No abstract

DevicesAccess at: www. CFRjournal.com Telehealth is a multiform term embracing the applications of telematics to medicine, in order to enable diagnosis and/or treatment remotely through a set of communication tools, including phones, smartphones and mobile wireless devices, with or without a video connection.1 Until a few years ago, digital applications in medicine were restricted to the use of data obtained from electronic health records (EHR), but, in more recent times, the technological context has notably expanded: the number of existing internet-connected mobile devices has roughly doubled every five years. This phenomenon will probably lead to the simultaneous operability of around 50 billion devices by 2020. 2 SensorsSensors are tools that are capable of detecting, recording and responding to specific inputs coming from a physical setting (e.g. a patient's vital signs) and are increasingly embedded in smartphones and other mobile devices. Recording and quantifying biological variables by means of sensors is generating large digital datasets that are suitable for transmission in real-time to healthcare and non-healthcare professionals. Computer applications arising from these phenomena are potentially numberless and will probably drive changes in both doctor-patient relationships and healthcare economic scenarios. Several insurance companies have already introduced better money premiums for customers who demonstrate regular use of smartphone applications aimed at illness prevention. 1 Some issues that will need to be addressed in the near future concern patient privacy and data safety. 3 As the practice of selling personal data to third parties for commercial purposes has come to light, increased attention has focused on data security of digital platforms and mobile devices. 4,5 Several reports published recently have revealed a concerning lack of details regarding the way that personal data is managed by telehealth application developers. 5 TheGlobal Privacy Enforcement Network has disclosed that around 60 % of the applications they evaluated exhibited criticisms regarding privacy issues, as they did not properly inform users how their personal data would be used and the number of personal questions asked was considered inappropriate. 6 Heart Failure EpidemiologyHeart failure (HF) is a common clinical syndrome associated with high morbidity and mortality. It is a major public health problem, with a prevalence of over 5.8 million people affected in the US, and over 26 million people worldwide. 7 In the US and in Europe, HF prevalence ranges from 1.1 % to 2.2 % in the general population. Most of the HF burden is situated in people aged over 65 years, who account for more than 80 % of deaths and prevalent cases in the US and in Europe. 8,9The lifetime probability of developing HF is believed to be one in five.Notwithstanding the historical equation that attributes HF genesis to a reduced left ventricular ejection fraction (LVEF), it has been shown that, in real medical practice, HF with preserved LVEF is ...

This paper considers the use of Machine Learning (ML) in medicine by focusing on the main problem that this computational approach has been aimed at solving or at least minimizing: uncertainty. To this aim, we point out how uncertainty is so ingrained in medicine that it biases also the representation of clinical phenomena, that is the very input of ML models, thus undermining the clinical significance of their output. Recognizing this can motivate both medical doctors, in taking more responsibility in the development and use of these decision aids, and the researchers, in pursuing different ways to assess the value of these systems. In so doing, both designers and users could take this intrinsic characteristic of medicine more seriously and consider alternative approaches that do not "sweep uncertainty under the rug" within an objectivist fiction, which everyone can come up by believing as true.

This article focuses on the production side of clinical data work, or data recording work, and in particular, on its multiplicity in terms of data variability. We report the findings from two case studies aimed at assessing the multiplicity that can be observed when the same medical phenomenon is recorded by multiple competent experts, yet the recorded data enable the knowledgeable management of illness trajectories. Often framed in terms of the latent unreliability of medical data, and then treated as a problem to solve, we argue that practitioners in the health informatics field must gain a greater awareness of the natural variability of data inscribing work, assess it, and design solutions that allow actors on both sides of clinical data work, that is, the production and care, as well as the primary and secondary uses of data to aptly inform each other’s practices.

Coronary stent thrombosis (CST) is a major concern of interventional cardiology. Several risk factors for CST have been identified, but as a whole they do not explain the pathophysiology of CST. This study was designed to investigate whether acute infection-inflammation could facilitate the occurrence of CST. Forty-one patients, aged 66.6 +/- 11 years, consecutively admitted to our catheterization laboratory for acute, subacute or late CST, were retrospectively analysed. Transient acute infection-inflammation on admission for CST was diagnosed by predefined criteria. Prevalence of known risk factors for CST was also investigated. Twenty-one patients (51%) met predefined criteria for the occurrence of acute infection-inflammation. On admission, in these patients, levels of systemic humoral and cellular inflammatory markers were significantly higher than those of patients without recent or ongoing acute infection-inflammation (p < 0.05 for all). 62% of patients with acute infection-inflammation had less than two known risk factors for CST whereas only 37% patients without infection-inflammation showed less than two risk factors (p = 0.03) and showed more frequent interruption of antiplatelet treatment (17 vs. 2.4%, p = 0.02), mean longer stent length (20.5 +/- 4.8 vs. 16.5 +/- 5.1 mm, p = 0.02) and lower left ventricular ejection fraction before CST (42.9 +/- 14 vs. 47.3 +/- 11%, p = 0.02). In conclusion, acute infection-inflammation could play a role in facilitating the occurrence of CST in a subgroup with low risk profile for known risk factors. Our findings, if confirmed, could suggest new opportunities for prevention and treatment of CST.