Propagating variational model uncertainty for bioacoustic call label smoothing

Along with propagating the input toward making a prediction, Bayesian neural networks also propagate uncertainty. This has the potential to guide the training process by rejecting predictions of low confidence, and recent variational Bayesian methods can do so without Monte Carlo sampling of weights. Here, we apply sample-free methods for wildlife call detection on recordings made via passive acoustic monitoring equipment in the animals' natural habitats. We further propose uncertainty-aware label smoothing, where the smoothing probability is dependent on sample-free predictive uncertainty, in order to downweigh data samples that should contribute less to the loss value. We introduce a bioacoustic dataset recorded in Malaysian Borneo, containing overlapping calls from 30 species. On that dataset, our proposed method achieves an absolute percentage improvement of around 1.5 points on area under the receiver operating characteristic (AU-ROC), 13 points in F1, and 19.5 points in expected calibration error (ECE) compared to the point-estimate network baseline averaged across all target classes.

Assessing the Feasibility of a Text-Based Conversational Agent for Asthma Support: Protocol for a Mixed Methods Observational Study

BACKGROUND

Despite efforts, the UK death rate from asthma is the highest in Europe, and 65% of people with asthma in the United Kingdom do not receive the professional care they are entitled to. Experts have recommended the use of digital innovations to help address the issues of poor outcomes and lack of care access. An automated SMS text messaging-based conversational agent (ie, chatbot) created to provide access to asthma support in a familiar format via a mobile phone has the potential to help people with asthma across demographics and at scale. Such a chatbot could help improve the accuracy of self-assessed risk, improve asthma self-management, increase access to professional care, and ultimately reduce asthma attacks and emergencies.

OBJECTIVE

The aims of this study are to determine the feasibility and usability of a text-based conversational agent that processes a patient's text responses and short sample voice recordings to calculate an estimate of their risk for an asthma exacerbation and then offers follow-up information for lowering risk and improving asthma control; assess the levels of engagement for different groups of users, particularly those who do not access professional services and those with poor asthma control; and assess the extent to which users of the chatbot perceive it as helpful for improving their understanding and self-management of their condition.

METHODS

We will recruit 300 adults through four channels for broad reach: Facebook, YouGov, Asthma + Lung UK social media, and the website Healthily (a health self-management app). Participants will be screened, and those who meet inclusion criteria (adults diagnosed with asthma and who use WhatsApp) will be provided with a link to access the conversational agent through WhatsApp on their mobile phones. Participants will be sent scheduled and randomly timed messages to invite them to engage in dialogue about their asthma risk during the period of study. After a data collection period (28 days), participants will respond to questionnaire items related to the quality of the interaction. A pre- and postquestionnaire will measure asthma control before and after the intervention.

RESULTS

This study was funded in March 2021 and started in January 2022. We developed a prototype conversational agent, which was iteratively improved with feedback from people with asthma, asthma nurses, and specialist doctors. Fortnightly reviews of iterations by the clinical team began in September 2022 and are ongoing. This feasibility study will start recruitment in January 2023. The anticipated completion of the study is July 2023. A future randomized controlled trial will depend on the outcomes of this study and funding.

CONCLUSIONS

This feasibility study will inform a follow-up pilot and larger randomized controlled trial to assess the impact of a conversational agent on asthma outcomes, self-management, behavior change, and access to care.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

PRR1-10.2196/42965.

Average Jane, Where Art Thou? – Recent Avenues in Efficient Machine Learning Under Subjectivity Uncertainty

In machine learning tasks an actual ‘ground truth’ may not be available. Then, machines often have to rely on human labelling of data. This becomes challenging the more subjective the learning task is, as human agreement can be low. To cope with the resulting high uncertainty, one could train individual models reflecting a single human’s opinion. However, this is not viable, if one aims at mirroring the general opinion of a hypothetical ‘completely average person’ – the ‘average Jane’. Here, I summarise approaches to optimally learn efficiently in such a case. First, different strategies of reaching a single learning target from several labellers will be discussed. This includes varying labeller trustability and the case of time-continuous labels with potential dynamics. As human labelling is a labour-intensive endeavour, active and cooperative learning strategies can help reduce the number of labels needed. Next, sample informativeness can be exploited in teacher-based algorithms to additionally weigh data by certainty. In addition, multi-target learning of different labeller tracks in parallel and/or of the uncertainty can help improve the model robustness and provide an additional uncertainty measure. Cross-modal strategies to reduce uncertainty offer another view. From these and further recent strategies, I distil a number of future avenues to handle subjective uncertainty in machine learning. These comprise bigger, yet weakly labelled data processing basing amongst other on reinforcement learning, lifelong learning, and self-learning. Illustrative examples stem from the fields of Affective Computing and Digital Health – both notoriously marked by subjectivity uncertainty.

