Data in the literature on cluster headache (CH) indicate a mean age at onset of about 29-30 years; recently, however, cases have been reported with onset in old age. A review of age at onset in all CH patients (n = 693) followed at the University of Parma Headache Centre between 1976 and 2011 shows that 73 (10.5 %) patients began to suffer from CH after age 50. In these 73 patient, the gender (M:F) ratio was 1.4:1, while in the 620 patients with CH onset before age 50, it was 2.5:1. In the patients with CH onset after and before age 50, respectively, the distribution by CH subtype shows that the episodic-to-chronic ratio was 7.6:1 and 7.9:1 in men and 1.5:1 and 7.8:1 in women. In episodic CH men with onset after 50 the average duration of active periods was 60 versus 39 days for those with onset before 50. In women, the duration was 80 and 42 days, respectively. In conclusion, our case review suggests that CH onset after age 50 is not rare, especially in women. Additionally, late onset represents a negative prognostic factor because, particularly in women, CH will more likely be a chronic form and even in episodic forms active periods will last longer.

In a minority of cases, the natural history of migraine without aura (MO) is characterised over time by its evolution into a form of chronic migraine (CM). In order to detect the possible factors predicting this negative evolution of MO, we searched in our Headache Centre files for all clinical records that met the following criteria: (a) first visit between 1976 and 1998; (b) diagnosis of MO or of common migraine at the first observation, with or without association with other primary headache types; (c)\15 days per month of migraine at the first observation; and (d) at least one follow-up visit at least 10 years after the first visit. The patients thus identified were then divided into two groups based on a favourable/ steady evolution (Group A: n = 243, 195 women and 48 men) or an unfavourable evolution (Group B: n = 72, 62 women and 10 men) of their migraine over time. In the two groups, we compared various clinical parameters that were present at the first observation or emerged at the subsequent follow-up visits. The parameters that were statistically significantly more frequent in Group B-and can therefore be considered possible negative prognostic factors-were: (a) C10 days per month of migraine at the first observation; (b) presence of depression at the first visit in males; and (c) onset of depression or arterial hypertension after the first observation but before transformation to CM in females. Based on these findings, in MO patients the high frequency of migraine attacks, comorbidity with depression, and the tendency to develop arterial hypertension should require particular attention and careful management to prevent evolution into CM.

The application of artificial intelligence technologies is growing in several fields of healthcare settings. The aim of this article is to review the current applications of artificial intelligence in bariatric surgery. We performed a review of the literature on Scopus, PubMed and Cochrane databases, screening all relevant studies published until September 2021, and finally including 36 articles. The use of machine learning algorithms in bariatric surgery is explored in all steps of the clinical pathway, from presurgical risk-assessment and intraoperative management to complications and outcomes prediction. The models showed remarkable results helping physicians in the decision-making process, thus improving the quality of care, and contributing to precision medicine. Several legal and ethical hurdles should be overcome before these methods can be used in common practice.

Modern medicine, both in clinical practice and research, has become more and more based on data, which is changing equally in type and quality with the advent and development of healthcare digitalization. The first part of the present paper aims to present the steps through which data, and subsequently clinical and research practice, have evolved from paper-based to digital, proposing a possible future of this digitalization in terms of potential applications and integration of digital tools in medical practice. Noting that digitalization is no more a possible future, but a concrete reality, there is a strong need for a new definition of evidence-based medicine, which must take into account the progressive integration of artificial intelligence (AI) in all decisionmaking processes. So, leaving behind the traditional research concept of human intelligence versus AI, poorly adaptable to real-world clinical practice, a Human and AI hybrid model, seen as a deep integration of AI and human thinking, is proposed as a new healthcare governance system. The second part of our review is focused on some of the major challenges the digitalization process has to face, particularly privacy issues, system complexity and opacity, and ethical concerns related to legal aspects and healthcare disparities. Analyzing these open issues, we aim to present some of the future directions that in our opinion should be pursued to implement AI in clinical practice.

No abstract