The ASA Classification System as a Predictive Factor to Stay at the Virtual Hybrid Care Hotel

INTRODUCTION

The Care Hotel is a virtual hybrid care model for postoperative patients after low-risk procedures which allow recovery in an outpatient environment. This study aimed to analyze if the American Society of Anesthesiologists Physical Status (ASA PS) Classification System can be used as a predictive factor for staying at Mayo Clinic's Care Hotel.

METHODS

This retrospective cohort study was conducted between July 23, 2020, and June 4, 2021, at Mayo Clinic in Florida, a 306-bed community academic hospital. ASA PS Class and post-procedure care setting (Care Hotel vs inpatient ward) were collected. Patients were classified into two ASA PS groups (ASA PS Classes 1-2 and 3-4). Pearson's Chi-square test was used to determine if the ASA PS Class and having stayed or not at the Care Hotel were independent and an Odds Ratio (OR) calculated.

RESULTS

Out of 392 surgical and procedural patients, 272 (69.39%) chose the Care Hotel and 120 (30.61%) chose the inpatient ward. There was a statistically significant association between ASA PS Class and staying at the Care Hotel, P < .01. The OR of preferring to stay at the Care Hotel in patients with ASA PS Class 1-2 vs ASA PC Class 3-4 was 1.91 (P = .0041, 95% CI: 1.229-2.982).

CONCLUSION

Patients with ASA PS Classes 1-2 are almost twice as likely to elect to stay at the Care Hotel compared to those with ASA PS Classes 3-4. This finding may help care teams focus their Care hotel recruitment efforts.

A qualitative focus group study]

Intervention-related demands: Criteria for an operating room-specific patient classification. A qualitative focus group study Abstract: Background: Optimal workforce deployment in the operating room-setting has gained high priority in the context of an economized health care system and the development of skill-grade mix. Therefore, mapping intervention-related demands on perioperative nurses as precisely as possible is a frequently discussed need. A surgery-specific patient classification might be helpful. Aim: This paper aims to present core elements of perioperative nursing care in the Swiss-German context and to establish a link to the Perioperative Nursing Data Set (PNDS). Methods: Three focus group interviews with perioperative nurses took place at a university hospital in the German-speaking part of Switzerland. Data analysis was performed in analogy to qualitative content analysis according to Mayring. The content structuring of the categories was based on the relevant PNDS taxonomies. Results: Intervention-related requirements can be divided into three areas: "patient safety", "nursing and caring", and "environmental factors". The conjunction with the PNDS taxonomy serves as a theoretical foundation. Conclusions: Elements of the PNDS taxonomies can describe the demands on perioperative nurses in the Swiss-German context. The identified definition of intervention-related demands can contribute to the visibility of perioperative nursing and promote professionalization as well as practice development in the operating room-setting.

Using EHR Data to Identify Patient Frailty and Risk for ICU Transfer

The predictive properties of four definitions of a frailty risk score (FRS) constructed using combinations of nursing flowsheet data, laboratory tests, and ICD-10 codes were examined for time to first intensive care unit (ICU) transfer in medical-surgical inpatients ≥50 years of age. Cox regression modeled time to first ICU transfer and Schemper-Henderson explained variance summarized predictive accuracy of FRS combinations. Modeling by age group and controlling for sex, all FRS measures significantly predicted time to first ICU transfer. Further multivariable modeling controlling for clinical characteristics substantially improved predictive accuracy. The effect of frailty on time to first ICU transfer depended on age, with highest risk in 50 to <60 years and ≥80 years age groups. Frailty prevalence ranged from 25.1% to 56.4%. Findings indicate that FRS-based frailty is a risk factor for time to first ICU transfer and should be considered in assessment and care-planning to address frailty in high-risk patients.Frailty prevalence was highest med-surg pts 60 to <70 years (56%); highest risk for time to first ICU transfer was in younger (50 to <60 years) and older (≥80 years) groups.

