Natural language processing and String Metric-assisted Assessment of Semantic Heterogeneity method for capturing and standardizing unstructured nursing activities in a hospital setting: a retrospective study

BACKGROUND

Nurses record data in electronic health records (EHRs) using different terminologies and coding systems. The purpose of this study was to identify unstructured free-text nursing activities recorded by nurses in EHRs with natural language processing (NLP) techniques and to map these nursing activities into standard nursing activities using the SMASH method.

STUDY DESIGN

A retrospective study using NLP techniques with a unidirectional mapping strategy called SMASH.

METHODS

The unstructured free-text nursing activities recorded in the Medicine, Neurology and Gastroenterology inpatient units of the Agostino Gemelli IRCCS University Hospital Foundation, Rome, Italy were collected for 6 months in 2018. Data were analyzed by three phases: a) text summarization component with NLP techniques, b) a consensus analysis by four experts to detect the category of word stems, and c) cross-mapping with SMASH. The SMASH method calculated the string comparison, similarity and distance of words through the Levenshtein distance (LD), Jaro-Winker distance and the cross-mapping's cut-offs: map [0.80-1.00] with < 13 LD, partial-map [0.50-0.79] with <13 LD and no map [0.0-0.49] with >13 LD.

RESULTS

During the study period, 491 patient records were assessed. 548 different unstructured free-text nursing activities were recorded by nurses. 451 unstructured free-text nursing activities (82.3%) were mapped to standard PAI nursing activities, 47 (8.7%) were partial mapped, while 50 (9.0%) were not mapped. This automated mapping yielded recall of 0.95%, precision of 0.94%, accuracy of 0.91%, F-measure of 0.96. The F-measure indicates good reliability of this automated procedure in cross-mapping.

CONCLUSIONS

Lexical similarities between unstructured free-text nursing activities and standard nursing activities were found, NLP with the SMASH method is a feasible approach to extract data related to nursing concepts that are not recorded through structured data entry.

Interventions to support family caregivers of people with advanced dementia at the end of life in nursing homes: A mixed-methods systematic review

BACKGROUND

Most people with dementia transition into nursing homes as their disease progresses. Their family caregivers often continue to be involved in their relative's care and experience high level of strain at the end of life.

AIM

To gather and synthesize information on interventions to support family caregivers of people with advanced dementia at the end of life in nursing homes and provide a set of recommendations for practice.

DESIGN

Mixed-Methods Systematic Review (PROSPERO no. CRD42020217854) with convergent integrated approach.

DATA SOURCES

Five electronic databases were searched from inception in November 2020. Published qualitative, quantitative, and mixed-method studies of interventions to support family caregivers of people with advanced dementia at the end of life in nursing home were included. No language or temporal limits were applied.

RESULTS

In all, 11 studies met the inclusion criteria. Data synthesis resulted in three integrated findings: (i) healthcare professionals should engage family caregivers in ongoing dialog and provide adequate time and space for sensitive discussions; (ii) end-of-life discussions should be face-to-face and supported by written information whose timing of supply may vary according to family caregivers' preferences and the organizational policies and cultural context; and (iii) family caregivers should be provided structured psychoeducational programs tailored to their specific needs and/or regular family meetings about dementia care at the end of life.

CONCLUSION

The findings provide useful information on which interventions may benefit family caregivers of people with advanced dementia at the end of life and where, when, and how they should be provided.

Translation and cross-cultural adaptation of the Clinical Care Classification system

INTRODUCTION

The Clinical Care Classification (CCC) system is one of the standard nursing terminologies recognized by the American Nurses Association, developed to describe nursing care through electronic documentation in different healthcare settings. The translation of the CCC system into languages other than English is useful to promote its widespread use in different countries and to provide the standard nursing data necessary for interoperable health information exchange. The aim of this study was to translate the CCC system from English to Italian and to test its clinical validity.

METHODS

A translation with cross-cultural adaptation was performed in four phases: forward-translation, back-translation, review, and dissemination. Subsequently a pilot cross-mapping study between nursing activities in free-text nursing documentation and the CCC interventions was conducted.

RESULTS

All elements of the CCC system were translated into Italian. Semantic and conceptual equivalences were achieved. Altogether 77.8% of the nursing activities were mapped into CCC interventions.

CONCLUSIONS

The CCC system, and its integration into electronic health records, has the potential to support Italian nurses in describing and providing outcomes and costs of their care in different healthcare settings. Future studies are needed to strengthen the impact of the CCC system on clinical practice.

[Development MPI_AGE and SOSIA classification to evaluate geriatric patients'care needs.]

