Machine Learning Techniques, Applications, and Potential Future Opportunities in Pressure Injuries (Bedsores) Management: A Systematic Review

Standardised Pressure Injury Prevention Protocol (SPIPP- Adult) Checklist 2.0: Language and Content Validity Study

INTRODUCTION

Implementation of clinical practice guidelines, an important strategy in the prevention of pressure injuries, enables the nurse to interpret evidence-based guideline recommendations, reduce errors, ensure compliance and standardisation of complex processes, manage patient-related risks and systematically regulate all preventable conditions.

OBJECTIVE

This study was conducted to ensure the Turkish language and content validity of the Standardised Pressure Injury Prevention Protocol (SPIPP- Adult) Checklist 2.0.

METHOD

In this methodological research study, a five-stage technique was used in the translation of the SPIPP- Adult Checklist 2.0, which was created and revised by Joyce Pitmann et al. based on the International 2019 Clinical Practice Guidelines, into Turkish. These stages included initial translation, evaluation of initial translation, back translation, evaluation of back translation and expert opinion. Davis technique was used to determine the content validity of SPIPP- Adult Checklist 2.0.

RESULTS

The scale was translated into Turkish and back-translated into the original language and the opinions of nine experts were obtained. The content validity scores of the SPIPP- Adult Checklist 2.0 were found to be between 0.88 and 1.0 and the total CGI score was calculated as 0.99. This value shows that content validity is at an acceptable level. After expert evaluations, it was decided that the final version of the scale was appropriate for use.

CONCLUSION

This study demonstrated that the SPIPP- Adult Checklist 2.0 is a valid tool. Interventions using the evidence-based checklist should be integrated into the workflow and provide the best opportunity for successful and sustainable pressure injury prevention.

Risk prediction tools for pressure injury occurrence: an umbrella review of systematic reviews reporting model development and validation methods

BACKGROUND

Pressure injuries (PIs) place a substantial burden on healthcare systems worldwide. Risk stratification of those who are at risk of developing PIs allows preventive interventions to be focused on patients who are at the highest risk. The considerable number of risk assessment scales and prediction models available underscores the need for a thorough evaluation of their development, validation, and clinical utility. Our objectives were to identify and describe available risk prediction tools for PI occurrence, their content and the development and validation methods used.

METHODS

The umbrella review was conducted according to Cochrane guidance. MEDLINE, Embase, CINAHL, EPISTEMONIKOS, Google Scholar, and reference lists were searched to identify relevant systematic reviews. The risk of bias was assessed using adapted AMSTAR-2 criteria. Results were described narratively. All included reviews contributed to building a comprehensive list of risk prediction tools.

RESULTS

We identified 32 eligible systematic reviews only seven of which described the development and validation of risk prediction tools for PI. Nineteen reviews assessed the prognostic accuracy of the tools and 11 assessed clinical effectiveness. Of the seven reviews reporting model development and validation, six included only machine learning models. Two reviews included external validations of models, although only one review reported any details on external validation methods or results. This was also the only review to report measures of both discrimination and calibration. Five reviews presented measures of discrimination, such as the area under the curve (AUC), sensitivities, specificities, F1 scores, and G-means. For the four reviews that assessed the risk of bias assessment using the PROBAST tool, all models but one were found to be at high or unclear risk of bias.

CONCLUSIONS

Available tools do not meet current standards for the development or reporting of risk prediction models. The majority of tools have not been externally validated. Standardised and rigorous approaches to risk prediction model development and validation are needed.

TRIAL REGISTRATION

The protocol was registered on the Open Science Framework ( https://osf.io/tepyk ).

A novel technique for rapid determination of pressure injury stages using intelligent machine vision

A developed intelligent machine vision system combined with deep-learning algorithms was attempted to determine pressure injury (PI) stages rapidly. A total of 500 images were selected according to the color and texture characteristics of probable PI sites closely related to fie PI stages based on the guidance of PI experts. Each target box of the PI site was labeled by the same researcher for label consistency. Characteristic values of pressure injuries were extracted from segmented images for further model construction. In developing the rapid determination models, five you just look once (YOLO) pattern recognition models (i.e., YOLO8n, YOLO8s, YOLO8m, YOLO8l, and YOLO8x) were constructed, and they were optimized among 100 epochs. Compared with other models, the YOLO8l model showed the best result, with the precision values among pressure injury stage I to V (i.e., PI_I, PI_II, PI_III, PI_IV, and PI_V) of 0.98, 0.97, 0.95, 0.95, and 0.94, respectively. The overall results suggest that this intelligent machine vision system is useful for PI stage determination and perhaps other disease diagnoses closely related to color and texture characteristics.