Machine learning-based patient classification system for adults with stroke: A systematic review

OBJECTIVE

To evaluate the existing evidence of a machine learning-based classification system that stratifies patients with stroke.

METHODS

The authors carried out a systematic review following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) recommendations for a review article. PubMed, MEDLINE, Web of Science, and CINAHL Plus Full Text were searched from January 2015 to February 2021.

RESULTS

There are twelve studies included in this systematic review. Fifteen algorithms were used in the included studies. The most common forms of machine learning (ML) used to classify stroke patients were the support vector machine (SVM) (n = 8 studies), followed by random forest (RF) (n = 7 studies), decision tree (DT) (n = 4 studies), gradient boosting (GB) (n = 4 studies), neural networks (NNs) (n = 3 studies), deep learning (n = 2 studies), and k-nearest neighbor (k-NN) (n = 2 studies), respectively. Forty-four features of inputs were used in the included studies, and age and gender are the most common features in the ML model.

DISCUSSION

There is no single algorithm that performed better or worse than all others at classifying patients with stroke, in part because different input data require different algorithms to achieve optimal outcomes.

Calculating the optimal number of nurses based on nursing intensity by patient classification groups in general units in South Korea: A cross-sectional study

AIM

This study aimed to calculate the total daily nursing workload and the optimal number of nurses per general unit based on the nursing intensity.

DESIGN

This study was conducted using a cross-sectional study.

METHODS

Three units at one general hospital were investigated. Patient classification according to nursing needs was performed for over 10 days in each unit in September 2018. The direct and non-direct nursing time and nursing intensity scores were analysed using descriptive statistics.

RESULTS

For the internal medicine unit, the average direct nursing time per patient was 1.0, 1.5, 2.2 and 2.9 h for Groups 1, 2, 3 and 4, respectively. For the surgical unit, the average direct nursing time per patient was 0.9, 1.4, 2.1 and 2.6 h for Groups 1, 2, 3 and 4, respectively. 5 and 9 additional nurses were needed in the internal medicine and surgical nursing units.

PATIENT CONTRIBUTION

This study confirmed that the optimal number of nurses was not achieved and that the nursing intensity was very high. Long-term efforts, such as improving the nursing environment, should be made to ensure an optimal number of nurses in various nursing units.

Whole-brain dynamical modelling for classification of Parkinson's disease

Simulated whole-brain connectomes demonstrate enhanced inter-individual variability depending on the data processing and modelling approach. By considering the human brain connectome as an individualized attribute, we investigate how empirical and simulated whole-brain connectome-derived features can be utilized to classify patients with Parkinson's disease against healthy controls in light of varying data processing and model validation. To this end, we applied simulated blood oxygenation level-dependent signals derived by a whole-brain dynamical model simulating electrical signals of neuronal populations to reveal differences between patients and controls. In addition to the widely used model validation via fitting the dynamical model to empirical neuroimaging data, we invented a model validation against behavioural data, such as subject classes, which we refer to as behavioural model fitting and show that it can be beneficial for Parkinsonian patient classification. Furthermore, the results of machine learning reported in this study also demonstrated that the performance of the patient classification can be improved when the empirical data are complemented by the simulation results. We also showed that the temporal filtering of blood oxygenation level-dependent signals influences the prediction results, where filtering in the low-frequency band is advisable for Parkinsonian patient classification. In addition, composing the feature space of empirical and simulated data from multiple brain parcellation schemes provided complementary features that improved prediction performance. Based on our findings, we suggest that combining the simulation results with empirical data is effective for inter-individual research and its clinical application.

