Value assessment of artificial intelligence in medical imaging: a scoping review.

BACKGROUND: Artificial intelligence (AI) is seen as one of the major disrupting forces in the future healthcare system. However, the assessment of the value of these new technologies is still unclear, and no agreed international health technology assessment-based guideline exists. This study provides an overview of the available literature in the value assessment of AI in the field of medical imaging. METHODS: We performed a systematic scoping review of published studies between January 2016 and September 2020 using 10 databases (Medline, Scopus, ProQuest, Google Scholar, and six related databases of grey literature). Information about the context (country, clinical area, and type of study) and mentioned domains with specific outcomes and items were extracted. An existing domain classification, from a European assessment framework, was used as a point of departure, and extracted data were grouped into domains and content analysis of data was performed covering predetermined themes. RESULTS: Seventy-nine studies were included out of 5890 identified articles. An additional seven studies were identified by searching reference lists, and the analysis was performed on 86 included studies. Eleven domains were identified: (1) health problem and current use of technology, (2) technology aspects, (3) safety assessment, (4) clinical effectiveness, (5) economics, (6) ethical analysis, (7) organisational aspects, (8) patients and social aspects, (9) legal aspects, (10) development of AI algorithm, performance metrics and validation, and (11) other aspects. The frequency of mentioning a domain varied from 20 to 78% within the included papers. Only 15/86 studies were actual assessments of AI technologies. The majority of data were statements from reviews or papers voicing future needs or challenges of AI research, i.e. not actual outcomes of evaluations. CONCLUSIONS: This review regarding value assessment of AI in medical imaging yielded 86 studies including 11 identified domains. The domain classification based on European assessment framework proved useful and current analysis added one new domain. Included studies had a broad range of essential domains about addressing AI technologies highlighting the importance of domains related to legal and ethical aspects.

Model for ASsessing the value of Artificial Intelligence in medical imaging (MAS-AI).

OBJECTIVES: Artificial intelligence (AI) is seen as a major disrupting force in the future healthcare system. However, the assessment of the value of AI technologies is still unclear. Therefore, a multidisciplinary group of experts and patients developed a Model for ASsessing the value of AI (MAS-AI) in medical imaging. Medical imaging is chosen due to the maturity of AI in this area, ensuring a robust evidence-based model. METHODS: MAS-AI was developed in three phases. First, a literature review of existing guides, evaluations, and assessments of the value of AI in the field of medical imaging. Next, we interviewed leading researchers in AI in Denmark. The third phase consisted of two workshops where decision makers, patient organizations, and researchers discussed crucial topics for evaluating AI. The multidisciplinary team revised the model between workshops according to comments. RESULTS: The MAS-AI guideline consists of two steps covering nine domains and five process factors supporting the assessment. Step 1 contains a description of patients, how the AI model was developed, and initial ethical and legal considerations. In step 2, a multidisciplinary assessment of outcomes of the AI application is done for the five remaining domains: safety, clinical aspects, economics, organizational aspects, and patient aspects. CONCLUSIONS: We have developed an health technology assessment-based framework to support the introduction of AI technologies into healthcare in medical imaging. It is essential to ensure informed and valid decisions regarding the adoption of AI with a structured process and tool. MAS-AI can help support decision making and provide greater transparency for all parties.

Comparison Between Isometric and Concentric Motor Fatigability in Persons With Multiple Sclerosis and Healthy Controls - exploring central and peripheral contributions of motor fatigability.

