Medical Evidence Influence on Inpatients and Nurses Pain Ratings Agreement

Pseudo-labeling based adaptations of pain domain classifiers

Introduction

Each human being experiences pain differently. In addition to the highly subjective phenomenon, only limited labeled data, mostly based on short-term pain sequences recorded in a lab setting, is available. However, human beings in a clinic might suffer from long painful time periods for which even a smaller amount of data, in comparison to the short-term pain sequences, is available. The characteristics of short-term and long-term pain sequences are different with respect to the reactions of the human body. However, for an accurate pain assessment, representative data is necessary. Although pain recognition techniques, reported in the literature, perform well on short-term pain sequences. The collection of labeled long-term pain sequences is challenging and techniques for the assessment of long-term pain episodes are still rare. To create accurate pain assessment systems for the long-term pain domain a knowledge transfer from the short-term pain domain is inevitable.

Methods

In this study, we adapt classifiers for the short-term pain domain to the long-term pain domain using pseudo-labeling techniques. We analyze the short-term and long-term pain recordings of physiological signals in combination with electric and thermal pain stimulation.

Results and conclusions

The results of the study show that it is beneficial to augment the training set with the pseudo labeled long-term domain samples. For the electric pain domain in combination with the early fusion approach, we improved the classification performance by 2.4% to 80.4% in comparison to the basic approach. For the thermal pain domain in combination with the early fusion approach, we improved the classification performance by 2.8% to 70.0% in comparison to the basic approach.

Observed and Perceived Pain: Findings of a Cross-Sectional Study in Hospitalized Subjects

BACKGROUND

Pain constitutes a serious problem of a health, economic, ethical, and social equity nature affecting negatively quality of life. Its assessment is often subjected to overestimation or underestimation.

AIM

The aim of this study is threefold: (1) to estimate the prevalence of pain in hospitalized patients; (2) to assess the grade of correlation between the level of pain observed by the nurses and the pain perceived by the patients; and (3) to examine the level of scientific knowledge among the healthcare professionals.

DESIGN

Cross-sectional study.

METHODS

The intensity level of observed and perceived pain has been evaluated in 401 patients with validated scales. Analyzed data have been extracted from the electronic medical record and integrated into the data-collection sheet. A questionnaire has been submitted to nurses to investigate their level of knowledge on pain assessment and management.

RESULTS

The study included 350 patients out of 401; for 51 patients the "pain" data was missing. Prevalence of perceived pain was 40.15%. Nurses overestimated pain in 7.43% of cases and underestimated it in 24.9%. The majority of the nursing staff claimed to be aware of the pain topic, however, they showed some uncertainties in clinical practice.

CONCLUSIONS

The differential variation between the observed pain and the perceived one resulted in 43.71% of cases, highlighting the dependence on the two variables: "area of hospitalization" and "intensity level". The observation and monitoring of pain did not appear to be a consolidated practice, thus representing an important area for investments in the nursing profession.

Multimodal automatic assessment of acute pain through facial videos and heart rate signals utilizing transformer-based architectures

Accurate and objective pain evaluation is crucial in developing effective pain management protocols, aiming to alleviate distress and prevent patients from experiencing decreased functionality. A multimodal automatic assessment framework for acute pain utilizing video and heart rate signals is introduced in this study. The proposed framework comprises four pivotal modules: the Spatial Module, responsible for extracting embeddings from videos; the Heart Rate Encoder, tasked with mapping heart rate signals into a higher dimensional space; the AugmNet, designed to create learning-based augmentations in the latent space; and the Temporal Module, which utilizes the extracted video and heart rate embeddings for the final assessment. The Spatial-Module undergoes pre-training on a two-stage strategy: first, with a face recognition objective learning universal facial features, and second, with an emotion recognition objective in a multitask learning approach, enabling the extraction of high-quality embeddings for the automatic pain assessment. Experiments with the facial videos and heart rate extracted from electrocardiograms of the BioVid database, along with a direct comparison to 29 studies, demonstrate state-of-the-art performances in unimodal and multimodal settings, maintaining high efficiency. Within the multimodal context, 82.74% and 39.77% accuracy were achieved for the binary and multi-level pain classification task, respectively, utilizing 9.62 million parameters for the entire framework.

ASAD: A Novel Audification Console for Assessment and Communication of Pain and Discomfort

Pain and discomfort are subjective perceptions that are difficult to quantify. Various methods and scales have been developed to find an optimal manner to describe them; however, these are difficult to use with some categories of patients. Audification of pain has been utilized as feedback in rehabilitation settings to enhance motor perception and motor control, but not in assessment and communication settings. We present a novel tool, the Audification-console for Self-Assessment of Discomfort (ASAD), for assessing and communicating pain and discomfort through sound. The console is a sequence of increasing pitch and frequencies triggered at the press of buttons and displayed as a matrix that can be associated with the subjective perception of pain and discomfort. The ASAD has been evaluated in its ability to capture and communicate discomfort, following a fatigue test in the lower limbs with thirty healthy volunteers, and compared to the most common self-reported methods used in the NHS. (The National Health Service (NHS) is the publicly funded healthcare system in England and one of the four National Health Service systems in the United Kingdom.) This was a qualitative, within subjects and across groups experiment study. The console provides a more accurate assessment than other scales and clearly recognizable patterns of sounds, indicating increased discomfort, significantly localized in specific frequency ranges, thus easily recognizable across subjects and in different instances of the same subject. The results suggest a possible use of the ASAD for a more precise and automatic assessment of pain and discomfort in health settings. Future studies might assess if this is easier to use for patients with communication or interpretation difficulties with the traditional tools.

