Trust in cervical screening and attributions of blame for interval cancers following a national controversy.

OBJECTIVES: This study investigated levels of trust and attributions of blame in connection with a cervical screening programme following a controversy related to the programme's audit, incorporating an experimental test of the effectiveness of new information materials. DESIGN: We compared responses in Ireland (N = 872) to equivalent responses in Scotland (N = 400). Participants in Ireland were randomly assigned to either a treatment group that received the information materials or a control group that did not. Participants then responded to questions about their trust in cervical screening and to whom they would attribute blame in a range of scenarios describing women diagnosed with cervical cancer between screening rounds. RESULTS: Results showed that the control group in Ireland had lower trust and attributed higher blame towards screening services than participants in Scotland. However, exposure to information materials in the treatment group improved trust and reduced blame. CONCLUSIONS: The findings suggest that public controversies influence perceptions of screening programmes and underscore the importance of transparent, choice-based communication in mitigating these effects. The findings have valuable implications for screening services worldwide as all screening programmes will have associated false negative and false positive results.

COMfort Eye Trial (COMET) results - a non-inferiority, randomized, investigator-masked, two-parallel group, phase III clinical trial, to evaluate the efficacy and safety of a preservative free formulation of latanoprost versus a reference drug (Xalatan®) in patients with primary open-angle glaucoma (POAG) or ocular hypertension (OHT).

AIM: To prove non-inferiority of preservative-free (PF) latanoprost versus benzalkonium chloride (BAK) containing latanoprost in lowering intraocular pressure (IOP) in primary open-angle glaucoma (POAG) or ocular hypertension (OHT) patients. DESIGN AND METHODS: This phase III, randomized, investigator-masked trial primarily aimed to demonstrate non-inferiority of YSLT PF latanoprost 50 µg/ml (Yonsung GmbH) to latanoprost (Xalatan®) 50 µg/ml (Pfizer) in reducing IOP from Baseline to Week 12. Secondary aims included conjunctival hyperemia evaluation and difference in ocular comfort levels. Total 130 patients with POAG or OHT were enrolled and randomized (1:1 ratio) to receive YSLT or latanoprost, instilling eye drops daily for 12 weeks. RESULTS: At Week 12, mean diurnal IOP reduction was -7.67 ± 2.104 mmHg for YSLT PF latanoprost and -7.77 ± 2.500 for latanoprost. The 97.5% confidence interval of between-treatment group difference in IOP reduction from Baseline to Week 12 was [-0.846, +∞), not crossing the non-inferiority margin of -1.5 mmHg. A low incidence of mild topical treatment emergent adverse events (TEAEs) was observed in both groups, while no serious TEAEs were reported. CONCLUSIONS: YSLT eye drops demonstrated non-inferiority to latanoprost in reducing IOP. Both products were well tolerated without serious TEAEs reported.

Leveraging Unlabelled Data in Multiple-Instance Learning Problems for Improved Detection of Parkinsonian Tremor in Free-Living Conditions.

Data-driven approaches for remote detection of Parkinson's Disease and its motor symptoms have proliferated in recent years, owing to the potential clinical benefits of early diagnosis. The holy grail of such approaches is the free-living scenario, in which data are collected continuously and unobtrusively during every day life. However, obtaining fine-grained ground-truth and remaining unobtrusive is a contradiction and therefore, the problem is usually addressed via multiple-instance learning. Yet for large scale studies, obtaining even the necessary coarse ground-truth is not trivial, as a complete neurological evaluation is required. In contrast, large scale collection of data without any ground-truth is much easier. Nevertheless, utilizing unlabelled data in a multiple-instance setting is not straightforward, as the topic has received very little research attention. Here we try to fill this gap by introducing a new method for combining semi-supervised with multiple-instance learning. Our approach builds on the Virtual Adversarial Training principle, a state-of-the-art approach for regular semi-supervised learning, which we adapt and modify appropriately for the multiple-instance setting. We first establish the validity of the proposed approach through proof-of-concept experiments on synthetic problems generated from two well-known benchmark datasets. We then move on to the actual task of detecting PD tremor from hand acceleration signals collected in-the-wild, but in the presence of additional completely unlabelled data. We show that by leveraging the unlabelled data of 454 subjects we can achieve large performance gains (up to 9% increase in F1-score) in per-subject tremor detection for a cohort of 45 subjects with known tremor ground-truth. In doing so, we confirm the validity of our approach on a real-world problem where the need for semi-supervised and multiple-instance learning arises naturally.

An interpretable multiple-instance approach for the detection of referable diabetic retinopathy in fundus images.