Validation and Improvement of a Convolutional Neural Network to Predict the Involved Pathology in a Head and Neck Surgery Cohort

The selection of patients for the constitution of a cohort is a major issue for clinical research (prospective studies and retrospective studies in real life). Our objective was to validate in real life conditions the use of a Deep Learning process based on a neural network, for the classification of patients according to the pathology involved in a head and neck surgery department. 24,434 Electronic Health Records (EHR) from the first visit between 2000 and 2020 were extracted. More than 6000 EHR were manually classified in ten groups of interest according to the reason for consultation with a clinical relevance. A convolutional neural network (TensorFlow, previously reported by Hsu et al.) was then used to predict the group of patients based on their pathology, using two levels of classification based on clinically relevant criteria. On the first and second level of classification, macro-average performances were: 0.95, 0.83, 0.85, 0.97, 0.84 and 0.93, 0.76, 0.83, 0.96, 0.79 for accuracy, recall, precision, specificity and F1-score versus accuracy, recall and precision of 0.580, 580 and 0.582 for Hsu et al., respectively. We validated this model to predict the pathology involved and to constitute clinically relevant cohorts in a tertiary hospital. This model did not require a preprocessing stage, was used in French and showed equivalent or better performances than other already published techniques.

A Hadoop-Based Platform for Patient Classification and Disease Diagnosis in Healthcare Applications

Nowadays, the increasing number of patients accompanied with the emergence of new symptoms and diseases makes heath monitoring and assessment a complicated task for medical staff and hospitals. Indeed, the processing of big and heterogeneous data collected by biomedical sensors along with the need of patients’ classification and disease diagnosis become major challenges for several health-based sensing applications. Thus, the combination between remote sensing devices and the big data technologies have been proven as an efficient and low cost solution for healthcare applications. In this paper, we propose a robust big data analytics platform for real time patient monitoring and decision making to help both hospital and medical staff. The proposed platform relies on big data technologies and data analysis techniques and consists of four layers: real time patient monitoring, real time decision and data storage, patient classification and disease diagnosis, and data retrieval and visualization. To evaluate the performance of our platform, we implemented our platform based on the Hadoop ecosystem and we applied the proposed algorithms over real health data. The obtained results show the effectiveness of our platform in terms of efficiently performing patient classification and disease diagnosis in healthcare applications.

The transcultural adaptation and the validity and reliability of the Turkish Version of Perroca's Patient Classification Instrument

AIM

This study examines the transcultural adaptation and the reliability and validity of the Turkish version of Perroca's Patient Classification Instrument.

BACKGROUND

Nurse managers need valid and reliable patient classification tools for determining patients' acuity or dependency levels on nursing care for measuring nursing workloads.

METHODS

This study was conducted in two stages in a private hospital in Istanbul, Turkey. First, the instrument was translated, and its content validation was analysed. In the second stage, data were gathered from 300 hospitalized patients and were analysed by factor analyses, Cronbach's alpha and Cohen's kappa.

RESULTS

Validity testing with ten experts revealed a scale-content validity index of 0.93. Exploratory factor analysis revealed a two-dimensional instrument with distinct factor loadings and a variance of 66.97%. The confirmatory factor analysis revealed that the fit indices were satisfactory. This instrument had an overall Cronbach's alpha coefficient of .86 and Cohen's kappa coefficient of .826.

CONCLUSION

The study provides evidence that the Turkish version of Perroca's Patient Classification Instrument is a valid and reliable tool to determine patients' acuity levels on nursing care.

IMPLICATIONS FOR NURSING MANAGEMENT

This instrument may be used by nurse managers to determine acuity levels of patients and measure nursing workload.

Balancing workload of nurses: Linear mixed effects modelling to estimate required nursing time on surgical wards

Aim

Quantifying the relation between patient characteristics and care time and explaining differences in nursing time between wards.

Design

Academic hospital in the Netherlands. Six surgical wards, capacity 15-30 beds, 2012-2014.

Methods

Linear mixed effects model to study the relation between patient characteristics and care time. Estimated marginal means to estimate baseline care time and differences between wards.

