Using Autoregressive Integrated Moving Average (ARIMA) Modelling to Forecast Symptom Complexity in an Ambulatory Oncology Clinic: Harnessing Predictive Analytics and Patient-Reported Outcomes

Predicting which patients with cancer will see a psychiatrist or counsellor from their initial oncology consultation document using natural language processing

BACKGROUND

Patients with cancer often have unmet psychosocial needs. Early detection of who requires referral to a counsellor or psychiatrist may improve their care. This work used natural language processing to predict which patients will see a counsellor or psychiatrist from a patient's initial oncology consultation document. We believe this is the first use of artificial intelligence to predict psychiatric outcomes from non-psychiatric medical documents.

METHODS

This retrospective prognostic study used data from 47,625 patients at BC Cancer. We analyzed initial oncology consultation documents using traditional and neural language models to predict whether patients would see a counsellor or psychiatrist in the 12 months following their initial oncology consultation.

RESULTS

Here, we show our best models achieved a balanced accuracy (receiver-operating-characteristic area-under-curve) of 73.1% (0.824) for predicting seeing a psychiatrist, and 71.0% (0.784) for seeing a counsellor. Different words and phrases are important for predicting each outcome.

CONCLUSION

These results suggest natural language processing can be used to predict psychosocial needs of patients with cancer from their initial oncology consultation document. Future research could extend this work to predict the psychosocial needs of medical patients in other settings.

End-of-Life Symptom Burden among Patients with Cancer Who Were Provided Medical Assistance in Dying (MAID): A Longitudinal Propensity-Score-Matched Cohort Study

Cancer is the primary underlying condition for most Canadians who are provided Medical Assistance in Dying (MAID). However, it is unknown whether cancer patients who are provided MAID experience disproportionally higher symptom burden compared to those who are not provided MAID. Thus, we used a propensity-score-matched cohort design to evaluate longitudinal symptom trajectories over the last 12 months of patients' lives, comparing cancer patients in Alberta who were and were not provided MAID. We utilized routinely collected retrospective Patient-Reported Outcomes (PROs) data from the Edmonton Symptom Assessment System (ESAS-r) reported by Albertans with cancer who died between July 2017 and January 2019. The data were analyzed using mixed-effect models for repeated measures to compare differences in symptom trajectories between the cohorts over time. Both cohorts experienced increasing severity in all symptoms in the year prior to death (β from 0.086 to 0.231, p ≤ .001 to .002). Those in the MAID cohort reported significantly greater anxiety (β = -0.831, p = .044) and greater lack of appetite (β = -0.934, p = .039) compared to those in the non-MAID cohort. The majority (65.8%) of patients who received MAID submitted their request for MAID within one month of their death. Overall, the MAID patients did not experience disproportionally higher symptom burden. These results emphasize opportunities to address patient suffering for all patients with cancer through routine collection of PROs as well as targeted and early palliative approaches to care.

Disparities in the Place of Death for Patients With Malignant Neoplasms of the Thyroid Gland

Introduction This study aims to examine the disparities in the place of death for patients due to thyroid neoplasms and understand the mortality trends. The study also aims to assess the influence of factors like age, gender, geography, and race, thus allowing for the assessment and improvement of end-of-life and palliative care. Methodology The study analyzes thyroid cancer mortality trends from 1999 to 2020 using the Centers for Disease Control and Prevention Wide-ranging Online Data for Epidemiologic Research (CDC WONDER) database, taking into consideration locations of death, medical facilities, home and hospice care, and others. Additional categories such as race, gender, and U.S. census regions were variables chosen to segregate the deaths. Microsoft Excel (Microsoft Corporation, Redmond, Washington, United States) and autoregressive integrated moving average (ARIMA) modeling were used for data analysis. Results The study revealed that around 50% of thyroid cancer patients in the United States passed away at home or in hospice settings, while the other 50% died in medical facilities or nursing homes. Patients aged 65-74 and 75-84 were more likely to die at home or in hospice, and males had a higher likelihood of dying in these settings compared to females. Geographically, individuals in the South and West regions were more inclined to die at home or in hospice. Additionally, racial disparities were observed, with Black or African Americans being less likely than Whites to die in home or hospice settings. Conclusions Socio-demographic factors play a major role in shaping end-of-life care, underscoring the need for tailored interventions. There is also a need for more refined early diagnostic techniques for smaller, localized tumors. Future studies should investigate the relationship between profession and income and the incidence and mortality of thyroid cancer.

