures and nursing care; variations in practice between nurses and physicians; and studies that related variability with characteristics of professionals, units or healthcare centers. CONCLUSION: The majority of papers found were limited to showing the existence of variability, but few sought variables that predicted it. Future investigations should focus on finding predictors of variability to address unjustified variations that are detected.

[Variations in clinical practice. Current status and challenges for nursing]. / Variabilidad de la práctica clínica. Situación actual y retos para enfermería.

The clinical practice can vary in every step of the process. The following article provides an overview of the most important concepts in the study of variations in clinical practice and the status of nursing regarding these variations. The variability can be seen both from a population and an individual point of view. These variations in practice have problems with quality of care and show that the practice is poorly based in research. The uncertainty hypothesis is the most cited as a primary cause of variations and leads to a style of practice by health professionals to use procedures which have ambiguous incomplete evidence. The main actions to address variations should focus on unwarranted variations and should be developed at institutional level. Most variability studies have been performed from the physician perspective and much less has been done from a nursing one. Paradoxically, few studies have described the level of variability in nursing, however, there are more studies on clinical practice guidelines, clinical pathways and protocols that attempt to standardise practice. Variability is therefore a phenomenon that is presumed to exist, but in many cases is unknown.

[Concordance among samples taken from a subcutaneous reservoir and a peripheral puncture]. / Concordancia entre muestras extraídas por reservorio subcutáneo y punción periférica.

Many patients who undergo phlebo-toxic treatment eventually require central vein access ways and of these accesses, the most common one used among oncology patients due to its advantages is a subcutaneous reservoir. The objective of this study was to verify the concordance among samples obtained from a subcutaneous reservoir using the rejection technique, and those obtained when using a direct puncture technique. This study included 22 patients who were carriers of a subcutaneous reservoir and who visited outpatient services during March and April in 2006. The study authors obtained simultaneous samples from subcutaneous reservoirs and from peripheral veins. These parameters were compared by means of an intra-class correlation coefficient. Only hematology parameters, that is leucocytes, hematocrits, hemoglobin and platelets, showed an adequate concordance.