BACKGROUND: Motor fatigability (i.e. contraction-induced reduction in muscle strength) from a concentric task associate stronger to walking and perception of fatigue in persons with multiple sclerosis (pwMS), compared with an isometric task. However, the central and peripheral contributions of motor fatigability between these tasks have not been investigated. OBJECTIVE: Compare the central and peripheral contributions of motor fatigability in the knee extensors in a sustained isometric fatigability protocol versus a concentric fatigability protocol and in pwMS versus healthy controls (HCs). METHODS: Participants (n=31 pwMS; n=15 HCs) underwent neuromuscular testing before and immediately after two knee extensor fatigability tasks (sustained isometric and concentric) in an isokinetic dynamometer. Neuromuscular testing of fatigability consisted of maximal voluntary contraction, voluntary activation (central/neural contributor), and resting twitch (peripheral/muscular contributor) determined by the interpolated twitch technique. RESULTS: Sustained isometric and concentric fatigability protocols resulted in motor fatigability for both pwMS and HCs, with no between-protocols differences for either group. Regression analysis showed that motor fatigability variance in pwMS was mainly attributed to central fatigability in the sustained isometric protocol and to both central and peripheral fatigability in the concentric protocol. In HCs, the variance in sustained isometric and concentric fatigability were attributed to both peripheral and central fatigability. CONCLUSION: Central and peripheral contributions of motor fatigability differed between sustained isometric and concentric protocols as well as between pwMS and HCs. These between-protocol differences in pwMS provide a neuromuscular dimension to the reported difference in the strength of associations of concentric and isometric tasks to walking and perception of fatigue in pwMS.

The hospital telemedicine TELEMED database: Providing information on evidence-based telemedicine services to hospital managers and healthcare professionals.

BACKGROUND: Increased use of telemedicine in the healthcare system is a political goal in Denmark. Although the number of hospital patients using interventions such as the video consultation has increased in recent years only a small proportion of the outpatient and inpatient visits involve telemedicine. The TELEMED database (https://telemedicine.cimt.dk/) has been launched at the Center for Innovative Medical Technology in Denmark to ensure that hospital managers and healthcare professionals have access to information about telemedicine services and their effectiveness. This article describes the development and the content of the TELEMED database. METHODS: A structured literature search was made in the PubMed Database for randomised controlled trials or observational studies with a control group that investigated the effect of telemedicine interventions for hospital patients. Data were extracted from each article on the clinical effectiveness, patient perceptions, economic effects and implementation challenges. As the database should only provide inspiration to healthcare professionals regarding possibilities for use of telemedicine, the risk of bias in the studies was not assessed. RESULTS: The literature search resulted in 2825 hits. Based on full text assessment, 331 articles were included for data extraction and assessment. These articles present telemedicine services used in 22 different medical specialities. Forty-eight percent of the studies found a positive, statistically significant clinical effect, while 47% showed no statistically significant difference. In 48% of the studies, patients' experiences were examined and of these 68% found positive patient experiences. Fifty-four percent of the articles included information on the economic effects and, of these, 51% found reduction in healthcare utilization. In the majority of studies between two and four types of implementation challenges were found.Conclusions and recommendations: The TELEMED database provides an easily accessible overview of existing evidence-based telemedicine services for use by hospital managers and health professionals, who whish to to implement telemedicine. The database is freely available and expected to be continuously improved and broadened over time.

Diagnostic accuracy of capsule endoscopy compared with colonoscopy for polyp detection: systematic review and meta-analyses.

BACKGROUND: Colon capsule endoscopy (CCE) is a technology that might contribute to colorectal cancer (CRC) screening programs as a filter test between fecal immunochemical testing and standard colonoscopy. The aim was to systematically review the literature for studies investigating the diagnostic yield of second-generation CCE compared with standard colonoscopy. METHODS: A systematic literature search was performed in PubMed, Embase, and Web of Science. Study characteristics including quality of bowel preparation and completeness of CCE transits were extracted. Per-patient sensitivity and specificity were extracted for polyps (any size, ≥ 10 mm, ≥ 6 mm) and lesion characteristics. Meta-analyses of diagnostic yield were performed. RESULTS: The literature search revealed 1077 unique papers and 12 studies were included. Studies involved a total of 2199 patients, of whom 1898 were included in analyses. The rate of patients with adequate bowel preparation varied from 40 % to 100 %. The rates of complete CCE transit varied from 57 % to 100 %. Our meta-analyses demonstrated that mean (95 % confidence interval) sensitivity, specificity, and diagnostic odds ratio were: 0.85 (0.73-0.92), 0.85 (0.70-0.93), and 30.5 (16.2-57.2), respectively, for polyps of any size; 0.87 (0.82-0.90), 0.95 (0.92-0.97), and 136.0 (70.6-262.1), respectively, for polyps ≥ 10 mm; and 0.87 (0.83-0.90), 0.88 (0.75-0.95), and 51.1 (19.8-131.8), respectively, for polyps ≥ 6 mm. No serious adverse events were reported for CCE. CONCLUSION: CCE had high sensitivity and specificity for per-patient polyps compared with standard colonoscopy However, the relatively high rate of incomplete investigations limits the application of CCE in a CRC screening setting.