The 2023 Update on Pressure Injuries: A Review of the Literature

GENERAL PURPOSE

To provide a summary of six articles published in 2023 that provide important new data or insights about pressure injuries (PIs).

TARGET AUDIENCE

This continuing education activity is intended for physicians, physician assistants, nurse practitioners, and registered nurses with an interest in skin and wound care.

LEARNING OBJECTIVES/OUTCOMES

After participating in this educational activity, the participant will:1. Summarize selected current evidence addressing the prevention of PIs.2. Evaluate new studies exploring PI treatment modalities.3. Identify recent findings concerning the role of artificial intelligence in staging PIs.

Inter-rater reliability among healthcare professionals in assessing postoperative wound photos for the presence or absence of surgical wound dehiscence: A Pretest - Posttest study

BACKGROUND

Surgical wound dehiscence (SWD) has various definitions, which complicates accurate and uniform diagnosis. To address this, the World Union Wound Healing Societies (WUWHS) presented a consensus based definition and classification for SWD (2018).

AIM

This quasi-experimental pretest-posttest study investigates the inter-rater reliability among healthcare professionals (HCP) and wound care professionals (WCP) when assessing wound photos on the presence or absence of SWD before and after training on the WUWHS-definition.

METHODS

Wound expert teams compiled a set of twenty photos (SWD+: nineteen, SWD-: one), and a video training. Subsequently, 262 healthcare professionals received the pretest link to assess wound photos. After completion, participants received the posttest link, including a (video) training on the WUWHS-definition, and reassessment of fourteen photos (SWD+: thirteen, SWD-: one).

PRIMARY OUTCOMES

1) pretest-posttest inter-rater-reliability among participants in assessing photos in congruence with the WUWHS-definition 2) the impact of training on assessment scores.

SECONDARY OUTCOME

familiarity with the WUWHS-definition.

RESULTS

One hundred thirty-one participants (65 HCPs, 66 WCPs) completed both tests. The posttest inter-rater reliability among participants for correctly identifying SWD was increased from 67.6 % to 76.2 %, reaching statistical significance (p-value: 0.001; 95 % Confidence Interval [1.8-2.2]). Sub-analyses per photo showed improved SWD posttest scores in thirteen photos, while statistical significance was reached in seven photos. Thirty-three percent of participants knew the WUWHS-definition.

CONCLUSION

The inter-rater reliability among participants increases after training on the WUWHS-definition. The definition provides diagnostic criteria for accurate SWD diagnosis. Widespread use of the definition may improve uniformity in care for patients with SWD.

One Month Prediction of Pressure Ulcers in Nursing Home Residents with Bayesian Networks

OBJECTIVES

Pressure ulcers (PUs) are a common and avoidable condition among residents of nursing homes, and their consequences are severe. Reliable and simple identification of high-risk residents is a major challenge for prevention. Available tools like the Braden and Norton scale have imperfect predictive performance. The objective is to predict the occurrence of PUs in nursing home residents from electronic health record (EHR) data.

DESIGN

Longitudinal retrospective nested case-control study.

SETTING AND PARTICIPANTS

EHR database of French nursing homes from 2013 to 2022.

METHODS

Residents who suffered from PUs were cases and those who did not were controls. For cases, we analyzed the data available in their EHR 1 month before the occurrence of the first PU. For controls, we used available data 1 month before an index date adjusted on the delays of PU onset. We conducted a Bayesian network (BN) analysis, an explainable machine learning method, using 136 input variables of potential medical interest determined with experts. To validate the model, we used scores, features selection, and explainability tools such as Shapley values.

RESULTS

Among 58,368 residents analyzed, 29% suffered from PUs during their stay. The obtained BN model predicts the occurrence of a PU at a 1-month horizon with a sensitivity of 0.94 (±0.01), a precision of 0.32 (±0.01) and an area under the curve of 0.69 (±0.02). It selects 3 variables: length of stay, delay since last hospitalization, and dependence for transfer. This BN model is suitable and simpler than models provided by other machine learning methods.

