An integrated model of multimorbidity and symptom science

Symptom-BERT: Enhancing Cancer Symptom Detection in EHR Clinical Notes

CONTEXT

Extracting cancer symptom documentation allows clinicians to develop highly individualized symptom prediction algorithms to deliver symptom management care. Leveraging advanced language models to detect symptom data in clinical narratives can significantly enhance this process.

OBJECTIVE

This study uses a pretrained large language model to detect and extract cancer symptoms in clinical notes.

METHODS

We developed a pretrained language model to identify cancer symptoms in clinical notes based on a clinical corpus from the Enterprise Data Warehouse for Research at a healthcare system in the Midwestern United States. This study was conducted in 4 phases:1 pretraining a Bio-Clinical BERT model on one million unlabeled clinical documents,2 fine-tuning Symptom-BERT for detecting 13 cancer symptom groups within 1112 annotated clinical notes,3 generating 180 synthetic clinical notes using ChatGPT-4 for external validation, and4 comparing the internal and external performance of Symptom-BERT against a non-pretrained version and six other BERT implementations.

RESULTS

The Symptom-BERT model effectively detected cancer symptoms in clinical notes. It achieved results with a micro-averaged F1-score of 0.933, an AUC of 0.929 internally, and 0.831 and 0.834 externally. Our analysis shows that physical symptoms, like Pruritus, are typically identified with higher performance than psychological symptoms, such as anxiety.

CONCLUSION

This study underscores the transformative potential of specialized pretraining on domain-specific data in boosting the performance of language models for medical applications. The Symptom-BERT model's exceptional efficacy in detecting cancer symptoms heralds a groundbreaking stride in patient-centered AI technologies, offering a promising path to elevate symptom management and cultivate superior patient self-care outcomes.

Interventions Addressing Symptoms in Older Adults with Multimorbidity: An Umbrella Review

This umbrella review was to synthesize the summarized evidence-based research regarding interventions addressing symptoms in older populations with multimorbidity. Three databases including PsycINFO, MEDLINE, and CINAHL were searched systematically. The JBI Methodology for Umbrella Reviews and the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statements were used to report this review. Six reviews published between 2016 and 2010 were included for analysis. Interventions were mixed and included components on health-related behaviors, body systems or functions, activities and participation domains, and the environment. Outcomes concerning physiological/clinical functioning were most reported. The evidence regarding the symptoms-related interventions was mixed, but all showed promising outcomes compared with usual care or not. To sum up, this umbrella review reveals the lack of strong empirical evidence for the effectiveness of intervention addressing symptoms in older adults with multimorbidity. It highlights the need to evaluate the established approach of interventions further to support this population.

Living with multimorbidity: A qualitative exploration of shared experiences of patients, family caregivers, and healthcare professionals in managing symptoms in the United States

AIMS

To elicit experiences of patients, family caregivers, and healthcare professionals in intermediate care units (IMCUs) in an academic medical centre in Baltimore, MD related to the challenges and intricacies of multimorbidity management to inform development of a multimorbidity symptom management toolkit.

DESIGN

Experience-based co-design.

METHODS

Between July and October 2021, patients aged 55 years and older with multimorbidity admitted to IMCUs at an academic medical centre in Baltimore, Maryland, USA were recruited and interviewed in person. Interdisciplinary healthcare professionals working in the IMCU were interviewed virtually. Participants were asked questions about their role in recognizing and treating symptoms, factors affecting the quality of life, symptom burden and trajectory over time, and strategies that have and have not worked for managing symptoms. An inductive thematic analysis approach was used for analysis.

RESULTS

Twenty-three interviews were conducted: 9 patients, 2 family caregivers, and 12 healthcare professionals. Patients' mean age was 67.5 (±6.5) years, over half (n = 5) were Black or Hispanic, and the average number of comorbidities was 3.67. Five major themes that affect symptom management emerged: (1) the patient-provider relationship; (2) open and honest communication; (3) accessibility of resources during hospitalization and at discharge; (4) caregiver support, training, and education; and (5) care coordination and follow-up care.

