A novel patient-reported outcome instrument assessing the symptoms of paroxysmal nocturnal hemoglobinuria, the PNH-SQ

Patient-Oriented Questionnaires and Machine Learning for Rare Disease Diagnosis: A Systematic Review

Background: A major challenge faced by patients with rare diseases (RDs) often stems from delays in diagnosis, typically due to nonspecific clinical symptoms or doctors' limited experience in connecting symptoms to the underlying RD. Using patient-oriented questionnaires (POQs) as a data source for machine learning (ML) techniques can serve as a potential solution. These questionnaires enable patients to portray their day-to-day experiences living with their condition, irrespective of clinical symptoms. This systematic review-registered at PROSPERO with the Registration-ID: CRD42023490838-aims to present the current state of research in this domain by conducting a systematic literature search and identifying the potentials and limitations of this methodology. Methods: The review adheres to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines and was primarily funded by the German Federal Ministry of Education and Research under grant no. 16DHBKI056 (ki4all). The methodology involved a systematic search across the databases PubMed, Semantic Scholar and Google Scholar, covering articles published until June 2023. The inclusion criteria encompass examining the use of POQs in diagnosing rare and common diseases. Additionally, studies that focused on applying ML techniques to the resulting datasets were considered for inclusion. The primary objective was to include English as well as German research that involved the generation of predictions regarding the underlying disease based on the information gathered from POQs. Furthermore, studies exploring identifying predictive indicators associated with the underlying disease were also included in the literature review. The following data were extracted from the selected studies: year of publication, number of questions in the POQs, answer scale in the questionnaires, the ML algorithms used, the input data for the ML algorithms, the performance of these algorithms and how the performance was measured. In addition, information on the development of the questionnaires was recorded. Results: This search retrieved 421 results in total. After one superficial and two comprehensive screening runs performed by two authors independently, we ended up with 26 studies for further consideration. Sixteen of these studies deal with diseases and ML algorithms to analyse data; the other ten studies provide contributing research in this field. We discuss several potentials and limitations of the evaluated approach. Conclusions: Overall, the results show that the full potential has not yet been exploited and that further research in this direction is worthwhile, because the study results show that ML algorithms can achieve promising results on POQ data; however, their use in everyday medical practice has not yet been investigated.

Paroxysmal nocturnal hemoglobinuria: Review of the patient experience and treatment landscape

Paroxysmal nocturnal hemoglobinuria (PNH) is a rare disorder caused by complement-mediated hemolysis and thrombosis through the alternative pathway. The most common symptom of PNH is fatigue due to chronic anemia, which can negatively impact quality of life (QoL) and affect overall well-being. The currently approved therapies for PNH significantly limit intravascular hemolysis (IVH) and reduce the risk of thrombosis; however, they are associated with an infusion schedule that can become burdensome, and not all patients experience complete disease control. Several new complement inhibitors are in development that address the need for convenient routes of administration and aim to provide better disease control. With the variety of new treatment options on the horizon, hematologic markers as well as QoL concerns, patient opinion, and lifestyle factors should be considered to choose the optimal PNH treatment for each specific patient.

Predictors for improvement in patient-reported outcomes: post hoc analysis of a phase 3 randomized, open-label study of eculizumab and ravulizumab in complement inhibitor-naive patients with paroxysmal nocturnal hemoglobinuria

Paroxysmal nocturnal hemoglobinuria (PNH) is characterized by uncontrolled terminal complement activation leading to intravascular hemolysis (IVH), thrombosis, and impairments in quality of life (QoL). The aim of this study was to identify the clinical drivers of improvement in patient-reported outcomes (PROs) in patients with PNH receiving the complement component 5 (C5) inhibitors eculizumab and ravulizumab.This post hoc analysis assessed clinical outcomes and PROs from 246 complement inhibitor-naive patients with PNH enrolled in a phase 3 randomized non-inferiority study that compared the C5 inhibitors ravulizumab and eculizumab (study 301; NCT02946463). The variables of interest were lactate dehydrogenase (LDH) levels, a surrogate measure of IVH, and hemoglobin (Hb) levels. PROs were collected using Functional Assessment of Chronic Illness Therapy-Fatigue (FACIT-F) and European Organisation for Research and Treatment of Cancer, Quality of Life Questionnaire-Core 30 (EORTC QLQ-C30) to assess fatigue and QoL, respectively.Improvements in absolute mean LDH levels were significantly associated with improvements in mean FACIT-F score (p = 0.0024) and EORTC QLQ-C30 global health (GH) score (p < 0.0001) from baseline to day 183. Improvements in scores were achieved despite a non-significant increase in Hb levels. To understand the interaction between LDH and Hb, a regression analysis was performed: LDH response with Hb improvements was a significant predictor of improvement in fatigue. The independent effect of improved Hb did not significantly affect FACIT-F or EORTC QLQ-C30 GH scores.These findings suggest that LDH levels are an important determinant of fatigue and QoL outcomes in patients with PNH. CTR: NCT02946463, October 27, 2016.