CONCLUSIONS AND IMPLICATIONS

One-month prediction for incident PU is possible in nursing home residents from their EHR data. The study paves the way for the development of a predictive tool fueled by routinely collected data that do not require additional work from health care professionals, thereby opening a new preventive strategy for PUs.

Implementable Prediction of Pressure Injuries in Hospitalized Adults: Model Development and Validation

Background

Numerous pressure injury prediction models have been developed using electronic health record data, yet hospital-acquired pressure injuries (HAPIs) are increasing, which demonstrates the critical challenge of implementing these models in routine care.

Objective

To help bridge the gap between development and implementation, we sought to create a model that was feasible, broadly applicable, dynamic, actionable, and rigorously validated and then compare its performance to usual care (ie, the Braden scale).

Methods

We extracted electronic health record data from 197,991 adult hospital admissions with 51 candidate features. For risk prediction and feature selection, we used logistic regression with a least absolute shrinkage and selection operator (LASSO) approach. To compare the model with usual care, we used the area under the receiver operating curve (AUC), Brier score, slope, intercept, and integrated calibration index. The model was validated using a temporally staggered cohort.

Results

A total of 5458 HAPIs were identified between January 2018 and July 2022. We determined 22 features were necessary to achieve a parsimonious and highly accurate model. The top 5 features included tracheostomy, edema, central line, first albumin measure, and age. Our model achieved higher discrimination than the Braden scale (AUC 0.897, 95% CI 0.893-0.901 vs AUC 0.798, 95% CI 0.791-0.803).

Conclusions

We developed and validated an accurate prediction model for HAPIs that surpassed the standard-of-care risk assessment and fulfilled necessary elements for implementation. Future work includes a pragmatic randomized trial to assess whether our model improves patient outcomes.

Differential effects of electronic patient record systems for wound care on hospital-acquired pressure injuries: Findings from a secondary analysis of German hospital data

INTRODUCTION

Despite the improvements made in recent decades, the OECD regards hospital-acquired pressure injuries (HAPI) as high priority areas for actions to ensure patient safety. This study was aimed at investigating the degree of utilization of two types of electronic patient record systems for wound care on lowering HAPI rates. Furthermore, the effect of user satisfaction with the systems and perceived alignment with clinical processes should be studied.

MATERIAL AND METHODS

A regression analysis of post-stratified data from German hospitals obtained from the Hospital Quality Reports (observed/expected HAPI ratio) and the IT Report Healthcare was performed. The sample comprised 319 hospitals reporting on digital wound record systems and 199 hospitals on digital nursing record systems for system utilization and the subset of hospitals using a digital system for user satisfaction and process alignment.

RESULTS

The study revealed a significant effect of hospital ownership for both types of systems and a significant interaction of ownership and system utilization for digital wound record systems: Only the for-profit hospitals benefited from a higher degree of system utilization with a lower HAPI ratio. In contrast, non-profit hospitals yielded a reversed pattern, with increasing HAPI rates matching an increased system utilization. User satisfaction (significant) and the perceived alignment of the clinical process (trend) of the digital nursing record system were related with lower HAPI ratios.

DISCUSSION

These findings point to a differential effect of system utilization on HAPI ratios depending on hospital ownership, and they demonstrate that those users who are satisfied with the system can act as catalysts for better care. The explained variance was small but comparable to other studies. Furthermore, it shows that explaining quality care is a complex undertaking. Sheer utilization has no effect while a differential perspective on the facilitators and barriers might help to explain the patient outcomes.

Insights into pressure injury prevention: Assessing the knowledge, attitudes, and practices of Palestinian nursing students

AIM

To assess the knowledge, attitudes, and practices of Palestinian nursing students towards pressure injury prevention.

MATERIALS AND METHODS

A descriptive cross-sectional study was conducted with 455 nursing students recruited from Arab American University-Palestine, employing a total population sample. Data collection forms include socio-demographic information, the Pressure Ulcer Knowledge Assessment Tool, Attitude towards Pressure Ulcer Prevention Instrument and Pressure Injury Preventive Practices scale.