Risk factors for underestimation of patient pain in outpatient colonoscopy

BACKGROUND

Adequate management of patient pain and discomfort during colonoscopy is crucial to obtaining a high-quality examination. We aimed to investigate the ability of endoscopists and endoscopy assistants to accurately assess patient pain in colonoscopy.

METHODS

This was a single-center, cross-sectional study including patients scheduled for an outpatient colonoscopy. Procedure-related pain, as experienced by the patient, was scored on a verbal rating scale (VRS). Endoscopists and endoscopy assistants rated patient pain likewise. Cohen's kappa was used to measure the agreement between ratings and logistic regression applied to test for potential predictors associated with underestimation of moderate-severe pain.

RESULTS

In total, 785 patients [median age: 54 years; females: n = 413] were included. Mild, moderate, and severe pain was reported in 378/785 (48%), 168/785 (22%), and 111/785 (14%) procedures respectively. Inter-rater reliability of patient pain comparing patients with endoscopists was κ = 0.29, p < .001 and for patients with endoscopy assistants κ = 0.37, p < .001. In the 279 patients reporting moderate/severe pain, multivariable analysis showed that male gender (OR = 1.79), normal BMI (OR = 1.71), no history of abdominal surgery (OR = 1.81), and index-colonoscopy (OR = 1.81) were factors significantly associated with a risk for underestimation of moderate/severe pain by endoscopists. Young age (OR = 2.05) was the only corresponding factor valid for endoscopy assistants.

CONCLUSIONS

In a colonoscopy, estimation of patient pain by endoscopists and endoscopy assistants is often inaccurate. Endoscopists need to pay specific attention to subgroups of patients, such as male gender, and normal BMI, among whom there seems to be an important risk of underestimation of moderate-severe pain.

Cognitive and implicit biases in nurses' judgment and decision-making: A scoping review

BACKGROUND

Cognitive and implicit biases of healthcare providers can lead to adverse events in healthcare and have been identified as a patient safety concern. Most research on the impact of these systematic errors in judgment has been focused on diagnostic decision-making, primarily by physicians. As the largest component of the workforce, nurses make numerous decisions that affect patient outcomes; however, literature on nurses' clinical judgment often overlooks the potential impact of bias on these decisions. The aim of this study was to map the evidence and key concepts related to bias in nurses' judgment and decision-making, including interventions to correct or overcome these biases.

METHODS

We conducted a scoping review using Joanna Briggs methodology. In November 2020 we searched CINAHL, PsychInfo, and PubMed databases to identify relevant literature. Inclusion criteria were primary research about nurses' bias; evidence of a nursing decision or action; and English language. No date or geographic limitations were set.

RESULTS

We found 77 items that met the inclusion criteria. Over half of these items were published in the last 12 years. Most research focused on implicit biases related to racial/ethnic identity, obesity, and gender; other articles examined confirmation, attribution, anchoring, and hindsight biases. Some articles examined heuristics and were included if they described the process of, and the problems with, nurse decision-making. Only 5 studies tested interventions to overcome or correct biases. 61 of the studies relied on vignettes, surveys, or recall methods, rather than examining real-world nursing practice. This could be a serious oversight because contextual factors such as cognitive load, which have a significant impact on judgment and decision-making, are not necessarily captured with vignette or survey studies. Furthermore, survey and vignette studies make it difficult to quantify the impact of these biases in the healthcare system.

CONCLUSIONS

Given the serious effects that bias has on nurses' clinical judgment, and thereby patient outcomes, a concerted, systematic effort to identify and test debiasing strategies in real-world nursing settings is needed.

TWEETABLE ABSTRACT

Bias affects nurses' clinical judgment - we need to know how to fix it.

Classism in Pain Care: The Role of Patient Socioeconomic Status on Nurses’ Pain Assessment and Management Practices

Objective

Research on social disparities in pain care has been mainly focused on the role of race/racism and sex/sexism. Classism in pain assessment and management practices has been much less investigated. We aimed to test the effect of patient socioeconomic status (SES; a proxy of social class) on nurses’ pain assessment and management practices and whether patient SES modulated the effects of patient distress and evidence of pathology on such practices.

Design

Two experimental studies with a two (patient SES: low/high) by two (patient distress or evidence of pathology: absent/present) between-subject design.

Subjects

Female nurses participated in two experimental studies (N = 150/N = 158).

Methods

Nurses were presented with a vignette/picture depicting the clinical case of a female with chronic low back pain, followed by a video of the patient performing a pain-inducing movement. Afterwards, nurses reported their pain assessment and management practices.

Results

The low-SES patient’s pain was assessed as less intense, more attributed to psychological factors, and considered less credible (in the presence of distress cues) than the higher-SES patient’s pain. Higher SES buffered the detrimental impact of the presence of distress cues on pain assessment. No effects were found on management practices.

Conclusions

Our findings point to the potential buffering role of SES against the detrimental effect of certain clinical cues on pain assessments. This study contributes to highlighting the need for further investigation of the role of SES/social class on pain care and its underlying meanings and processes.