Static overlays for pressure ulcer prevention: a hospital-based health technology assessment.

INTRODUCTION: At Odense University Hospital (OUH) alternating-air mattresses (AAM) are used in the prevention of pressure ulcers (PU); however, static overlays might be more effective and have lower costs. To investigate the properties and consequences of using static overlays for prevention of PU at OUH, a hospital-based health technology assessment (HTA) was conducted. METHODS: Two types of static overlays were tested in an observational study and compared with AAM for patients with a medium-high risk of PU in geriatric and orthopaedic wards at OUH. Incidence of PU was investigated 7 months before (n=720) and 6 months after implementation (n=837). Staff attitudes were examined in a questionnaire survey (n=55) and focus group interviews (n=13). Patients who had tried one of the overlays and the AAM were interviewed (n=12). RESULTS: No statistical difference in PU incidence was found before and after the implementation of overlays (2.5% before, 2.7% after, P=0.874, n=1557) and no patients lying on overlays developed PU (n=123). Staff had mixed attitudes, but the majority preferred having overlays as an option for their patients. Interviewed patients preferred overlays due to less noise and improved mobility. CONCLUSION: Both types of overlay are effective in PU prevention. However, overlays introduce challenges for staff and clear guidelines for the selection of support surfaces are needed. Overall, it is recommended that static overlays are considered as an alternative to AAM for PU prevention.

A Head-to-Head Comparison of an Isometric and a Concentric Fatigability Protocol and the Association With Fatigue and Walking in Persons With Multiple Sclerosis.

Background. Fatigue is one of the most frequent symptoms in persons with multiple sclerosis (MS). Distinction is made between subjective perceptions of fatigue and objective measures of fatigability. Fatigability can be measured by different protocols. Yet no studies have compared isometric and concentric contraction protocols of the lower extremities head-to-head. Therefore, the purpose of the present study was to (1) compare 2 such protocols head-to-head and (2) to investigate the association between fatigability evoked by the 2 protocols and measures of fatigue and walking. Methods. A total of 45 patients with MS had their walking capacity measured objectively by the 6-minute walk test (6MWT) and subjectively by the 12-item Multiple Sclerosis Walking Scale (MSWS-12). Fatigue was measured by the Modified Fatigue Impact Scale (MFIS) and fatigability by 2 knee extension protocols: sustained isometric and concentric. Results. The sustained isometric protocol induced a higher degree of fatigability than the concentric protocol (P < .01). Regression analyses revealed that sustained isometric fatigability was not associated with either measures of fatigue or walking (all r2 = 0.00; P = .85-.99), whereas the concentric protocol was significantly associated with fatigue (r2 = 0.20; P < .01), 6MWT (r2 = 0.09; P < .05), and MSWS-12 (r2 = 0.16; P < .01). Furthermore, after adjusting for maximal strength and sex, concentric fatigability remained a strong and significant predictor of fatigue (ß = 0.49) and walking (6MWT: ß = -0.26; MSWS: ß = 0.37). Conclusion. This study provides the first evidence that a lower-extremity concentric fatigability protocol provides superior reflection of both fatigue and walking when compared with a sustained isometric protocol. We suggest that concentric protocols should be the focus of future studies investigating fatigability.

Multifaceted Pharmacist-led Interventions in the Hospital Setting: A Systematic Review.