RESULTS

The study found that students had a mean knowledge score of 54% (14.04/26), a positive attitude score of 75.8% (39.42/52), and demonstrated a fair level of practice 75.3% (30.12/40). Significant differences were observed in the Knowledge, Attitude, and Practice total scores, linked to academic year, clinical experience, and the number of attended departments during clinical training (p < 0.001). Additionally, weak but significant positive relationships were found between practice and attitude scores (r = 0.303, p < 0.001), practice and knowledge score (r = 0.211, p < 0.001), and a moderate positive significant relationship between knowledge and attitude scores (r = 0.567, p < 0.001).

CONCLUSION

The study revealed insufficient knowledge, positive attitudes, and somewhat unsafe practices among nursing students regarding pressure injury prevention. It highlights the need for specific revisions in the nursing curriculum. Improvements can be achieved through detailed coverage in classrooms and laboratories, integrating simulation methods. Additionally, ensuring that students gain adequate experiences in clinical units, with a specific emphasis on pressure injury prevention, is crucial for improving students' capability and contribute to better pressure injury management.

Artificial intelligence in wound care: diagnosis, assessment and treatment of hard-to-heal wounds: a narrative review

OBJECTIVE

The effective assessment of wounds, both acute and hard-to-heal, is an important component in the delivery by wound care practitioners of efficacious wound care for patients. Improved wound diagnosis, optimising wound treatment regimens, and enhanced prevention of wounds aid in providing patients with a better quality of life (QoL). There is significant potential for the use of artificial intelligence (AI) in health-related areas such as wound care. However, AI-based systems remain to be developed to a point where they can be used clinically to deliver high-quality wound care. We have carried out a narrative review of the development and use of AI in the diagnosis, assessment and treatment of hard-to-heal wounds. We retrieved 145 articles from several online databases and other online resources, and 81 of them were included in this narrative review. Our review shows that AI application in wound care offers benefits in the assessment/diagnosis, monitoring and treatment of acute and hard-to-heal wounds. As well as offering patients the potential of improved QoL, AI may also enable better use of healthcare resources.

Evaluating the Effectiveness of an Alternating Pressure Overlay in Patients Undergoing Cardiothoracic Surgery

LOCAL PROBLEM

In 2019 and the first half of 2020, our facility experienced an increase in the number and severity of hospital-acquired pressure injuries (HAPIs) among our cardiothoracic surgery population. Fifty percent of these HAPIs occurred within 72 hours of surgery. A review of the literature revealed that alternating pressure overlays (APOs) have been successfully used to prevent HAPIs in surgical patients.

PURPOSE

The primary purpose of our quality improvement (QI) project was to measure perioperative HAPI rates in cardiothoracic surgery patients after the addition of APOs to our HAPI prevention protocol. Our secondary purpose was to identify common factors among those patients who developed HAPIs.

METHODS

This QI project collected both pre- and postintervention data and compared the findings. A nurse-led team was responsible for measuring HAPI rates during the intervention-from July through October 2020-which involved placing an APO under cardiothoracic surgery patients during the 72-hour perioperative period. APOs were placed on all operating room (OR) tables and remained with the patients following surgery. Bed linens and skin care products were standardized for consistency. Lifts were used to reduce friction during repositioning.

RESULTS

During preintervention data collection, we identified 10 patients who developed HAPIs (seven out of 1,174 cardiothoracic surgery patients in 2019, for a HAPI rate of 0.6%, and three out of 333 patients in the first half of 2020, for a HAPI rate of 0.9%). During the four-month intervention period, in which APOs were used in 331 patients undergoing cardiothoracic surgery, no HAPIs developed.

CONCLUSION

Use of an APO in cardiothoracic ORs and critical care units may help reduce HAPI rates.

Systematic Review for Risks of Pressure Injury and Prediction Models Using Machine Learning Algorithms

Pressure injuries are increasing worldwide, and there has been no significant improvement in preventing them. This study is aimed at reviewing and evaluating the studies related to the prediction model to identify the risks of pressure injuries in adult hospitalized patients using machine learning algorithms. In addition, it provides evidence that the prediction models identified the risks of pressure injuries earlier. The systematic review has been utilized to review the articles that discussed constructing a prediction model of pressure injuries using machine learning in hospitalized adult patients. The search was conducted in the databases Cumulative Index to Nursing and Allied Health Literature (CINAHIL), PubMed, Science Direct, the Institute of Electrical and Electronics Engineers (IEEE), Cochrane, and Google Scholar. The inclusion criteria included studies constructing a prediction model for adult hospitalized patients. Twenty-seven articles were included in the study. The defects in the current method of identifying risks of pressure injury led health scientists and nursing leaders to look for a new methodology that helps identify all risk factors and predict pressure injury earlier, before the skin changes or harms the patients. The paper critically analyzes the current prediction models and guides future directions and motivations.