CONCLUSION

Patients, caregivers, and healthcare professionals often have similar goals but different priorities for multimorbidity management. It is imperative to identify shared priorities and target holistic interventions that consider patient and caregiver experiences to improve outcomes.

IMPLICATIONS FOR THE PROFESSION AND/OR PATIENT CARE AND IMPACT

This paper addresses the paucity of research related to the shared experience of disease trajectory and symptom management for people living with multimorbidity. We found that patients, caregivers, and healthcare professionals often have similar goals but different care and communication priorities. Understanding differing priorities will help better design interventions to support symptom management so people with multimorbidity can have the best possible quality of life.

REPORTING METHOD

We have adhered to the Consolidated Criteria for Reporting Qualitative Studies (COREQ) guidelines in our reporting.

PATIENT OR PUBLIC CONTRIBUTION

This study has been designed and implemented with patient and public involvement throughout the process, including community advisory board engagement in the project proposal phase and interview guide development, and member checking in the data collection and analysis phases. The method we chose, experience-based co-design, emphasizes the importance of engaging members of a community to act as experts in their own life challenges. In the coming phases of the study, the public will be involved in developing and testing a new intervention, informed by these qualitative interviews and co-design events, to support symptom management for people with multimorbidity.

Multidimensional Model of Energy in Patients With Cancer

OBJECTIVES

Evidence suggests that energy is a distinct symptom from fatigue in patients with cancer. The purpose of this paper is to present the Multidimensional Model of Energy in Patients with Cancer (MMEPC) that is based on emerging evidence and to make recommendations for clinical practice and future research.

METHODS

The literature was reviewed to determine various factors associated with variations in energy in patients with cancer. In addition, some of the emerging evidence in the model is supported by studies of energy in the general population and in patients with other chronic conditions.

RESULTS

Based on a review of the literature, specific concepts in the MMEPC include: person factors, clinical factors, cancer-related factors, biological factors, factors associated with energy balance, and co-occurring symptoms. The evidence to support the association between each of these factors and variations in energy levels in patients with cancer is described and synthesized.

CONCLUSION

This article provides emerging evidence on factors that influence variations in energy levels in patients with cancer. While the fundamental biobehavioral and biologic mechanisms that underlie variations in energy levels are not well understood, the model can be used to design pre-clinical and clinical studies of energy in patients with cancer. In addition, while emerging evidence supports the hypothesis that fatigue and energy are distinct symptoms, additional research on common and distinct risk factors and underlying mechanisms is warranted to be able to develop and test precision interventions for one or both symptoms.

IMPLICATIONS FOR NURSING PRACTICE

The risk factors (eg, being female, sleep quality) associated with variations in energy levels in patients with cancer identified in this paper have important clinical implications. Clinicians can use the identified risk factors to guide their assessments; identify high-risk patients with decrements in energy decrement; and develop targeted energy conservation interventions for the patients.

The Development and Implementation of the Fast-Pace Assessment Framework and Tiered Analgesic Orders for Opioid Optimization

BACKGROUND

Within the context of the opioid epidemic, changes needed to be made in the prescription and administration of analgesics. The purpose of this paper is to describe the development and implementation of a project that utilized a holistic pain assessment framework and introduced new order sets to guide the integration of nonopioid, opioid, and co-analgesics in a quaternary care medical center.

METHODS

An interdisciplinary team updated policies and procedures for pain assessment and opioid administration and created new analgesic order sets for both adult and pediatric patients. Following requisite approvals, these order sets were integrated into the electronic health record. Education of clinicians, patients, and caregivers was provided to facilitate implementation of these new clinical practices.

RESULTS

Prescribers' levels of adherence with the use of the pain order sets ranged from 80% to 90% and no adverse effects were reported. Education of nursing staff was incorporated into hospital orientation. Ongoing evaluations are providing insights into how the new policies and procedures can be optimized to ensure reliable, safe, and effective pain management.

CONCLUSIONS

Since the implementation of the opioid optimization project, adherence with the tiered, multimodal approach to analgesic prescribing is high. Next steps include both qualitative and quantitative evaluations of the benefits and challenges associated with this practice change. For example, systems will be developed to monitor nurses' adherence with the implementation of the pain order sets and the use of both pharmacologic and nonpharmacologic pain management interventions.