Systematic Review of the Effect of a One-Day Versus Seven-Day Recall Duration on Patient Reported Outcome Measures (PROMs)

BACKGROUND

There is ongoing uncertainty around the most suitable recall period for patient-reported outcome measures (PROMs).

METHOD

This systematic review integrates quantitative and qualitative literature across health, economics, and psychology to explore the effect of a one-day (or '24-h') versus seven-day (or 'one week') recall period. The following databases were searched from database inception to 30 November 2021: MEDLINE, EMBASE, PsycINFO, Web of Science, EconLit, CINAHL Complete, Cochrane Library, and Sociological Abstracts. Studies were included that compared a one-day (or '24-h') versus seven-day (or weekly) recall period condition on patient-reported scores for PROM and Health-Related Quality-of-Life (HRQoL) instrument scores in adult populations (aged 18 and above) or combined paediatric and adult populations with a majority of respondents aged over 18 years. Studies were excluded if they assessed health behaviours only, used ecological momentary assessment to derive an index of daily recall, or incorporated clinician reports of patient symptoms. We extracted results relevant to six domains with generic health relevance: physical functioning, pain, cognition, psychosocial wellbeing, sleep-related symptoms and aggregated disease-specific signs and symptoms. Quantitative studies compared weekly recall scores with the mean or maximum score over the last seven days or with the same-day recall score.

RESULTS

Overall, across the 24 quantitative studies identified, 158 unique results were identified. Symptoms tended to be reported as more severe and HRQoL lower when assessed with a weekly recall than a one-day recall. A narrative synthesis of 33 qualitative studies integrated patient perspectives on the suitability of a one-day versus seven-day recall period for assessing health state or quality of life. Participants had mixed preferences, some noted the accuracy of recall for the one-day period but others preferred the seven-day recall for conditions characterised by high symptom variability, or where PROMs concepts required integration of infrequent experiences or functioning over time.

CONCLUSION

This review identified a clear trend toward higher symptom scores and worse quality of life being reported for a seven-day compared to a one-day recall. The review also identified anomalies in this pattern for some wellbeing items and a need for further research on positively framed items. A better understanding of the impact of using different recall periods within PROMs and HRQoL instruments will help contextualise future comparisons between instruments. Questionnaires ask patients about their health over different time periods (e.g., "what were your symptoms like over the last week?" versus "what were your symptoms like today?"). Studies find that people may report their symptoms as more severe when they are asked to think about their symptoms over the last week compared to the last day. Understanding how different time periods influence patient responses will allow researchers to compare and develop new questionnaires and may help clinicians to choose the best questionnaire to understand their patient's condition. We conducted a systematic literature review on studies which had looked at the impact of using different recall periods on patient responses. We found 24 studies that compared patient scores from questionnaires asking their health "over the last day" compared to "over the last week". Overall, symptoms tended to be reported as more severe and health as poorer when they were reported over the last week compared to the last day on average. We also found 33 studies that asked patients to describe which recall period they preferred. Patients had mixed preferences with more preferring a seven-day recall where symptoms and health impacts varied a lot.

Managing Fatigue in Patients with Paroxysmal Nocturnal Hemoglobinuria: A Patient-Focused Perspective

The most frequently reported symptom in patients with paroxysmal nocturnal hemoglobinuria (PNH), a disease characterized by complement mediated hemolysis and chronic anemia, is "fatigue". The latter seems the best word to communicate patient' perception of personal health status and disease impact on daily living, namely quality of life (QoL). Objectivating QoL and grading patient's fatigue is one of the most difficult medical tasks given the highly heterogeneous communication skills of patients and caregivers and the multitude of meanings that might be attributed to this term. Along with anemia, QoL in PNH is also affected by the emotional burden of a chronic life-long disease with heterogeneous treatment requirement, risk of hemolytic exacerbations (breakthrough hemolysis) and of thrombosis. In the last decade, structured surveys and scores have been adapted from cancer settings to evaluate fatigue and QoL in patients with PNH, and to assess the benefit of complement inhibitors in this setting. Eculizumab was the first drug utilized and was shown to improve QoL scores in the registrative trials. However, the intravenous fortnightly administration, the presence of residual anemia, and the risk of extravascular hemolysis are some of the unmet needs impacting QoL under eculizumab. Several novel drugs have been designed to improve patients' convenience and alleviate anemia and fatigue. In this review, we focus on available studies that evaluated fatigue and QoL in PNH patients, and the effect of old and new therapeutic strategies.