COVID-19 is one of the biggest challenges that human beings have faced recently. Many researchers have proposed different prediction methods for establishing a virus transmission model and predicting the trend of COVID-19. Among them, the methods based on artificial intelligence are currently the most interesting and widely used. However, only using artificial intelligence methods for prediction cannot capture the time change pattern of the transmission of infectious diseases. To solve this problem, this paper proposes a COVID-19 prediction model based on time-dependent SIRVD by using deep learning. This model combines deep learning technology with the mathematical model of infectious diseases, and forecasts the parameters in the mathematical model of infectious diseases by fusing deep learning models such as LSTM and other time prediction methods. In the current situation of mass vaccination, we analyzed COVID-19 data from January 15, 2021, to May 27, 2021 in seven countries – India, Argentina, Brazil, South Korea, Russia, the United Kingdom, France, Germany, and Italy. The experimental results show that the prediction model not only has a 50% improvement in single-day predictions compared to pure deep learning methods, but also can be adapted to short- and medium-term predictions, which makes the overall prediction more interpretable and robust.

IntroductionTwo million people in the UK are experiencing long COVID (LC), which necessitates effective and scalable interventions to manage this condition. This study provides the first results from a scalable rehabilitation programme for participants presenting with LC.Methods601 adult participants with symptoms of LC completed the Nuffield Health COVID-19 Rehabilitation Programme between February 2021 and March 2022 and provided written informed consent for the inclusion of outcomes data in external publications. The 12-week programme included three exercise sessions per week consisting of aerobic and strength-based exercises, and stability and mobility activities. The first 6 weeks of the programme were conducted remotely, whereas the second 6 weeks incorporated face-to-face rehabilitation sessions in a community setting. A weekly telephone call with a rehabilitation specialist was also provided to support queries and advise on exercise selection, symptom management and emotional wellbeing.ResultsThe 12-week rehabilitation programme significantly improved Dyspnea-12 (D-12), Duke Activity Status Index (DASI), World Health Orginaisation-5 (WHO-5) and EQ-5D-5L utility scores (all p < 0.001), with the 95% confidence intervals (CI) for the improvement in each of these outcomes exceeding the minimum clinically important difference (MCID) for each measure (mean change [CI]: D-12: −3.4 [−3.9, −2.9]; DASI: 9.2 [8.2, 10.1]; WHO-5: 20.3 [18.6, 22.0]; EQ-5D-5L utility: 0.11 [0.10, 0.13]). Significant improvements exceeding the MCID were also observed for sit-to-stand test results (4.1 [3.5, 4.6]). On completion of the rehabilitation programme, participants also reported significantly fewer GP consultations (p < 0.001), sick days (p = 0.003) and outpatient visits (p = 0.007) during the previous 3 months compared with baseline.DiscussionThe blended and community design of this rehabilitation model makes it scalable and meets the urgent need for an effective intervention to support patients experiencing LC. This rehabilitation model is well placed to support the NHS (and other healthcare systems worldwide) in its aim of controlling the impacts of COVID-19 and delivering on its long-term plan.Clinical trial registrationhttps://www.isrctn.com/ISRCTN14707226, identifier 14707226.

BackgroundFinding effective intervention strategies to combat rising obesity levels could significantly reduce the burden that obesity and associated non-communicable diseases places on both individuals and the National Health Service.MethodsIn this parallel randomised-controlled trial, 76 participants who are overweight or obese (50 female) were given free access to a fitness centre for the duration of the 12-week intervention and randomised to one of three interventions. The commercial intervention, the Healthy Weight Programme, (HWP, n = 25, 10/15 men/women) consisted of twelve 1-h nutrition coaching sessions with a nutritionist delivered as a mixture of group and 1 to 1 sessions. In addition, twice-weekly exercise sessions (24 in total) were delivered by personal trainers for 12 weeks. The NHS intervention (n = 25, 8/17 men/women) consisted of following an entirely self-managed 12-week online NHS resource. The GYM intervention (n = 26, 8/18 men/women) received no guidance or formal intervention. All participants were provided with a gym induction for safety and both the NHS and GYM participants were familiarised with ACSM physical activity guidelines by way of a hand-out.ResultsThe overall follow-up rate was 83%. Body mass was significantly reduced at post-intervention in all groups (HWP: N = 18, − 5.17 ± 4.22 kg, NHS: N = 21–4.19 ± 5.49 kg; GYM: N = 24–1.17 ± 3.00 kg; p < 0.001) with greater reductions observed in HWP and NHS groups compared to GYM (p < 0.05). Out with body mass and BMI, there were no additional statistically significant time x intervention interaction effects.ConclusionsThis is the first study to evaluate the efficacy of both a free online NHS self-help weight-loss tool and a commercial weight loss programme that provides face-to-face nutritional support and supervised exercise. The findings suggest that both interventions are superior to an active control condition with regard to eliciting short-term weight-loss.Trial registrationISRCTN Registry - ISRCTN31489026. Prospectively registered: 27/07/16.

IntroductionOsteoarthritis is a chronic musculoskeletal condition that impacts more than 300 million people worldwide, with 43 million people experiencing moderate to severe disability due to the disease. This service evaluation provides the results from a tailored blended model of care on joint health, physical function, and personal wellbeing.Methods1,593 adult participants with osteoarthritis completed the Nuffield Health Joint Pain Programme between February 2019 and May 2022. The 12-week programme included two 40-min exercise sessions per week. All exercise sessions were conducted face-to-face and were followed by 20 min of education to provide information and advice on managing osteoarthritis.ResultsThe 12-week joint pain programme significantly improved Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) global scores (Week 0: 37.5 [17.2]; Week 12: 24.0 [16.6]; p &lt; 0.001), as well as subscales for pain (Week 0: 7.6 [3.7]; Week 12: 4.9 [3.7]; p &lt; 0.001), function (Week 0: 26.0 [13.0]; Week 12: 16.3 [12.4]; p &lt; 0.001), and stiffness (Week 0: 3.9 [1.6]; Week 12: 2.8 [1.7]; p &lt; 0.001). Significant improvements in health-related outcomes including systolic and diastolic blood pressure (Week 0: 139 [18] mmHg; Week 12: 134 [17] mmHg, and Week 0: 82 [11] mmHg; Week 12: 79 [19] mmHg; both p &lt; 0.001), body mass index (Week 0: 29.0 [4.5] kg/m2; Week 12: 28.6 [4.4] kg/m2; p &lt; 0.001), waist to hip ratio (Week 0: 0.92 [0.23]; Week 12: 0.90 [0.11], p &lt; 0.01) and timed up and go (Week 0: 10.8 s [2.9]; Week 12: 8.1 s [2.0]; p &lt; 0.001) were also observed. On completion of the joint pain programme, participants also reported significant improvements in all assessed aspects of self-reported wellbeing (all p &lt; 0.001).DiscussionWith reductions in physical symptoms of osteoarthritis and improvements in personal wellbeing, the joint pain programme delivered by personal trainers in a gym-setting offers a nationally scalable, non-pharmacological treatment pathway for osteoarthritis.