Social Determinants of Health and Multimorbidity Among Adults 50 Years and Older in the United States

BACKGROUND

Living with two or more chronic conditions simultaneously-known as multimorbidity-has become increasingly prevalent as the aging population continues to grow. However, the factors that influence the development of multimorbidity are still not fully understood.

OBJECTIVES

The purpose of this study was to investigate the prevalence of multimorbidity among U.S. adults 50 years and older and identify associated factors with multimorbidity.

METHODS

We used data from four cycles from the National Health and Nutrition Examination Survey (2011-2018) to examine the associations between social determinants of health and multimorbidity among American adults aged 50 years and older. A set of variables on socioeconomic status and health behaviors was chosen based on the social determinants of health conceptual framework developed by the World Health Organization. In our study, 4,552 participants were included. All analyses were accounted for a complex survey design and the use of survey weights. Multiple logistic regression analyses were performed to examine the associated factors with multimorbidity.

RESULTS

The average age was 63.1 years, and 52.9% were female. The average number of chronic conditions was 2.27. The prevalence of multimorbidity was 63.8%, with high cholesterol and hypertension being the most prevalent conditions. In the adjusted model, age, gender, household income, citizenship status, health insurance, healthcare access, body mass index, and smoking status were found to be associated with living with multimorbidity.

DISCUSSION

Our results indicate that continued efforts aimed at promoting smoking cessation and maintaining a healthy weight will be beneficial in preventing the onset of chronic conditions. Additional research is warranted to gain a deeper understanding of the interrelationships between gender, race/ethnicity, household income, citizenship status, health insurance, and healthcare access as social determinants of health in the context of multimorbidity. Further research will help us develop targeted interventions and policies to address disparities and improve health outcomes for individuals with multimorbidity.

Systematic Review of the Literature on Multiple Co-occurring Symptoms in Patients Receiving Treatment for Gynecologic Cancers

OBJECTIVE

Patients with gynecologic cancers experience a very high symptom burden that has a negative impact on their quality of life. This systematic review aims to identify the common co-occurring symptoms, the prevalence of common symptoms, common instruments used to measure symptoms, associated risk factors, and the symptom burden in patients with gynecologic cancers.

DATA SOURCES

A search of four databases (ie, PubMed, Embase, Web of Science, and CINAHL) was done from January 1, 2012, through September 5, 2022. A qualitative synthesis of the extant literature was performed using Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines (PRISMA 2020).

CONCLUSION

A total of 118 studies met the prespecified inclusion criteria. Ninety-six symptoms were assessed across these studies. The top six symptoms and their grand mean prevalence rates were lack of energy (64.4%), fatigue (62.1%), abdominal pain (53.3%), depression (52.6%), concentration dysfunction (52.0%), and drowsiness (51.9%). Numerous methodologic challenges were evident across studies. Future research needs to develop a disease-specific symptom assessment measure, evaluate for risk factors associated with a higher symptom burden, and determine the impact of multiple symptoms on patient outcomes.

IMPLICATION FOR NURSING PRACTICE

The results are relevant for oncology clinicians to assess patients with gynecologic cancers for the presence of common symptoms and risk factors for higher symptom burden in the patients and to offer effective management interventions.

Cancer-Related Symptom Frameworks Using a Biopsychosocial-Spiritual Perspective: A Scoping Review

BACKGROUND

Research to understand and manage cancer-related symptoms continues to advance, yet work that more fully adopts a biopsychosocial-spiritual view of symptoms is needed.

OBJECTIVE

The purpose of this article is to review existing frameworks that have the potential to guide research on cancer-related symptoms, to explore the characteristics of each framework, and to appraise each using a biopsychosocial-spiritual lens.

METHODS

A scoping review was conducted to identify available frameworks that could be applied to guide cancer-related symptom research and to assess their characteristics. Research questions and criteria were formulated at the outset, followed by identifying relevant publications detailing novel frameworks, charting data, and collating results. Upon identification of available frameworks, each was appraised for alignment with a standard definition of "biopsychosocial-spiritual."