Clinical pharmacy services often comprise complex interventions. In this MiniReview, we conducted a systematic review aiming to evaluate the impact of multifaceted pharmacist-led interventions in a hospital setting. We searched MEDLINE, Embase, Cochrane Library and CINAHL for peer-reviewed articles published from 2006 to 1 March 2018. Controlled trials concerning hospitalized patients in any setting receiving patient-related multifaceted pharmacist-led interventions were considered. All types of outcome were accepted. Inclusion and data extraction were performed. Study characteristics were collected, and risk of bias assessment was conducted utilizing the Cochrane Risk of Bias tools. All stages were conducted by at least two independent reviewers. The review was registered in PROSPERO (CRD42017075808). A total of 11,896 publications were identified, and 28 publications were included. Of these, 17 were conducted in Europe. Six of the included publications were multi-centre studies, and 16 were randomized trials. Usual care was the comparator. Significant results on quality of medication use were reported as positive in eleven studies (n = 18; 61%) and negative in one (n = 18, 6%). Hospital visits were reduced significantly in seven studies (n = 16; 44%). Four studies (n = 12; 33%) reported a positive significant effect on either length of stay or time to revisit, and one study reported a negative effect (n = 12; 6%). All studies investigating mortality (n = 6), patient-reported outcome (n = 7) and cost-effectiveness (n = 1) showed no significant results. This MiniReview indicates that multifaceted pharmacist-led interventions in a hospital setting may improve the quality of medication use and reduce hospital visits and length of stay, while no effect was seen on mortality, patient-reported outcome and cost-effectiveness.

Can resistance training impact MRI outcomes in relapsing-remitting multiple sclerosis?

BACKGROUND: Multiple sclerosis (MS) is characterised by accelerated brain atrophy, which relates to disease progression. Previous research shows that progressive resistance training (PRT) can counteract brain atrophy in other populations. OBJECTIVE: To evaluate the effects of PRT by magnetic resonance imaging (MRI) and clinical measures of disease progression in people with MS. METHODS: This study was a 24-week randomised controlled cross-over trial, including a Training ( n = 18, 24 weeks of PRT followed by self-guided physical activity) and Waitlist group ( n = 17, 24 weeks of habitual lifestyle followed by PRT). Assessments included disability measures and MRI (lesion load, global brain volume, percentage brain volume change (PBVC) and cortical thickness). RESULTS: While the MS Functional Composite score improved, Expanded Disability Status Scale, lesion load and global brain volumes did not differ between groups. PBVC tended to differ between groups and higher absolute cortical thickness values were observed in 19 of 74 investigated cortical regions after PRT. Observed changes were confirmed and reproduced when comparing relative cortical thickness changes between groups for four areas: anterior cingulate gyrus, temporal pole, orbital sulcus and inferior temporal sulcus. CONCLUSION: PRT seem to induce an increase in cortical thickness, indicating that PRT have a neuroprotective or even neuroregenerative effect in relapsing-remitting MS.

Validity of the Model for Assessment of Telemedicine: A Delphi study.

Introduction In 2009, the Model for Assessment of Telemedicine (MAST) was developed within the MethoTelemed project as a framework for description of the effectiveness of telemedicine applications. The goal was for the assessments to be used as basis for decision-making in healthcare systems. Since then, MAST has been used in many European telemedicine studies and is now the most widely used model for assessment of telemedicine. The aim of this study was to assess the face validity of MAST. Methods A modified Delphi process was carried out and included a workshop with a sample of healthcare decision makers. A total of 56 decision makers and experts in telemedicine were invited and 19 persons participated in the two Delphi rounds. Thirteen hospitals or regional health authorities from 12 European countries and six research organisations were represented in the final sample. The participants were asked to assess the importance of the different domains and topics in MAST on a 0-3 Likert scale. Results All respondents completed the two rounds. Based on the answers, the face validity of all MAST domains was confirmed, since all domains were considered moderately or highly important by more than 80% of the respondents. Discussion Even though the study confirmed the validity of MAST, a number of supplements and improvements regarding study design and data collection were suggested. When considering the results it should be noticed that the sample size was small and larger studies are needed to confirm the results.

Can aerobic exercise alleviate flu-like symptoms following interferon beta-1a injections in patients with multiple sclerosis?

