Longitudinal Healthcare Utilization and Costs in Parkinson's Disease: Pre-Diagnosis to 9 Years After

Detecting Parkinson's disease from shoe-mounted accelerometer sensors using convolutional neural networks optimized with modified metaheuristics

Neurodegenerative conditions significantly impact patient quality of life. Many conditions do not have a cure, but with appropriate and timely treatment the advance of the disease could be diminished. However, many patients only seek a diagnosis once the condition progresses to a point at which the quality of life is significantly impacted. Effective non-invasive and readily accessible methods for early diagnosis can considerably enhance the quality of life of patients affected by neurodegenerative conditions. This work explores the potential of convolutional neural networks (CNNs) for patient gain freezing associated with Parkinson's disease. Sensor data collected from wearable gyroscopes located at the sole of the patient's shoe record walking patterns. These patterns are further analyzed using convolutional networks to accurately detect abnormal walking patterns. The suggested method is assessed on a public real-world dataset collected from parents affected by Parkinson's as well as individuals from a control group. To improve the accuracy of the classification, an altered variant of the recent crayfish optimization algorithm is introduced and compared to contemporary optimization metaheuristics. Our findings reveal that the modified algorithm (MSCHO) significantly outperforms other methods in accuracy, demonstrated by low error rates and high Cohen's Kappa, precision, sensitivity, and F1-measures across three datasets. These results suggest the potential of CNNs, combined with advanced optimization techniques, for early, non-invasive diagnosis of neurodegenerative conditions, offering a path to improve patient quality of life.

Diagnostic windows in non-neoplastic diseases: a systematic review

BACKGROUND

Investigating changes in prediagnostic healthcare utilisation can help identify how much earlier conditions could be diagnosed. Such 'diagnostic windows' are established for cancer but remain relatively unexplored for non-neoplastic conditions.

AIM

To extract evidence on the presence and length of diagnostic windows for non-neoplastic conditions.

DESIGN AND SETTING

A systematic review of studies of prediagnostic healthcare utilisation was carried out.

METHOD

A search strategy was developed to identify relevant studies from PubMed and Connected Papers. Data were extracted on prediagnostic healthcare use, and evidence of diagnostic window presence and length was assessed.

RESULTS

Of 4340 studies screened, 27 were included, covering 17 non-neoplastic conditions, including both chronic (for example, Parkinson's disease) and acute conditions (for example, stroke). Prediagnostic healthcare events included primary care encounters and presentations with relevant symptoms. For 10 conditions, sufficient evidence to determine diagnostic window presence and length was available, ranging from 28 days (herpes simplex encephalitis) to 9 years (ulcerative colitis). For the remaining conditions, diagnostic windows were likely to be present, but insufficient study duration was often a barrier to robustly determining their length, meaning that diagnostic window length may exceed 10 years for coeliac disease, for example.

CONCLUSION

Evidence of changing healthcare use before diagnosis exists for many non-neoplastic conditions, establishing that early diagnosis is possible, in principle. In particular, some conditions may be detectable many years earlier than they are currently diagnosed. Further research is required to accurately estimate diagnostic windows and to determine how much earlier diagnosis may be possible, and how this might be achieved.

Objective measurement versus clinician-based assessment for Parkinson's disease

INTRODUCTION

Although clinician-based assessment through standardized clinical rating scales is currently the gold standard for quantifying motor impairment in Parkinson's disease (PD), it is not without limitations, including intra- and inter-rater variability and a degree of approximation. There is increasing evidence supporting the use of objective motion analyses to complement clinician-based assessment. Objective measurement tools hold significant potential for improving the accuracy of clinical and research-based evaluations of patients.

AREAS COVERED

The authors provide several examples from the literature demonstrating how different motion measurement tools, including optoelectronics, contactless and wearable systems allow for both the objective quantification and monitoring of key motor symptoms (such as bradykinesia, rigidity, tremor, and gait disturbances), and the identification of motor fluctuations in PD patients. Furthermore, they discuss how, from a clinician's perspective, objective measurements can help in various stages of PD management.

EXPERT OPINION

In our opinion, sufficient evidence supports the assertion that objective monitoring systems enable accurate evaluation of motor symptoms and complications in PD. A range of devices can be utilized not only to support diagnosis but also to monitor motor symptom during the disease progression and can become relevant in the therapeutic decision-making process.

Causes, factors, and complications associated with hospital admissions among patients with Parkinson's disease

Introduction

Patients with Parkinson's disease (PD) are at a higher risk of hospital admissions compared to the general population. We studied the causes and factors associated with admissions among patients with PD over 6 years.

Methods

We included all PD admissions between 1 January 2016 and 31 December 2021. Other causes of parkinsonism were excluded. Causes of admissions were divided into PD-related (direct or indirect) or non-PD-related. The type of admission was categorized into emergency or elective.

Results

We identified 605 hospital admissions (259 patients with PD); 345 (57.0%) were PD-related and 260 (43%) were non-PD-related. Emergency PD admissions contributed to 50.4% of all admissions, most commonly from respiratory infection (23%). PD admissions in comparison to non-PD admissions were associated with worse disease severity (HY ≥ 3; p < 0.001), longer disease duration [8.71 (SD 6.23) vs. 6.60 (SD 5.39) years; p < 0.001], and longer hospital stay [7.70 (SD 5.89) vs. 6.42 (SD 7.63) days; p = 0.020]. Non-PD admissions were associated with more comorbidities (97.3%; p = 0.013). There were 124 (20.5%) complications and 31 deaths (5.1%). A total of 29 deaths were due to respiratory infection and 3 deaths were due to COVID-19 pneumonia. Emergency admission (PD- and non-PD-related; p = 0.001) and respiratory-related causes (p < 0.001) were predictors of unfavorable hospital admission outcomes (death and complications).

Conclusion

Respiratory infection was the leading cause of hospital admission and a significant independent predictor of unfavorable hospital admission outcomes (death and complications). PD-related admissions were associated with disease severity and led to more complications and longer hospital stays. Non-PD-related admissions were associated with comorbidities.