RESULTS

Eleven frameworks were identified to guide cancer-related symptom research. All were developed in the United States, led by nurse scientists, including symptom experiences as well as their antecedents and outcomes, and could be applied to one or more concurrent cancer-related symptoms. While all 11 frameworks included biopsychosocial dimensions, only 4 included spirituality.

CONCLUSIONS

Four biopsychosocial-spiritual frameworks offer unique insight to support advancement of cancer-related symptom research and practice from a holistic perspective. This foundational work could lead to development and validation of new frameworks and modification of existing frameworks to more closely align with a biopsychosocial-spiritual view of cancer-related symptoms. This review offers a starting point to carefully and explicitly adopt frameworks in research and practice with increased emphasis on considering spiritual dimensions of symptoms.

Understanding multimorbidity requires sign-disease networks and higher-order interactions, a perspective

Background

Count scores, disease clustering, and pairwise associations between diseases remain ubiquitous in multimorbidity research despite two major shortcomings: they yield no insight into plausible mechanisms underlying multimorbidity, and they ignore higher-order interactions such as effect modification.

Objectives

We argue that two components are currently missing but vital to develop novel multimorbidity metrics. Firstly, networks should be constructed which consists simultaneously of signs, symptoms, and diseases, since only then could they yield insight into plausible shared biological mechanisms underlying diseases.Secondly, learning pairwise associations is insufficient to fully characterize the correlations in a system. That is, synergistic (e.g., cooperative or antagonistic) effects are widespread in complex systems, where two or more elements combined give a larger or smaller effect than the sum of their individual effects. It can even occur that pairs of symptoms have no pairwise associations whatsoever, but in combination have a significant association. Therefore, higher-order interactions should be included in networks used to study multimorbidity, resulting in so-called hypergraphs.

Methods

We illustrate our argument using a synthetic Bayesian Network model of symptoms, signs and diseases, composed of pairwise and higher-order interactions. We simulate network interventions on both individual and population levels and compare the ground-truth outcomes with the predictions from pairwise associations.

Conclusion

We find that, when judged purely from the pairwise associations, interventions can have unexpected 'side-effects' or the most opportune intervention could be missed. The hypergraph uncovers links missed in pairwise networks, giving a more complete overview of sign and disease associations.

Impact of Dementia on Long-Term Hip Fracture Surgery Outcomes: An Electronic Health Record Analysis

OBJECTIVE

Older adults with dementia are at higher risk for sustaining hip fracture and their long-term health outcomes after surgery are usually worse than those without dementia. Widespread adoption of electronic health records (EHRs) may allow hospitals to better monitor long-term health outcomes in patients with dementia after hospitalization. This study aimed to (1) estimate how dementia influences discharge location, mortality, and readmission 180 days and 1 year after hip fracture surgery in older adults, and (2) demonstrate the feasibility of using selection-bias reduced EHR data for research and long-term health outcomes monitoring.

DESIGN

Retrospective observational cohort study using EHRs.

SETTING AND PARTICIPANTS

A cohort of 1171 patients over age 65 years who had an initial hip fracture surgery between October 2015 and December 2018 was extracted from EHRs of one health system; 376 of these patients had dementia.

METHODS

Logistic regression was applied to estimate influences of dementia on discharge disposition and Cox proportional hazards model for mortality. The Fine and Gray regression model was used to analyze readmission, accounting for the competing risk of death. To reduce selection bias in EHRs, inverse probability of treatment weighting using propensity scores was implemented before modeling.

RESULTS

Dementia had significant impacts on all outcomes: being discharged to facilities [odds ratio (OR) = 2.11, 95% confidence interval (CI) 1.19-3.74], 180-day mortality [hazard ratio (HR) = 1.69, 95% CI 1.20-2.38], 1-year mortality (HR = 1.78, 95% CI 1.33-2.38), 180-day readmission (HR = 1.62, 95% CI 1.39-1.89), and 1 year readmission (HR = 1.39, 95% CI 1.21-1.58).

CONCLUSIONS AND IMPLICATIONS

Dementia was a significant risk factor for worse long-term outcomes. The inverse probability of treatment weighting approach can be used to reduce selection bias in EHR data for research and monitoring long-term health outcomes in the target population. Such monitoring could foster collaborations with post-acute and long-term health care services to improve recovery outcomes in patients with dementia after hip fracture surgery.