Screening of colorectal cancer (CRC) patients for lynch syndrome (LS) emphasizes the need for public insurance coverage of genetic testing: Results of a national program by the Hellenic Society of Medical Oncology (HeSMO)

e13141

Background: Lynch Syndrome is associated with germline mutations in Mismatch Repair (MMR) genes ( MLH1, MSH2, MSH6, PMS2). CRC patients whose tumors exhibit high-level microsatellite instability (MSI-H) have an increased probability of LS. Although the diagnosis of LS has important implications for the patient and the family, germline genetic testing is not reimbursed by the Hellenic Public State Healthcare Services. To address this need HeSMO conducted a national program to screen and diagnose CRC patients with LS. Methods: All patients with CRC were eligible. Assessment for LS involved initially screening tumor tissue for the presence of MMR deficiency, either via molecular MSI testing or via immunohistochemistry (IHC) to detect the absence of one or more MMR proteins. Patients with an MMR-deficient tumor in the absence of a somatic cause (e.g. BRAF mutation or MLH1 promoter hypermethylation) underwent genetic counseling and germline testing to confirm a LS diagnosis. Results: From June 2017 to December 2018, 104 patients diagnosed with CRC were enrolled and tested. Median age of diagnosis was 58,5 years (range 32 - 89) and male-to-female ratio was 1.6:1. Fifty patients (48%) had tumors that exhibited the MSI-H phenotype. From the MSI-H tumors, 41 (82%) did not harbor the BRAF V600E mutation and 33 of them (80.5%) did not harbor an MLH1 promoter hypermethylation. Therefore, 33 patients were invited for genetic counseling and testing. Fifteen patients (45.45%) were diagnosed with LS: 6 ( 40 %) had a mutation in MLH1 (one of which had also a mutation in PMS2 gene), 4 (26.6%) in MSH6, 4 (26.6%) in MSH2 and 1 (6.6%) in PMS2. Conclusions: In our series, 30% of the CRC patients with MSI-H tumors were tested positive for LS. These results confirm the value of a universal screening program of CRC patients for LS. Hopefully, these results will convince the Hellenic Public State Healthcare Services to reimburse screening and germline genetic testing of CRC patients for LS.

Multilabel user classification using the community structure of online networks

We study the problem of semi-supervised, multi-label user classification of networked data in the online social platform setting. We propose a framework that combines unsupervised community extraction and supervised, community-based feature weighting before training a classifier. We introduce Approximate Regularized Commute-Time Embedding (ARCTE), an algorithm that projects the users of a social graph onto a latent space, but instead of packing the global structure into a matrix of predefined rank, as many spectral and neural representation learning methods do, it extracts local communities for all users in the graph in order to learn a sparse embedding. To this end, we employ an improvement of personalized PageRank algorithms for searching locally in each user's graph structure. Then, we perform supervised community feature weighting in order to boost the importance of highly predictive communities. We assess our method performance on the problem of user classification by performing an extensive comparative study among various recent methods based on graph embeddings. The comparison shows that ARCTE significantly outperforms the competition in almost all cases, achieving up to 35% relative improvement compared to the second best competing method in terms of F1-score.

Hemosiderosis causing liver cirrhosis in a patient with Hb S/beta thalassemia and no other known causes of hepatic disease

BACKGROUND

Hemosiderosis in the absence of blood transfusions has been encountered in conditions associated with ineffective erythropoiesis but not in sickle-cell disease (SCD). Description of the case: We report a case of a 34-year-old Caucasian male, with a history of SCD and beta thalassemia (Hb S/β⁺-thal) who presented with acute painful crises. Despite never having received regular blood transfusions in the past, the patient demonstrated elevated ferritin levels and transferrin saturation of 83 %. Further evaluation revealed diffuse hepatocellular dysfunction and cirrhosis.

CONCLUSION

To the best of our knowledge, this is the first patient with Hb S/β⁺-thal without a prior history of chronic blood transfusions or other predisposing factors for liver disease who developed hemosiderosis and cirrhosis. The pathomechanism, in this case, is thought to be related to increased duodenal iron uptake secondary to premature red cell precursor death. Further studies are required to characterize ineffective intramedullary erythropoiesis and iron metabolism better, and to improve the existing management guidelines of iron overload. The data reported herein suggest that patients with hemoglobinotpathies should be screened for iron overload regardless of transfusion history. HIPPOKRATIA 2017, 21(1): 43-45.

HIV infection in Greek intravenous drug users

In order to investigate the prevalence of HIV infection among Greek intravenous drug users (IVDU), its trend during years recent and possible risk factors, we studied 893 inmates recently admitted to the main prisons of Greece from 1986 to 1989. Screening and counselling was offered to all of them. The acceptance rate was 98%. One thousand one hundred and two IVDUs voluntarily attending the AIDS Reference Centre in Athens for counselling and screening were also included in the study. Anti-HIV were determined by commercially available radioimmunoassays, and positive results were confirmed by Western Blot. Our results showed that the prevalence of HIV infection remained very low in both groups during the study period; it was similar to the prevalence found (2.1%) in stored sera drawn in 1982 from imprisoned IVDU. In the non-prisoner group, the prevalence among those who reported needle/syringe sharing (2.6%) was similar to that among those who denied sharing (2.5%). This lack of difference may be due to the fact that sharing is only an occasional practice and that cleaning of of the injection equipment is common. We conclude that the prevalence of anti-HIV in IVDU in Greece is considerably lower than that in neighbouring countries and that it has remained stable during the last eight years. Further studies are necessary to identify behavioral and other risk factors.