Diabetic retinopathy (DR) is one of the leading causes of vision loss across the world. Yet despite its wide prevalence, the majority of affected people lack access to the specialized ophthalmologists and equipment required for monitoring their condition. This can lead to delays in the start of treatment, thereby lowering their chances for a successful outcome. Machine learning systems that automatically detect the disease in eye fundus images have been proposed as a means of facilitating access to retinopathy severity estimates for patients in remote regions or even for complementing the human expert's diagnosis. Here we propose a machine learning system for the detection of referable diabetic retinopathy in fundus images, which is based on the paradigm of multiple-instance learning. Our method extracts local information independently from multiple rectangular image patches and combines it efficiently through an attention mechanism that focuses on the abnormal regions of the eye (i.e. those that contain DR-induced lesions), thus resulting in a final image representation that is suitable for classification. Furthermore, by leveraging the attention mechanism our algorithm can seamlessly produce informative heatmaps that highlight the regions where the lesions are located. We evaluate our approach on the publicly available Kaggle, Messidor-2 and IDRiD retinal image datasets, in which it exhibits near state-of-the-art classification performance (AUC of 0.961 in Kaggle and 0.976 in Messidor-2), while also producing valid lesion heatmaps (AUPRC of 0.869 in the 81 images of IDRiD that contain pixel-level lesion annotations). Our results suggest that the proposed approach provides an efficient and interpretable solution against the problem of automated diabetic retinopathy grading.

Unobtrusive detection of Parkinson's disease from multi-modal and in-the-wild sensor data using deep learning techniques.

Parkinson's Disease (PD) is the second most common neurodegenerative disorder, affecting more than 1% of the population above 60 years old with both motor and non-motor symptoms of escalating severity as it progresses. Since it cannot be cured, treatment options focus on the improvement of PD symptoms. In fact, evidence suggests that early PD intervention has the potential to slow down symptom progression and improve the general quality of life in the long term. However, the initial motor symptoms are usually very subtle and, as a result, patients seek medical assistance only when their condition has substantially deteriorated; thus, missing the opportunity for an improved clinical outcome. This situation highlights the need for accessible tools that can screen for early motor PD symptoms and alert individuals to act accordingly. Here we show that PD and its motor symptoms can unobtrusively be detected from the combination of accelerometer and touchscreen typing data that are passively captured during natural user-smartphone interaction. To this end, we introduce a deep learning framework that analyses such data to simultaneously predict tremor, fine-motor impairment and PD. In a validation dataset from 22 clinically-assessed subjects (8 Healthy Controls (HC)/14 PD patients with a total data contribution of 18.305 accelerometer and 2.922 typing sessions), the proposed approach achieved 0.86/0.93 sensitivity/specificity for the binary classification task of HC versus PD. Additional validation on data from 157 subjects (131 HC/26 PD with a total contribution of 76.528 accelerometer and 18.069 typing sessions) with self-reported health status (HC or PD), resulted in area under curve of 0.87, with sensitivity/specificity of 0.92/0.69 and 0.60/0.92 at the operating points of highest sensitivity or specificity, respectively. Our findings suggest that the proposed method can be used as a stepping stone towards the development of an accessible PD screening tool that will passively monitor the subject-smartphone interaction for signs of PD and which could be used to reduce the critical gap between disease onset and start of treatment.

Assistive HCI-Serious Games Co-design Insights: The Case Study of i-PROGNOSIS Personalized Game Suite for Parkinson's Disease.

Human-Computer Interaction (HCI) and games set a new domain in understanding people's motivations in gaming, behavioral implications of game play, game adaptation to player preferences and needs for increased engaging experiences in the context of HCI serious games (HCI-SGs). When the latter relate with people's health status, they can become a part of their daily life as assistive health status monitoring/enhancement systems. Co-designing HCI-SGs can be seen as a combination of art and science that involves a meticulous collaborative process. The design elements in assistive HCI-SGs for Parkinson's Disease (PD) patients, in particular, are explored in the present work. Within this context, the Game-Based Learning (GBL) design framework is adopted here and its main game-design parameters are explored for the Exergames, Dietarygames, Emotional games, Handwriting games, and Voice games design, drawn from the PD-related i-PROGNOSIS Personalized Game Suite (PGS) (www.i-prognosis.eu) holistic approach. Two main data sources were involved in the study. In particular, the first one includes qualitative data from semi-structured interviews, involving 10 PD patients and four clinicians in the co-creation process of the game design, whereas the second one relates with data from an online questionnaire addressed by 104 participants spanning the whole related spectrum, i.e., PD patients, physicians, software/game developers. Linear regression analysis was employed to identify an adapted GBL framework with the most significant game-design parameters, which efficiently predict the transferability of the PGS beneficial effect to real-life, addressing functional PD symptoms. The findings of this work can assist HCI-SG designers for designing PD-related HCI-SGs, as the most significant game-design factors were identified, in terms of adding value to the role of HCI-SGs in increasing PD patients' quality of life, optimizing the interaction with personalized HCI-SGs and, hence, fostering a collaborative human-computer symbiosis.

