Intelligent Palliative Care Based on Patient-Reported Outcome Measures

Evaluation of the Concept of Value-Based Healthcare Applied to an Integrated Palliative Care Program in Colombia

OBJECTIVE

This study aimed to evaluate the "Value-Based Healthcare" concept of an integrated palliative care (PC) program in Bogotá, Colombia, through the measurement of health outcomes and care costs in the last 3 months of life.

METHODS

A multicenter, retrospective cohort study that included patients ≥18 years old who died in 2020 due to medical conditions amenable to PC. The measured health outcomes included pain, wellbeing, comfort, quality of life (QOL), and satisfaction. We analyzed the behavior of overall care costs during the last 3 months of the patients' lives and controlled for the effect of exposure to the program, considering the disease type and insurance coverage, using a linear regression model, nearest-neighbor matching, and sensitivity analysis.

RESULTS

Among patients exposed to the program, the mean pain score was 2.1/10 (± 1.3) and wellbeing was rated at 3.5/10 (± 1.0), comfort at 1.6/24 (± 1.3), QOL at 3.6/5.0 (± 0.17), and satisfaction at 9.3/100 (± 0.15). The positive changes in these scores were greater for patients who remained in the program for over 3 months. Cost reduction was demonstrated in the last 90 days of life, with statistically significant and chronologically progressive savings during the last 30 days of life exceeding 5 million pesos per patient (P < .05).

CONCLUSIONS

This study demonstrated the success of PC in reducing pain, improving wellbeing and QOL, providing comfort, and ensuring high levels of satisfaction. Moreover, PC is an effective value-based healthcare strategy and can significantly enhance the efficiency of healthcare services by reducing end-of-life healthcare costs.

The use of natural language processing in palliative care research: A scoping review

BACKGROUND

Natural language processing has been increasingly used in palliative care research over the last 5 years for its versatility and accuracy.

AIM

To evaluate and characterize natural language processing use in palliative care research, including the most commonly used natural language processing software and computational methods, data sources, trends in natural language processing use over time, and palliative care topics addressed.

DESIGN

A scoping review using the framework by Arksey and O'Malley and the updated recommendations proposed by Levac et al. was conducted.

SOURCES

PubMed, Web of Science, Embase, Scopus, and IEEE Xplore databases were searched for palliative care studies that utilized natural language processing tools. Data on study characteristics and natural language processing instruments used were collected and relevant palliative care topics were identified.

RESULTS

197 relevant references were identified. Of these, 82 were included after full-text review. Studies were published in 48 different journals from 2007 to 2022. The average sample size was 21,541 (median 435). Thirty-two different natural language processing software and 33 machine-learning methods were identified. Nine main sources for data processing and 15 main palliative care topics across the included studies were identified. The most frequent topic was mortality and prognosis prediction. We also identified a trend where natural language processing was frequently used in analyzing clinical serious illness conversations extracted from audio recordings.

CONCLUSIONS

We found 82 papers on palliative care using natural language processing methods for a wide-range of topics and sources of data that could expand the use of this methodology. We encourage researchers to consider incorporating this cutting-edge research methodology in future studies to improve published palliative care data.

Natural language processing and network analysis in patients withdrawing from life-sustaining treatments: a retrospective cohort study

BACKGROUND

Providing palliative care to patients who withdraw from life-sustaining treatments is crucial; however, delays or the absence of such services are prevalent. This study used natural language processing and network analysis to identify the role of medications as early palliative care referral triggers.

METHODS

We conducted a retrospective observational study of 119 adult patients receiving specialized palliative care after endotracheal tube withdrawal in intensive care units of a Taiwan-based medical center between July 2016 and June 2018. Patients were categorized into early integration and late referral groups based on the median survival time. Using natural language processing, we analyzed free texts from electronic health records. The Palliative trigger index was also calculated for comparison, and network analysis was performed to determine the co-occurrence of terms between the two groups.

RESULTS

Broad-spectrum antibiotics, antifungal agents, diuretics, and opioids had high Palliative trigger index. The most common co-occurrences in the early integration group were micafungin and voriconazole (co-correlation = 0.75). However, in the late referral group, piperacillin and penicillin were the most common co-occurrences (co-correlation = 0.843).

CONCLUSION

Treatments for severe infections, chronic illnesses, and analgesics are possible triggers for specialized palliative care consultations. The Palliative trigger index and network analysis indicated the need for palliative care in patients withdrawing from life-sustaining treatments. This study recommends establishing a therapeutic control system based on computerized order entry and integrating it into a shared-decision model.

Contribution of Synthetic Data Generation towards an Improved Patient Stratification in Palliative Care

AI model development for synthetic data generation to improve Machine Learning (ML) methodologies is an integral part of research in Computer Science and is currently being transferred to related medical fields, such as Systems Medicine and Medical Informatics. In general, the idea of personalized decision-making support based on patient data has driven the motivation of researchers in the medical domain for more than a decade, but the overall sparsity and scarcity of data are still major limitations. This is in contrast to currently applied technology that allows us to generate and analyze patient data in diverse forms, such as tabular data on health records, medical images, genomics data, or even audio and video. One solution arising to overcome these data limitations in relation to medical records is the synthetic generation of tabular data based on real world data. Consequently, ML-assisted decision-support can be interpreted more conveniently, using more relevant patient data at hand. At a methodological level, several state-of-the-art ML algorithms generate and derive decisions from such data. However, there remain key issues that hinder a broad practical implementation in real-life clinical settings. In this review, we will give for the first time insights towards current perspectives and potential impacts of using synthetic data generation in palliative care screening because it is a challenging prime example of highly individualized, sparsely available patient information. Taken together, the reader will obtain initial starting points and suitable solutions relevant for generating and using synthetic data for ML-based screenings in palliative care and beyond.

Strengthening Community End-of-Life Care through Implementing Measurement-Based Palliative Care

The increasing demand for palliative care in New Zealand presents a potential threat to the quality of service delivery. One strategy to overcome this is through the implementation of valid and reliable patient-reported outcome measures. This mixed-methods study aimed to (1) implement measurement-based palliative care (MBPC) in a community palliative care service in Auckland, New Zealand; (2) evaluate the clinical utility of MBPC perceived by clinicians; (3) describe patient characteristics as measured by the Integrated Palliative Care Outcome Scale (IPOS), the Australasian Modified Karnofsky Performance Scale (AKPS), and Phase of Illness (POI); and (4) evaluate the internal consistency of the IPOS. Participants were over 18 years of age from a community outpatient palliative care service. In a phased approach to implementation, healthcare staff were educated on each instrument used for patient assessment. Uptake and internal consistency were evaluated through descriptive statistics. An interpretive descriptive methodology was used to explore the clinical utility of MBPC through semi-structured interviews with seven clinical staff members. Individual patient assessments (n = 1507) were undertaken predominantly on admission, with decreasing frequency as patients advanced through to the terminal phase of their care. Mean total IPOS scores were 17.97 (SD = 10.39, α = 0.78). The POI showed that 65% of patients were in the stable phase, 20% were in the unstable phase, 9% were in the deteriorating phase, and 2% were in the terminal phase. Clinicians reported that MBPC facilitated holistic and comprehensive assessments, as well as the development of a common interdisciplinary language. Clinicians expressed discomfort using the psychosocial and spiritual items. Measurement-based palliative care was only partially implemented but it was valued by staff and perceived to increase the quality of service delivery. Future research should determine the optimal timing of assessments, cultural responsivity for Māori and Pacific patients, and the role of MBPC in decision support for clinicians.