BACKGROUND: Flu-like symptoms (FLS) are common side effects of interferon beta (IFNß) treatment, and may affect the willingness to initiate therapy, the long-term acceptability, and the adherence to the treatment. Case reports suggest that aerobic exercise is able to markedly reduce FLS following IFNß-1a injections in persons with multiple sclerosis (PwMS). OBJECTIVE: To test the hypothesis that aerobic exercise can alleviate FLS following IFNß-1a injections in PwMS, and secondarily to examine whether or not fluctuations in circulating cytokines provide a mechanism that can explain a potential positive effect. METHODS: Seventeen PwMS who frequently experience FLS following IFNß-1a injections completed four days of testing. On two of the testing days they completed 35min of aerobic exercise on a bicycle-ergometer following IFNß-1a injection. On the two other testing days, no intervention took place following the injection. FLS were assessed pre-injection and 3h, 5h, 12h and 24h post-injection. Blood samples were taken pre-injection and 1h and 3h post-injection to determine levels of circulating interleukin 6 and 17 and IFNγ. The primary study endpoint was the comparison of the change in FLS severity from pre-injection to 5h post-injection between days with injection alone and days with injection followed by aerobic exercise. RESULTS: FLS severity change was significantly lower on days with exercise compared to days with rest. IL6 was significantly increased 3h following IFNß-1a injection and exercise compared to 1h post and pre and when compared to the resting condition. Participants reported no adverse events in addition to FLS during the study period. CONCLUSION: Data from this study suggest that moderate intensity aerobic exercise following IFNß-1a injections is safe and can alleviate the FLS severity in PwMS. Based on these results, 35min of aerobic exercise should be encouraged for PwMS who often experience FLS following IFNß-1a injections.

Relationship between muscle strength parameters and functional capacity in persons with mild to moderate degree multiple sclerosis.

BACKGROUND: Maximal muscle strength has been shown to be an important predictor of functional capacity for persons with multiple sclerosis (PwMS). Another muscle strength parameter known to be important for functional capacity in other patient groups is rate of force development (RFD) in knee extensors and flexors. This has not been investigated for PwMS. Thus, the purpose of this study was to investigate the relationship between RFD and maximal muscle strength of knee extensors and flexors and measures of functional capacity in PwMS. METHODS: 35 PwMS (Expanded Disability Status Scale 2-4) underwent isokinetic dynamometry to determine RFD and maximal isometric and isokinetic muscle strength for both legs. Furthermore all participants performed timed 25 foot walk tests (T25FWT), two minute walk tests (2MWT), stairclimb tests and 5-time sit-to-stand (5STS) tests to determine functional capacity. Multiple linear regressions were performed to determine which muscle strength parameter would serve as a stronger predictor of walking performance. RESULTS: Both RFD and maximal muscle strength correlated with functional capacity. Correlations were strongest for knee extensors and flexors of the weaker leg, while no clear ranking of the influence of the knee extensors vs. flexors on walking was evident. Multiple linear regressions showed that maximal isokinetic strength of the weaker leg is a better predictor for T25FWT and 2MWT performance than RFD. CONCLUSIONS: Maximal muscle strength of the weaker leg is the better predictor of walking performance in persons with mild to moderate multiple sclerosis. RFD, although also important for functional capacity, is a less strong predictor. Maximal strength of the knee extensors, rather than the knee flexors, predicted performance in the stairclimb and 5STS tests.

Neuromuscular adaptations to long-term progressive resistance training translates to improved functional capacity for people with multiple sclerosis and is maintained at follow-up.

BACKGROUND: Progressive resistance training (PRT) is acknowledged to effectively improve muscle strength for people with multiple sclerosis (PwMS), but diverging results exist regarding whether such improvements translates to improved functional capacity, possibly relating to insufficient duration and/or intensity in some previous studies. OBJECTIVE: The purpose of this study was to evaluate potential changes in functional capacity and neuromuscular function after 24 weeks of supervised PRT, and whether improvements are maintained after an additional 24 weeks of self-guided exercise. METHODS: This study was a randomised controlled trial, with a training group and a waitlist group undergoing supervised PRT for 24 weeks initially or after 24 weeks of habitual lifestyle, respectively. Functional capacity, isometric muscle strength of knee extensors and flexors, neural drive and thigh muscle cross-sectional area was measured at baseline, after 24 and 48 weeks. RESULTS: The training group significantly improved neuromuscular function of the knee extensors and flexors, which translated to improvements in functional capacity. Furthermore, the improved functional capacity was maintained after 24 weeks of self-guided physical activity. The waitlist group produced similar patterns of changes after PRT. CONCLUSION: Compelling evidence is provided, that PRT performed over sufficiently long periods, improves functional capacity, likely due to neuromuscular adaptations.

Similar changes in muscle fiber phenotype with differentiated consequences for rate of force development: endurance versus resistance training.