Detecting Parkinsonian Tremor From IMU Data Collected in-the-Wild Using Deep Multiple-Instance Learning.

Parkinson's Disease (PD) is a slowly evolving neurological disease that affects about [Formula: see text] of the population above 60 years old, causing symptoms that are subtle at first, but whose intensity increases as the disease progresses. Automated detection of these symptoms could offer clues as to the early onset of the disease, thus improving the expected clinical outcomes of the patients via appropriately targeted interventions. This potential has led many researchers to develop methods that use widely available sensors to measure and quantify the presence of PD symptoms such as tremor, rigidity and braykinesia. However, most of these approaches operate under controlled settings, such as in lab or at home, thus limiting their applicability under free-living conditions. In this work, we present a method for automatically identifying tremorous episodes related to PD, based on IMU signals captured via a smartphone device. We propose a Multiple-Instance Learning approach, wherein a subject is represented as an unordered bag of accelerometer signal segments and a single, expert-provided, tremor annotation. Our method combines deep feature learning with a learnable pooling stage that is able to identify key instances within the subject bag, while still being trainable end-to-end. We validate our algorithm on a newly introduced dataset of 45 subjects, containing accelerometer signals collected entirely in-the-wild. The good classification performance obtained in the conducted experiments suggests that the proposed method can efficiently navigate the noisy environment of in-the-wild recordings.

Multiple-Instance Learning for In-The-Wild Parkinsonian Tremor Detection.

Parkinson's Disease (PD) is a neurodegenerative disorder that manifests through slowly progressing symptoms, such as tremor, voice degradation and bradykinesia. Automated detection of such symptoms has recently received much attention by the research community, owing to the clinical benefits associated with the early diagnosis of the disease. Unfortunately, most of the approaches proposed so far, operate under a strictly laboratory setting, thus limiting their potential applicability in real world conditions. In this work, we present a method for automatically detecting tremorous episodes related to PD, based on acceleration signals. We propose to address the problem at hand, as a case of Multiple-Instance Learning, wherein a subject is represented as an unordered bag of signal segments and a single, expert-provided, ground-truth. We employ a deep learning approach that combines feature learning and a learnable pooling stage and is trainable end-to-end. Results on a newly introduced dataset of accelerometer signals collected in-the-wild confirm the validity of the proposed approach.

Personalised meal eating behaviour analysis via semi-supervised learning.

Automated monitoring and analysis of eating behaviour patterns, i.e., "how one eats", has recently received much attention by the research community, owing to the association of eating patterns with health-related problems and especially obesity and its comorbidities. In this work, we introduce an improved method for meal micro-structure analysis. Stepping on a previous methodology of ours that combines feature extraction, SVM micro-movement classification and LSTM sequence modelling, we propose a method to adapt a pretrained IMU-based food intake cycle detection model to a new subject, with the purpose of improving model performance for that subject. We split model training into two stages. First, the model is trained using standard supervised learning techniques. Then, an adaptation step is performed, where the model is fine-tuned on unlabeled samples of the target subject via semisupervised learning. Evaluation is performed on a publicly available dataset that was originally created and used in [1] and has been extended here to demonstrate the effect of the semisupervised approach, where the proposed method improves over the baseline method.

Current management of presbyopia.

Presbyopia is a physiologic inevitability that causes gradual loss of accommodation during the fifth decade of life. The correction of presbyopia and the restoration of accommodation are considered the final frontier of refractive surgery. Different approaches on the cornea, the crystalline lens and the sclera are being pursued to achieve surgical correction of this disability. There are however, a number of limitations and considerations that have prevented widespread acceptance of surgical correction for presbyopia. The quality of vision, optical and visual distortions, regression of effect, complications such as corneal ectasia and haze, anisometropia after monovision correction, impaired distance vision and the invasive nature of the currently techniques have limited the utilization of presbyopia surgery. The purpose of this paper is to provide an update of current procedures available for presbyopia correction and their limitations.

Serum uric acid as a predictor of mortality and future exacerbations of COPD.