The Association of Multimorbidity With Whole Health Activities Among Adults in the United States: Evidence From the NHIS and BRFSS

Background

Whole health is a holistic approach encompassing integrative medicine, emotional, and spiritual health and is critical to improving health outcomes among individuals with multimorbidity.

Objective

To examine the prevalence of Whole Health activities and the association of multimorbidity and Whole Health activities using nationally representative datasets.

Methods

As no single dataset has information on Whole Health self-care activities, data from the 2017 National Health Interview Survey (n = 25 134) was used to measure participants' mind-body therapy usage, sleep, mental health, and physical activity. We used the 2017 Behavioral Risk Factor Surveillance System (n = 347 029) to assess regular vegetable and/or fruit consumption.

Results

A significantly lower percentage of adults with multimorbidity had adequate sleep (58.2%vs.67.1%), no psychological distress (71.8%vs.82.1%), adequate physical activity (48.2%vs.62.1%), and regular vegetable and/or fruit consumption (54.2%vs.56.6%) compared to those without multimorbidity. Although lower percentages of adults with multimorbidity utilized mind-body therapies (22.9%vs.25.2%), the association was reversed when adjusted for socioeconomic factors. In the fully adjusted models, adults with multimorbidity were more likely to use mind-body therapies (AOR = 1.19, 95%CI = 1.09, 1.31). Furthermore, when adjusting for other independent variables, the associations of multimorbidity with sleep, psychological distress, and diet were exacerbated, and the association of multimorbidity with physical activity was attenuated.

Conclusion

Adults with multimorbidity were less likely to engage in most of the Whole Health activities except mind-body therapies compared to the no multimorbidity group. Findings suggest that adjustment for other factors such as age and socioeconomic status changed the magnitude and direction of the association of multimorbidity with Whole Health activities.

Examining the variability of multiple daily symptoms over time among individuals with multiple long-term conditions (MLTC-M/multimorbidity): An exploratory analysis of a longitudinal smartwatch feasibility study

Introduction

People living with multiple long-term conditions (MLTC-M) (multimorbidity) experience a range of inter-related symptoms. These symptoms can be tracked longitudinally using consumer technology, such as smartphones and wearable devices, and then summarised to provide useful clinical insight.

Aim

We aimed to perform an exploratory analysis to summarise the extent and trajectory of multiple symptom ratings tracked via a smartwatch, and to investigate the relationship between these symptom ratings and demographic factors in people living with MLTC-M in a feasibility study.

Methods

'Watch Your Steps' was a prospective observational feasibility study, administering multiple questions per day over a 90 day period. Adults with more than one clinician-diagnosed long-term condition rated seven core symptoms each day, plus up to eight additional symptoms personalised to their LTCs per day. Symptom ratings were summarised over the study period at the individual and group level. Symptom ratings were also plotted to describe day-to-day symptom trajectories for individuals.

Results

Fifty two participants submitted symptom ratings. Half were male and the majority had LTCs affecting three or more disease areas (N = 33, 64%). The symptom rated as most problematic was fatigue. Patients with increased comorbidity or female sex seemed to be associated with worse experiences of fatigue. Fatigue ratings were strongly correlated with pain and level of dysfunction.

Conclusion

In this study we have shown that it is possible to collect and descriptively analyse self reported symptom data in people living with MLTC-M, collected multiple times per day on a smartwatch, to gain insights that might support future clinical care and research.

Children and adolescents are not small adults: towards a better understanding of multimorbidity in younger populations

Multimorbidity is of increasing importance for the health of both children and adults but research has hitherto focused on adult multimorbidity. Hence, public awareness, practice and policy lack vital information about multimorbidity in childhood and adolescence. We convened an international and interdisciplinary group of experts from six nations to identify key priorities supported by published evidence to strengthen research for children and adolescent with multimorbidity. Future research is encouraged 1) To develop a conceptual framework to capture unique aspects of child and adolescent multimorbidity - including definitions, characteristic patterns of conditions for different age groups, its dynamic nature through childhood and adolescence and understanding of severity and trajectories for different clusters of multiple chronic conditions, 2) To define new indices to classify the presence of multimorbidity in children and adolescents, 3) To improve the availability and linkage of data across countries, 4) To synthesize evidence on the global phenomenon of multimorbidity in childhood and adolescence as well as health inequalities, 5) To involve children and adolescents in research relevant to their health.