Nurses' and nursing students' knowledge and attitudes to pressure injury prevention: A meta-analysis based on APUP and PUKAT

BACKGROUND

Morbidity and mortality among patients due to pressure injuries continue to rise. Nurses play a critical role in preventing pressure injuries. However, published results on nurses' knowledge and attitudes for pressure injury prevention are often contradictory.

OBJECTIVES

To conduct a meta-analysis of nurses' and nursing students' knowledge and attitudes toward pressure injury prevention.

DESIGN

A meta-analysis of cross-sectional studies.

DATA SOURCES

Ten databases were queried for the meta-analysis. The search period was from the time of the databases' establishment to February 2023.

REVIEW METHODS

This review followed the preferred reporting items for systematic reviews and meta-analyses (PRISMA) guidelines. The Agency for Healthcare Research and Quality (AHRQ) was used to assess the methodological quality of the included studies. Statistical analysis was conducted with the Stata 15.0 software, and the quantitative data of knowledge and attitude toward preventing PI in all studies were summarized.

RESULTS

Thirteen studies from 9 countries were included. The meta-analysis showed that nurses and nursing students had low knowledge but positive attitudes toward pressure injury prevention. Subgroup analysis showed that the pooled proportion of both knowledge and attitudes was higher in Asia than in Europe. Nurses had higher knowledge than nursing students, however, the former had a more negative attitude than the latter. Sensitivity analyses were robust. Egger's test showed no significant publication bias.

CONCLUSION

The knowledge of nurses and nursing students about pressure injury prevention is not promising and there is an urgent need for continuous learning. Attitudes are more positive but there is room for improvement. The relevant departments should strengthen nurses' and nursing students' knowledge of pressure injury prevention and further improve their attitudes toward pressure injury prevention.

An Integrated System of Braden Scale and Random Forest Using Real-Time Diagnoses to Predict When Hospital-Acquired Pressure Injuries (Bedsores) Occur

BACKGROUND AND OBJECTIVES

Bedsores/Pressure Injuries (PIs) are the second most common diagnosis in healthcare system billing records in the United States and account for 60,000 deaths annually. Hospital-Acquired Pressure Injuries (HAPIs) are one classification of PIs and indicate injuries that occurred while the patient was cared for within the hospital. Until now, all studies have predicted who will develop HAPI using classic machine algorithms, which provides incomplete information for the clinical team. Knowing who will develop HAPI does not help differentiate at which point those predicted patients will develop HAPIs; no studies have investigated when HAPI develops for predicted at-risk patients. This research aims to develop a hybrid system of Random Forest (RF) and Braden Scale to predict HAPI time by considering the changes in patients' diagnoses from admission until HAPI occurrence.

METHODS

Real-time diagnoses and risk factors were collected daily for 485 patients from admission until HAPI occurrence, which resulted in 4619 records. Then for each record, HAPI time was calculated from the day of diagnosis until HAPI occurrence. Recursive Feature Elimination (RFE) selected the best factors among the 60 factors. The dataset was separated into 80% training (10-fold cross-validation) and 20% testing. Grid Search (GS) with RF (GS-RF) was adopted to predict HAPI time using collected risk factors, including Braden Scale. Then, the proposed model was compared with the seven most common algorithms used to predict HAPI; each was replicated for 50 different experiments.

RESULTS

GS-RF achieved the best Area Under the Curve (AUC) (91.20 ± 0.26) and Geometric Mean (G-mean) (91.17 ± 0.26) compared to the seven algorithms. RFE selected 43 factors. The most dominant interactable risk factors in predicting HAPI time were visiting ICU during hospitalization, Braden subscales, BMI, Stimuli Anesthesia, patient refusal to change position, and another lab diagnosis.

CONCLUSION

Identifying when the patient is likely to develop HAPI can target early intervention when it is needed most and reduces unnecessary burden on patients and care teams when patients are at lower risk, which further individualizes the plan of care.