Serum uric acid is increased in respiratory disease, especially in the presence of hypoxia and systemic inflammation. We evaluated serum uric acid as a biomarker for prediction of mortality and future acute exacerbation of chronic obstructive pulmonary disease (AECOPD). Serum uric acid was measured in 314 eligible consecutive patients on admission for AECOPD. Patients were evaluated monthly for 1 year. Uric acid levels were higher in patients with more severe airflow limitation and in those experiencing frequent exacerbations. High uric acid levels (≥6.9 mg·dL(-1)) were an independent predictor of 30-day mortality in multivariate Cox regression analysis (HR 1.317, 95% CI 1.011-1.736; p=0.044), but not of 1-year mortality. Patients with high serum uric acid required more prolonged hospitalisation, and more often needed noninvasive ventilation and admission to the intensive care unit within 30 days. In addition, high uric acid levels were associated with increased risk and hospitalisation for AECOPD in 1 year in multivariate Poisson regression analysis (incidence rate ratio 1.184 (95% CI 1.125-1.246) and 1.190 (95% CI 1.105-1.282), respectively; both p<0.001). Serum uric acid is associated with increased 30-day mortality and risk for AECOPD and hospitalisations in 1-year follow-up. This low-cost biomarker may be useful in the identification of high-risk chronic obstructive pulmonary disease patients that could benefit from intensive management.

Adequacy of semitendinosus tendon alone for anterior cruciate ligament reconstruction graft and prediction of hamstring graft size by evaluating simple anthropometric parameters.

INTRODUCTION: Preoperative identification of patients with inadequate hamstring grafts for anterior cruciate ligament reconstruction is still a subject of interest. PURPOSE: The purpose of this study was to determine whether the semitendinosus tendon length is adequate for four-strand graft harvested by common technique (without bone plug) and whether there is correlation of gracilis and semitendinosus tendon grafts length and diameter of quadrupled graft with anthropometric parameters. MATERIALS AND METHODS: In this retrospective study, 61 patients (45 males, 16 females) undergoing ACL reconstruction using four-strand hamstring autograft tendons were included. Results. The length of semitendinosus tendon, harvested by the common technique, was in 21% of our cases inadequate in order to be used alone as a four-strand graft especially in females (43%). There was moderate correlation between semitendinosus and gracilis graft diameter and patient's height and weight and fair correlation to BMI. We found no statistically important predictor for graft diameter in female patients. CONCLUSIONS: The length of semitendinosus tendon, harvested by common technique, is usually inadequate to be used alone as a four-strand graft especially in females. The most reliable predictor seems to be patient's height in males. In female patients, there is no statistically important predictor.

First 500 cases of robotic-assisted laparoscopic radical prostatectomy from a single UK centre: learning curves of two surgeons.

OBJECTIVE: • To study the outcomes and learning curve of robotic-assisted laparoscopic radical prostatectomy (RALP) in a single centre by two surgeons. PATIENTS AND METHODS: • In total, 500 consecutive patients underwent RALP between 2005 and 2009 carried out by two surgeons. Using an ethically-approved database, prospective data collection of demographic, surgical, oncological and functional outcomes (patient reported) was performed, with up to 4 years of follow-up. • The learning curves of both surgeons were analyzed and, in addition, the first 100 and last 100 patients were compared to determine the effect of surgeon experience. RESULTS: • The mean age of the patients was 61.5 years and mean preoperative prostate-specific antigen was 7.0 µg/L. Clinical stages were T1 in 63.2%, T2 in 33.8% and T3 in 3.0% of patients. Median (range) operating time was 170 (63-420) min and median (range) blood loss was 200 (20-3000) mL, with significant improvements for both surgeons with increasing experience (P < 0.001 and P= 0.029, respectively). • Pathological stages were pT2 in 53.4%, pT3a in 41.6%, pT3b in 4.0% and pT4 in 0.6% of patients. Overall, the positive margin rate (PMR) was 24.0% and stage-specific rates were 16.1%, 30.4%, 55.0% and 100.0% for pT2, pT3a, pT3b and pT4 disease, respectively. In the last 50 cases performed by each surgeon, the PMRs for pT2 and pT3a disease were 8.0% and 19.1% (surgeon 1) and 12.9% and 23.5% (surgeon 2). • At 12 months of follow-up, 91.3% of patients were continent and, by 48 months of follow-up, 75% of men with preoperative potency who underwent bilateral nerve-sparing RALP were potent. CONCLUSION: • This is the first report of two surgeons' learning curves in a single centre and shows that key learning curve outcomes continued to improve during the series, suggesting that the learning curve for RALP may be longer than has been previously suggested.