Prediction of early-onset colorectal cancer mortality rates in the United States using machine learning

INTRODUCTION

The current study, focusing on a significant US (United States) colorectal cancer (CRC) burden, employs machine learning for predicting future rates among young population.

METHODS

CDC WONDER data from 1999 to 2022 was analyzed for CRC-related mortality in patients younger than 56 years. Temporal trends in age-adjusted mortality rates (AAMRs) were assessed via Joinpoint software. Future mortality rates were forecasted using an optimal Autoregressive Integrated Moving Average (ARIMA) model.

RESULTS

From 1999 to 2022, we observed 150,908 deaths with CRC listed as the underlying cause, predominantly in males, with an upward trend in AAMR. The ARIMA model projects an increase in CRC mortality by 2035, estimating an average annual percent change (AAPC) of 1.3% overall, 1% for females, and 1.5% for males.

CONCLUSION

Our study findings emphasize the need for more robust preventive measures to reduce future CRC mortality among younger population. These results have significant implications for public health policies, particularly for males under 56, and underscore the importance of early screening and lifestyle modifications.

Clinical Integration of Digital Patient-Reported Outcome Measures in Primary Health Care for Chronic Disease Management: Protocol for a Systematic Review

BACKGROUND

Health measurement guides policies and health care decisions are necessary to describe and attain the quintuple aim of improving patient experience, population health, care team well-being, health care costs, and equity. In the primary care setting, patient-reported outcome measurement allows outcome comparisons within and across settings and helps improve the clinical management of patients. However, these digital patient-reported outcome measures (PROMs) are still not adapted to the clinical context of primary health care, which is an indication of the complexity of integrating these tools in this context. We must then gather evidence of their impact on chronic disease management in primary health care and understand the characteristics of effective implementation.

OBJECTIVE

We will conduct a systematic review to identify and assess the impact of electronic PROMs (ePROMs) implementation in primary health care for chronic disease management. Our specific objectives are to (1) determine the impact of ePROMs in primary health care for chronic disease management and (2) compare and contrast characteristics of effective ePROMs' implementation strategies.

METHODS

We will conduct a systematic review of the literature in accordance with the guidelines of the Cochrane Methods Group and in compliance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines for its reporting. A specific search strategy was developed for relevant databases to identify studies. Two reviewers will independently apply the inclusion criteria using full texts and will extract the data. We will use a 2-phase sequential mixed methods synthesis design by conducting a qualitative synthesis first, and use its results to perform a quantitative synthesis.

RESULTS

This study was initiated in June 2022 by assembling the research team and the knowledge transfer committee. The preliminary search strategy will be developed and completed in September 2022. The main search strategy, data collection, study selection, and application of inclusion criteria were completed between October and December 2022.

CONCLUSIONS

Results from this review will help support implementation efforts to accelerate innovations and digital adoption for primary health care and will be relevant for improving clinical management of chronic diseases and health care services and policies.

TRIAL REGISTRATION

PROSPERO International Prospective Register of Systematic Reviews CRD42022333513; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=333513.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/48155.

Patient-Reported Symptom Complexity and Acute Care Utilization Among Patients With Cancer: A Population-Based Study Using a Novel Symptom Complexity Algorithm and Observational Data

BACKGROUND

Patients with cancer in Canada are often effectively managed in ambulatory settings; however, patients with unmanaged or complex symptoms may turn to the emergency department (ED) for additional support. These unplanned visits can be costly to the healthcare system and distressing for patients. This study used a novel patient-reported outcomes (PROs)-derived symptom complexity algorithm to understand characteristics of patients who use acute care, which may help clinicians identify patients who would benefit from additional support.

PATIENTS AND METHODS

This retrospective observational cohort study used population-based linked administrative healthcare data. All patients with cancer in Alberta, Canada, who completed at least one PRO symptom-reporting questionnaire between October 1, 2019, and April 1, 2020, were included. The algorithm used ratings of 9 symptoms to assign a complexity score of low, medium, or high. Multivariable binary logistic regressions were used to evaluate factors associated with a higher likelihood of having an ED visit or hospital admission (HA) within 7 days of completing a PRO questionnaire.