Results

Nine patient characteristics significantly related to care time. Most required between 18 and 35 min extra, except "two or more IV/drip/drain" (8) and "one-on-one care" (156). Care time for minimum patient profile: 44-57 min and for average patient profile: 75-88 min. Sources of variation: nurse proficiency, patients, day-to-day variation within patients. The set of characteristics is short, simple and useful for planning and comparing workload. Explained variance up to 36%. Calculating estimated means per ward has not been done before. Nurse proficiency is an important factor.

Heart Disease Dataset Clusterization

Clusterization is a promising group of methods in the context of patient similarity. However, results of clustering are not often clear for physicians as well as different clustering methods can produce different results. We have examined a well-known dataset and implemented 3 clustering methods (k-means, Agglomerative and Spectral). We have compared and evaluated clusters and their correlation with data attributes. In contrast to original dataset's target value, the clusters correlated with only a few attributes. Finally, we train 2 predictive models based on k-nearest neighbors (KNN) algorithm and Artificial Neural Network (ANN). Models evaluation demonstrates that using the results of clustering algorithms as predictive attribute give a higher F-score than the original target attribute.

Quality of nursing intensity data: inter-rater reliability of the patient classification after two decades in clinical use

AIMS

The aim of this study was to measure the inter-rater reliability of the Oulu Patient Classification and to discuss existing methods of reliability testing.

BACKGROUND

The Oulu Patient Classification, part of the RAFAELA^® System, has been developed to assist nursing managers with the proper allocation of nursing resources. Due to the increased intensity of inpatient care during recent years, there is a need for the reliability testing of the classification, which has been in clinical use for 20 years.

DESIGN

Retrospective statistical study.

METHODS

To test inter-rater reliability, a pair of nurses classified the same patients, without knowledge of each other's ratings, as a part of annually conducted standardization. Data on the parallel classifications (n = 19,997) was obtained from inpatient units (n = 32) with different specialties at a university hospital in Finland during 2010-2015. Parallel classification practices were also analysed. The reliability of the overall classification and its subareas were calculated using suitable statistical coefficients.

RESULTS

Inter-rater reliability coefficients were a reliable or almost perfect means of considering the nursing intensity category and various practices, but there were detectable differences between subareas. The lowest agreement levels occurred in the subareas 'Planning and Coordination of Nursing Care' and 'Guiding of Care/Continued Care and Emotional Support'.

CONCLUSIONS

There is a need to develop the descriptions of subareas and to clarify the related concepts. Precise nursing documentation can promote a high level of agreement and reliable results. The traditional overall proportion of agreement does not provide an adequate picture of reliability - weighted kappa coefficients should be used instead.

REACTIVE NEUROMUSCULAR TRAINING RESULTS IN IMMEDIATE AND LONG TERM IMPROVEMENTS IN MEASURES OF HAMSTRING FLEXIBILITY: A CASE REPORT

BACKGROUND AND PURPOSE

Hamstring tightness is a common complaint among active individuals and patients are traditionally classified with tight hamstrings based on commonly accepted clinical exams including the active knee extension, active straight leg raise, and passive straight leg raise tests. Apparent hamstring tightness is a condition that is present in patients who have the perception of hamstring tightness and are classified with a tissue extensibility dysfunction but demonstrate immediate gains in hamstring range of motion following an intervention that does not address a tissue length dysfunction. Reactive neuromuscular training can be used as part of the evaluative process used to classify and treat patients with apparent hamstring tightness. The purpose of this case report was to identify, treat, and report the outcomes experienced when using a reactive neuromuscular training technique on a patient who was classified with hamstring inflexibility based on traditional testing methods.

CASE DESCRIPTION

A 20 year-old female softball player presented with a chief complaint of hamstring tightness of more than four years duration. The patient tested positive for hamstring inflexibility based on traditional testing methods. The patient was then treated using a reactive neuromuscular training technique in which the patient resisted a manual anterior to posterior force at the abdomen, sternum and across the hips while simultaneously bending forward at the hips in an attempt to touch her toes.

OUTCOMES

Following one reactive neuromuscular training treatment session the patient tested negative for hamstring inflexibility based on traditional testing methods and maintained those results at a five-week follow-up appointment.