Integrating Multimorbidity into a Whole-Body Understanding of Disease Using Spatial Genomics

Multimorbidity is characterized by multidimensional complexity emerging from interactions between multiple diseases across levels of biological (including genetic) and environmental determinants and the complex array of interactions between and within cells, tissues and organ systems. Advances in spatial genomic research have led to an unprecedented expansion in our ability to link alterations in genome folding with changes that are associated with human disease. Studying disease-associated genetic variants in the context of the spatial genome has enabled the discovery of transcriptional regulatory programmes that potentially link dysregulated genes to disease development. However, the approaches that have been used have typically been applied to uncover pathological molecular mechanisms occurring in a specific disease-relevant tissue. These forms of reductionist, targeted investigations are not appropriate for the molecular dissection of multimorbidity that typically involves contributions from multiple tissues. In this perspective, we emphasize the importance of a whole-body understanding of multimorbidity and discuss how spatial genomics, when integrated with additional omic datasets, could provide novel insights into the molecular underpinnings of multimorbidity.

Symptom experience of older oncology patients with low versus high levels of multimorbidity prior to chemotherapy

PURPOSE

Evaluate for differences in demographic and clinical characteristics between older oncology patients with low multimorbidity (<2 multimorbidities) and high multimorbidity (≥2 multimorbidities) and evaluate for differences in symptom occurrence, severity, and distress ratings between the two groups.

METHODS

Symptoms of older oncology patients (n = 125) were assessed using the Memorial Symptom Assessment Scale prior to chemotherapy administration. Data were analyzed using t-tests for continuous variables and Chi-square or Fisher's exact tests for categorical variables.

RESULTS

For the total sample, lack of energy and pain were the two most common symptoms. Compared to the low multimorbidity group, the high multimorbidity group had a higher number of symptoms and significantly higher occurrence rates for feeling nervous, difficulty sleeping, dry mouth, and pain. Compared to the low multimorbidity group, the high multimorbidity group had significantly higher severity ratings for pain, feeling sad, lack of energy, feeling drowsy, and worrying. For distress, the high multimorbidity group reported significantly higher ratings for pain, worrying, feeling sad, feeling nervous, and "I don't look like myself". No differences were found in any demographic or clinical characteristics between the two multimorbidity groups.

CONCLUSIONS

Multimorbidity is associated with higher symptom occurrence, severity, and distress in older oncology patients. Our findings suggest that the symptoms with the highest severity ratings were not the most distressing. Clinicians should identify multimorbidities and assess symptoms prior to chemotherapy to identify patients at increased risk and initiate referrals for interventions.

Self-Regulation Strategies Among Community-Dwelling People Aging With Arthritis and Multimorbidity

Self-regulation strategies of selection, optimization, and compensation (SR-SOC) have been found to predict arthritis self-efficacy and quality of life among community-dwelling people aging with arthritis and multimorbidity. The current study aimed to describe the health resources and chronic disabling symptom characteristics of community-dwelling people aging with arthritis and multimorbidity and investigate how these characteristics influence and predict SR-SOC strategies in managing arthritis multimorbidity after controlling for demographics and comorbidities. One hundred forty individuals aged >50 years completed surveys on demographics, comorbidities, health resources, symptoms, and SR-SOC strategy use frequencies. Descriptive statistics were used to describe sample characteristics. Correlations and multivariate hierarchical stepwise regressions were used to examine the associated characteristics and predictors for SR-SOC strategy use frequency. Lower health literacy, health care provider communication quality, and smaller social network were reported less often than arthritis in general. Significant predictors of SR-SOC strategy use were physical symptoms, health care provider communication quality, and age (p < 0.05). Better symptom management and health care provider communication quality could help promote self-regulation. [Journal of Gerontological Nursing, 47(1), 35-45.].