INTRODUCTION

Today's healthcare system requires more care for older patients. Aim of this study is to determine the relationships between the SOSIA classification system and the MPI_AGE index (Multidimensional Prognostic Index) based on a Comprehensive Geriatric Assessment (CGA).

METHOD

The comparison was made by the retrieval of information from the CBA social-health folder, User Management (SOSIA Area) and MPI Computer Archive. The cross-mapping has been developed by a dedicate working group using Delphi process.

RESULTS

From January 2018 to April 2018, 100 geriatric patients were assessed by cross-mapping the two classification systems applied to an Italian Nursing Home. Among these patients, 100% were women (mean age 82 years). SOSIA form 1 was the most frequent classification system with 45% of patients followed by SOSIA form 3 (31%), form 7 (16%), form 8 (5%), form 5 (3%) and (MPI_AGE= 3 with 79% of patients). Using the MPI_AGE system, the patients analyzed in class 1 has MPI= 0.81, with Activities of Daily Living (ADL= 0), Instrumental Activities of Daily Living (IADL= 0), Short Portable Mental Status Questionnaire (SPMSQ= 10), Mini Nutritional Assessement (MNAShort= 12), Exton-Smith= 11, Cumulative Index Rating Scale - Comorbidity Index (CIRS= 8), drugs assumed= 5.

DISCUSSION

The benif of a comparison between different classification systems may be found in a more accurately treatment of older patient with an "individual personalized care plan".

Developing a subset of ICNP nursing diagnoses for medical and surgical hospital settings, informed by an Italian nursing conceptual model: a multicenter cross-sectional study

BACKGROUND

The International Classification for Nursing Practice (ICNP) is designed to facilitate the expression of nursing diagnoses, interventions and outcomes. The development of the ICNP subsets may support nurses by providing appropriate terms for documenting nursing care. This project aimed to develop a subset of ICNP nursing diagnoses oriented by an Italian Nursing Conceptual Model (MPI) to describe nursing clinical data in medical and surgical acute hospital wards.

STUDY DESIGN

A subset of ICNP nursing diagnoses was developed based on a literature review and on an expert consensus. A cross-sectional study was conducted in three Northern Italian hospitals to empirically test the subset in target settings.

METHODS

In accordance with the guidelines adopted by the International Council of Nursing, the study followed the process for developing an ICNP subset. Twelve expert nurses from clinical settings and nursing education in surgical and medical care participated in a Delphi method to further validate the subset. A cross-mapping process has been implemented and the prevalence of diagnoses was described. Data were collected from healthcare documentation of admitted patients, including, retrospectively, nursing clinical data from the patients' admission date to the time of data collection.

RESULTS

Documentation from 476 admitted patients was analysed: 228 were from surgical and 248 from medical wards. 24,142 nursing diagnoses were detected consulting retrospectively each documentation. A total number of 21,401 nursing diagnoses (88%) were fully mapped by the ICNP subset.

CONCLUSION

Results showed a high capability of ICNP terminology to describe nursing care in acute medical and surgical areas in Italian hospitals. The identified subset of ICNP diagnoses could be a valuable way to support a computerized documentation system for hospitals using MPI and ICNP. Results could be used to start revising nursing education programs in order to introduce this nursing standardized terminology combining it with the nursing conceptual model in use.

[Assessment of geriatric patients' care needs based on sosia classification: the reality of the lombardy region in nursing home.]

The increased demand to care that originates from demographic changes called in Italy a rapid development in Nursing Home with particular emergency the problem of programme the welfare response. It is essential the development of a classification system able to describe the stratification of the case mix on the basis of the care requirements, allowing a remuneration in function of the complexity care. Since 2003, the Lombardy region has introduced a case-mix reimbursement system for nursing homes based on the SOSIA form which classifies residents into eight classes of frailty. In the present study the agreement between SOSIA classification and other well documented instruments, including Barthel Index, Mini-Mental State Examination on the basis of three indicators (mobility, cognition, comorbidity) is evaluated in eight classes of frailty. However, it is not any research project was published in order to assess the agreement between SOSIA classification and other measuring instruments. Although various methods exist by which researchers have attempted to measure the need for nursing care, there is no nationally accepted system for determining the total amount of registered nursing resources required by residents in long-term care. The aim of this study was to evaluate the correlation between SOSIA and filing systems widely used, such as the degree of Barthel disability rating scale, the Mini-Mental State Examination to offer care appropriate for the case-mix. Only the higher complexity care has classified in the first two classes, while the remaining levels has categorized in the lowest paid. Misclassification therefore induces an underestimation of the real care needs and, consequently, inadequate remuneration.