DISCUSSION

The subject in this case report demonstrated the effectiveness of reactive neuromuscular training in identifying and treating apparent hamstring tightness. Based on these findings, clinicians should consider using reactive neuromuscular training to properly classify and treat patients with a chief complaint of hamstring "tightness."

LEVEL OF EVIDENCE

4 (single case report).

Using OR patient classification for staffing assignments

Traditionally, one nurse is assigned per OR. Recent health care reforms and the AORN "Position statement on perioperative safe staffing and on-call practices" require managers to rethink this practice. Staffing levels that are insufficient have been linked to sentinel events. A patient classification system that includes patient acuity and procedure complexity can be used to determine which surgical procedures require more than one RN circulator and offer a scientific basis for increasing staff budgetary requests. The goal is to experience fewer sentinel events while providing better patient care and achieving higher nurse retention.

Design and validation of the INICIARE instrument, for the assessment of dependency level in acutely ill hospitalised patients

AIMS AND OBJECTIVES

The aim of this study was to establish the validity and reliability of an instrument (Inventario del NIvel de Cuidados mediante IndicAdores de clasificación de Resultados de Enfermería) used to assess the dependency level in acutely hospitalised patients. This instrument is novel, and it is based on the Nursing Outcomes Classification.

BACKGROUND

Multiple existing instruments for needs assessment have been poorly validated and based predominately on interventions. Standardised Nursing Languages offer an ideal framework to develop nursing sensitive instruments.

DESIGN

A cross-sectional validation study in two acute care hospitals in Spain.

METHODS

This study was implemented in two phases. First, the research team developed the instrument to be validated. In the second phase, the validation process was performed by experts, and the data analysis was conducted to establish the psychometric properties of the instrument.

RESULTS

Seven hundred and sixty-one patient ratings performed by nurses were collected during the course of the research study. Data analysis yielded a Cronbach's alpha of 0·91. An exploratory factorial analysis identified three factors (Physiological, Instrumental and Cognitive-behavioural), which explained 74% of the variance.

CONCLUSIONS

Inventario del NIvel de Cuidados mediante IndicAdores de clasificación de Resultados de Enfermería was demonstrated to be a valid and reliable instrument based on its use in acutely hospitalised patients to assess the level of dependency.

RELEVANCE TO CLINICAL PRACTICE

Inventario del NIvel de Cuidados mediante IndicAdores de clasificación de Resultados de Enfermería can be used as an assessment tool in hospitalised patients during the nursing process throughout the entire hospitalisation period. It contributes information to support decisions on nursing diagnoses, interventions and outcomes. It also enables data codification in large databases.

Psychological profile and self-administered relaxation in patients with craniofacial pain: a prospective in-office study

INTRODUCTION

The objective of this study was to evaluate the psychological profile of craniofacial pain sufferers and the impact of patient subtype classification on the short-time effectiveness of a self-administered relaxation training.

METHODS

One hundred unselected in-office patients (67% females) suffering from chronic facial pain and/or headache with the presumptive diagnose of temporo-mandibular disorder (TMD) completed a questionnaire battery comprising craniofacial pain perception, somatic complaints, irrational beliefs, and pain behavior and were classified into subtypes using cluster analysis. They underwent a self-administered progressive relaxation training and were re-evaluated for pain perception after 3 months.

RESULTS

Pain was mild to moderate in the majority of patients. Symptom domains comprised parafunctional activities, temporo-mandibular pain and dysfunction, fronto-temporal headache, head/neck and neck/back pain. Three patient subtypes were identified regarding symptom/dysfunction level: (i) low burden (mild/moderate), (ii) psychosocial dysfunction (moderate/high), (iii) adaptive coping (moderate/mild). Self-rated adherence to the recommended relaxation training was moderate throughout the sample, but self-rated relief was significantly different between clusters. At follow-up, pain intensity was significantly decreased in all patients, whereas pain-related interference was improved only in dysfunctional and adaptive patients. Improvement of symptom domains varied between clusters and was most comprehensive in adaptive patients.

