The aim of the study was to evaluate the healthcare costs and effects of a remote person-centred care (PCC) add-on intervention compared with usual care for people with chronic heart failure (CHF) and/or chronic obstructive pulmonary Disease (COPD) from a societal perspective.

A cost-effectiveness analysis (CEA) based on the results from a randomised controlled trial.

The study was conducted from August 2017 until June 2021 within nine primary care centres across Western Sweden.

Participants in the study had a diagnosis of COPD (J43.0, J44.0–J44.9) and/or CHF (I50.0–I50.9).

224 patients were randomly allocated to the study groups. After two withdrawals, the final intention-to-treat analysis included 110 participants in the intervention group and 112 in the control group.

Both the intervention and control group received usual care through their primary care centres. In addition, the intervention group participated in a remote PCC add-on intervention consisting of a digital platform and structured telephone support.

Incremental cost-effectiveness ratio using direct healthcare costs, productivity loss and prescription drug costs, compared with health effects measured using the EuroQoL questionnaire (EQ-5D-3L) over a 2-year time horizon.

The intervention group had lower healthcare utilisation in inpatient care, specialised outpatient care and reduced productivity loss. The CEA showed incremental effects of 0.0469 quality-adjusted life years and incremental costs of SEK –68 533 (Swedish crowns). The PCC alternative was both more effective and resulted in lower healthcare costs compared with usual care, that is, PCC was dominant.

The results of this CEA demonstrated that a remote PCC add-on intervention for people with COPD and/or CHF had lower healthcare costs and higher health-related quality of life compared with usual care.

NCT03183817 ClinicalTrials.gov.

To describe the usage patterns of patients and healthcare professionals (HCPs) using a person-centred telehealth and e-health intervention.

An exploratory, descriptive, observational study embedded in the "Person-centred care at a distance (PROTECT)" randomised controlled trial (ClinicalTrials.gov: NCT03183817) as part of a process evaluation. Data on intervention use and time spent on the intervention were collected. Descriptive statistics were calculated.

Participants were recruited from nine public primary healthcare facilities located in various areas of Gothenburg, Sweden.

110 patients participating in the intervention group in the PROTECT trial were included. Participants were diagnosed with chronic heart failure (CHF, n=42), chronic obstructive pulmonary disease (COPD, n=56) or both (n=12). They were 33–93 years old (mean 71 years).

A secondary outcome report on resource use.

The 6-month-long intervention was performed as an add-on to standard care and comprised person-centred telephone support and access to a digital platform. Per-protocol use included co-creation of a health plan via the telephone and use of the digital platform at least once. Forms of use were tailored to the preferences and needs of the patients.

Most intervention activities took place in the first 3 months of the intervention. Most patients used a combination of phone and digital support, spending most of their time using the digital platform. Overall, patients and HCPs spent 6 and 2.5 hours/patient using the intervention, respectively. Of this time, 1.5 hours involved synchronous communication through phone calls, with health-plan calls averaging 77 min.

The intervention usage patterns of patients and HCPs differed. Despite HCPs being accessible when required, patients dedicated most of their time to self-care practices. Based on time distribution data, 15 full-time HCPs could potentially co-create, document and follow-up on health plans for 10 000 patients under study conditions.

ClinicalTrials.gov: NCT03183817.

To compare the quality and time efficiency of physician-written summaries with customised large language model (LLM)-generated medical summaries integrated into the electronic health record (EHR) in a non-English clinical environment.

Cross-sectional non-inferiority validation study.

Tertiary academic hospital.

52 physicians from 8 specialties at a large Dutch academic hospital participated, either in writing summaries (n=42) or evaluating them (n=10).

Physician writers wrote summaries of 50 patient records. LLM-generated summaries were created for the same records using an EHR-integrated LLM. An independent, blinded panel of physician evaluators compared physician-written summaries to LLM-generated summaries.

Primary outcome measures were completeness, correctness and conciseness (on a 5-point Likert scale). Secondary outcomes were preference and trust, and time to generate either the physician-written or LLM-generated summary.

The completeness and correctness of LLM-generated summaries did not differ significantly from physician-written summaries. However, LLM summaries were less concise (3.0 vs 3.5, p=0.001). Overall evaluation scores were similar (3.4 vs 3.3, p=0.373), with 57% of evaluators preferring LLM-generated summaries. Trust in both summary types was comparable, and interobserver variability showed excellent reliability (intraclass correlation coefficient 0.975). Physicians took an average of 7 min per summary, while LLMs completed the same task in just 15.7 s.

LLM-generated summaries are comparable to physician-written summaries in completeness and correctness, although slightly less concise. With a clear time-saving benefit, LLMs could help reduce clinicians’ administrative burden without compromising summary quality.