RESULTS

Of the 29,133 patients in the cohort, 738 had an ED visit and 452 had an HA within 7 days of completing the PRO questionnaire. Patients with high symptom complexity had significantly higher odds of having an ED visit (OR, 3.10; 95% CI, 2.59-3.70) or HA (OR, 4.20; 95% CI, 3.36-5.26) compared with low complexity patients, controlling for demographic covariates.

CONCLUSIONS

Given that patients with higher symptom complexity scores were more likely to use acute care, clinicians should monitor these more complex patients closely, because they may benefit from additional support or symptom management in ambulatory settings. A symptom complexity algorithm can help clinicians easily identify patients who may require additional support. Using an algorithm to guide care can enhance patient experiences, while reducing use of acute care services and the accompanying cost and burden.

Emotion Regulation Flexibility and Electronic Patient-Reported Outcomes: A Framework for Understanding Symptoms and Affect Dynamics in Pediatric Psycho-Oncology

Simple Summary

The individual’s ability to conceive and regulate the broad spectrum of their human emotions is closely linked to their mental health. The implications of a serious disease such as cancer represent an extraordinary burden to these internal coping mechanisms, especially in the case of young patients. Regarding their well-being and support, it is therefore of particular interest for caregivers to be able to follow the dynamics of the patient’s emotional world and perceptions. Technical progress enables new possibilities for data collection through tools for digital patient self-reports while simultaneously creating new challenges. Within the scope of this article, we provide an overview of the literature on this topic, outlining the current strengths and weaknesses and possible perspectives on digital aids, especially in terms of capturing the flexibility, fluctuations and early detection of symptom changes.

Abstract

Emotion dysregulation is regarded as a driving mechanism for the development of mental health problems and psychopathology. The role of emotion regulation (ER) in the management of cancer distress and quality of life (QoL) has recently been recognized in psycho-oncology. The latest technological advances afford ways to assess ER, affective experiences and QoL in child, adolescent and young adult (CAYA) cancer patients through electronic patient-reported outcomes (ePRO) in their daily environment in real-time. Such tools facilitate ways to study the dynamics of affect and the flexibility of ER. However, technological advancement is not risk-free. We critically review the literature on ePRO in cancer existing models of ER in pediatric psycho-oncology and analyze strength, weaknesses, opportunities and threats of ePRO with a focus on CAYA cancer research and care. Supported by personal study-based experiences, this narrative review serves as a foundation to propose a novel methodological and metatheoretical framework based on: (a) an extended notion of ER, which includes its dynamic, adaptive and flexible nature and focuses on processes and conditions rather than fixed categorical strategies; (b) ePRO as a means to measure emotion regulation flexibility and affect dynamics; (c) identifying early warning signals for symptom change via ePRO and building forecasting models using dynamical systems theory.

Understanding the Symptoms and Concerns of Adolescents and Young Adults with Cancer in Alberta: A Comparative Cohort Study Using Patient-Reported Outcomes

Purpose: Adolescents and young adults (AYAs) with cancer are in a unique situation due to their age and developmental stage in life and may have different symptoms and concerns than older patients. Patient-Reported Outcomes (PROs) questionnaires, routinely used in Alberta, can help identify the distinct needs of AYAs. We aimed to compare PROs data for AYAs and older adults (OAs) to better understand how the concerns of AYAs differ, which is key to providing individualized care and creating targeted programming and system-level change. Methods: Retrospective data were collected for two patient cohorts who completed at least one PROs questionnaire between October 1, 2019 and April 1, 2020. The AYA cohort was aged 18-39, and the OA cohort was aged 40 and older. Symptoms were compared using mean scores and multiple linear regression, and concerns were compared using counts and multivariate negative binomial regression. Results: AYAs had significantly higher mean scores on depression and anxiety, compared to OAs, and lower mean scores for most physical symptoms. They indicated significantly more concerns in the Emotional and Social/Family/Spiritual domains, and were over three times more likely to indicate Work/School as a concern. Conclusion: AYAs with cancer have distinct concerns that should be addressed to ensure comprehensive, quality cancer care for this population. PROs data are useful in identifying needs and facilitating evidence-based, data-driven change at all levels of the health care system.