CONCLUSIONS

In conclusion, craniofacial pain sufferers can be divided in meaningful subtypes based on their pain perception, irrational beliefs, and pain behaviour. A self-administered relaxation training generally yielded positive effects on pain perception, however the benefit may be greater in patients with more marked symptom impact (both dysfunctional and adaptive).

The new version of a patient classification instrument: assessment of psychometric properties

AIMS

This paper assessed the reliability and construct validity of the new version of a patient classification instrument.

BACKGROUND

In the development of patient classification instruments, monitoring validity and reliability is essential to assure that patient care requirements and nursing staff workload are appropriately measured.

DESIGN METHOD

The sample included 194 patients (construct validity test) and 60 patients (inter-rater reliability test) at medical, surgical, and specialized wards of a teaching hospital in the south east of Brazil. The study was conducted in 2009-2010. For analysis purposes, Spearman's correlation and Cronbach's alpha (internal consistency) were used, and weighted kappa (inter-rater reliability), factor analysis with principal axis factoring extraction method (construct validity) and ordinal regression (instrument's predictive ability).

RESULTS

A high level of inter-rater agreement was found. The importance of all care areas and their contribution to distinguish patient care needs and category in the new instrument were demonstrated. Results also showed the instrument's high predictive ability (99·6%).

CONCLUSION

The findings give the evidence that the new scale is a reliable and valid tool to assess patient care needs and care category and that it can be used to guide nursing management practice in determining the nursing staff workload.

Pattern recognition analyses of brain activation elicited by happy and neutral faces in unipolar and bipolar depression

OBJECTIVES

Recently, pattern recognition approaches have been used to classify patterns of brain activity elicited by sensory or cognitive processes. In the clinical context, these approaches have been mainly applied to classify groups of individuals based on structural magnetic resonance imaging (MRI) data. Only a few studies have applied similar methods to functional MRI (fMRI) data.

METHODS

We used a novel analytic framework to examine the extent to which unipolar and bipolar depressed individuals differed on discrimination between patterns of neural activity for happy and neutral faces. We used data from 18 currently depressed individuals with bipolar I disorder (BD) and 18 currently depressed individuals with recurrent unipolar depression (UD), matched on depression severity, age, and illness duration, and 18 age- and gender ratio-matched healthy comparison subjects (HC). fMRI data were analyzed using a general linear model and Gaussian process classifiers.

RESULTS

The accuracy for discriminating between patterns of neural activity for happy versus neutral faces overall was lower in both patient groups relative to HC. The predictive probabilities for intense and mild happy faces were higher in HC than in BD, and for mild happy faces were higher in HC than UD (all p < 0.001). Interestingly, the predictive probability for intense happy faces was significantly higher in UD than BD (p = 0.03).

CONCLUSIONS

These results indicate that patterns of whole-brain neural activity to intense happy faces were significantly less distinct from those for neutral faces in BD than in either HC or UD. These findings indicate that pattern recognition approaches can be used to identify abnormal brain activity patterns in patient populations and have promising clinical utility as techniques that can help to discriminate between patients with different psychiatric illnesses.

Chronic venous insufficiency: clinical assessment and patient selection

Chronic venous insufficiency is a complex condition, with widely varied clinical manifestations, etiologies, and underlying pathophysiology. An orderly workup is mandatory to assess the nature of a patient's underlying venous disease. This begins in the office setting with a careful medical history, physical examination, and bedside diagnostic tests. These are augmented by confirmatory diagnostic testing, including duplex ultrasonography, venography, plethysmography, and ambulatory venous pressure measurement. Based upon the results of these examinations, the patient's venous disease can be classified according to standardized classification schemes, which in turn leads to the selection of an appropriate treatment strategy. This article outlines the steps in the clinical assessment and classification of patients with chronic venous insufficiency.