Resistance training has been shown to positively affect the rate of force development (RFD) whereas there is currently no data on the effect of endurance training on RFD. Subjects completed ten weeks of either resistance training (RT, n=7) or endurance cycling (END, n=7). Pre and post measurements included biopsies obtained from m. vastus lateralis to quantify fiber phenotype and fiber area and isokinetic dynamometer tests to quantify maximal torque (Nm) and RFD (Nm/s) at 0-30, 0-50, 0-100 and 0-200ms during maximal isometric contraction for both knee extensors and flexors. Both groups increased the area percentage of type IIa fibers (p<.01) and decreased the area percentage of type IIx fibers (p=.05), whereas only RT increased fiber size (p<.05). RT significantly increased eccentric, concentric and isometric strength for both knee extensors and flexors, whereas END did not. RT increased 200ms RFD (p<.01) in knee flexor RFD and a tendency towards an increase at 100ms (p<.1), whereas tendencies towards decreases were observed for the END group at 30, 50 and 100ms (p<.1), resulting in RT having a higher RFD than END at post (p<.01). In conclusion, resistance training may be very important for maintaining RFD, whereas endurance training may negatively impact RFD.

Aerobic intensity and pacing pattern during the six-minute walk test in patients with multiple sclerosis.

OBJECTIVE: To examine the aerobic intensity level and pacing pattern during the 6-min walk test (6MWT) in persons with multiple sclerosis, taking into account time of day, fatigue, disability level and multiple sclerosis subtype. DESIGN: Cross-sectional study. SUBJECTS/PATIENTS: Eighty multiple sclerosis patients (Expanded Disability Status Scale, EDSS ≤ 6.5). METHODS: Participants performed the 6MWT at 3 different time-points (morning, noon, afternoon) during 1 day. Heart rate and pacing strategy (distance covered every minute) were registered. A sub-group analysis determined the effects of fatigue, disability level and multiple sclerosis subtype. RESULTS: The relative aerobic intensity was constant throughout the day (67 ± 10% of estimated maximal heart rate). In all sub-groups heart rate increased and distance walked declined after the first minute (p < 0.001). The mild EDSS sub-group showed a slightly larger increase throughout the 6MWT in heart rate development, while no differences were seen in sub-groups of fatigue and multiple sclerosis subtype. In most sub-groups walking speed was fastest in the first minute and constant during the final 4 minutes. CONCLUSION: In patients with multiple sclerosis aerobic intensity is moderate during the 6MWT and unaffected by time of day. Disability may have some influence on aerobic intensity, but not on pacing strategy during the 6MWT, whereas neither fatigue nor multiple sclerosis subtype has any effect.

Muscle morphological and strength adaptations to endurance vs. resistance training.

Fascicle angle (FA) is suggested to increase as a result of fiber hypertrophy and furthermore to serve as the explanatory link in the discrepancy in the relative adaptations in the anatomical cross-sectional area (CSA) and fiber CSA after resistance training (RT). In contrast to RT, the effects of endurance training on FA are unclear. The purpose of this study was therefore to investigate and compare the longitudinal effects of either progressive endurance training (END, n = 7) or RT (n = 7) in young untrained men on FA, anatomical CSA, and fiber CSA. Muscle morphological measures included the assessment of vastus lateralis FA obtained by ultrasonography and anatomical CSA by magnetic resonance imaging of the thigh and fiber CSA deduced from histochemical analyses of biopsy samples from m. vastus lateralis. Functional performance measures included VO2max and maximal voluntary contraction (MVC). The RT produced increases in FA by 23 ± 8% (p < 0.01), anatomical CSA of the knee extensor muscles by 9 ± 3% (p = 0.001), and fiber CSA by 19 ± 7% (p < 0.05). RT increased knee extensor MVC by 20 ± 5% (p < 0.001). END increased VO2max by 10 ± 2% but did not evoke changes in FA, anatomical CSA, or in fiber CSA. In conclusion, the morphological changes induced by 10 weeks of RT support that FA does indeed serve as the explanatory link in the observed discrepancy between the changes in anatomical and fiber CSA. Contrarily, 10 weeks of endurance training did not induce changes in FA, but the lack of morphological changes from END indirectly support the fact that fiber hypertrophy and FA are interrelated.