The rapid increase in telemedicine coupled with recent advances in diagnostic artificial intelligence (AI) create the imperative to consider the opportunities and risks of inserting AI-based support ...into new paradigms of care. Here we build on recent achievements in the accuracy of image-based AI for skin cancer diagnosis to address the effects of varied representations of AI-based support across different levels of clinical expertise and multiple clinical workflows. We find that good quality AI-based support of clinical decision-making improves diagnostic accuracy over that of either AI or physicians alone, and that the least experienced clinicians gain the most from AI-based support. We further find that AI-based multiclass probabilities outperformed content-based image retrieval (CBIR) representations of AI in the mobile technology environment, and AI-based support had utility in simulations of second opinions and of telemedicine triage. In addition to demonstrating the potential benefits associated with good quality AI in the hands of non-expert clinicians, we find that faulty AI can mislead the entire spectrum of clinicians, including experts. Lastly, we show that insights derived from AI class-activation maps can inform improvements in human diagnosis. Together, our approach and findings offer a framework for future studies across the spectrum of image-based diagnostics to improve human-computer collaboration in clinical practice.
Artificial intelligence technology has advanced rapidly in recent years and has the potential to improve healthcare outcomes. However, technology uptake will be largely driven by clinicians, and ...there is a paucity of data regarding the attitude that clinicians have to this new technology. In June-August 2019 we conducted an online survey of fellows and trainees of three specialty colleges (ophthalmology, radiology/radiation oncology, dermatology) in Australia and New Zealand on artificial intelligence. There were 632 complete responses (n = 305, 230, and 97, respectively), equating to a response rate of 20.4%, 5.1%, and 13.2% for the above colleges, respectively. The majority (n = 449, 71.0%) believed artificial intelligence would improve their field of medicine, and that medical workforce needs would be impacted by the technology within the next decade (n = 542, 85.8%). Improved disease screening and streamlining of monotonous tasks were identified as key benefits of artificial intelligence. The divestment of healthcare to technology companies and medical liability implications were the greatest concerns. Education was identified as a priority to prepare clinicians for the implementation of artificial intelligence in healthcare. This survey highlights parallels between the perceptions of different clinician groups in Australia and New Zealand about artificial intelligence in medicine. Artificial intelligence was recognized as valuable technology that will have wide-ranging impacts on healthcare.
Purpose
We evaluated the utility of the implementation science framework “Integrated Promoting Action on Research Implementation in Health Services” (i-PARIHS) for introducing patient-reported ...outcome measures (PROMs) into a medical oncology outpatient department. The i-PARIHS framework identifies four core constructs for implementation, including Facilitation, Innovation, Context and Recipients.
Methods
A pilot study used the i-PARIHS framework to identify PROM implementation barriers and enablers to inform facilitation support strategies, such as training clinicians and staff, workflow support, technical support and audit and feedback. Pre- and post-implementation surveys were completed by 83 and 72 staff, respectively, (nurses, doctors and allied health), to assess perceived knowledge, enablers, barriers and utility of PROMs; and acceptability of the PROM intervention was also assessed post-implementation.
Results
Important barriers included time constraints and previous experiences with technology. Enablers included good leadership support and a culture of learning. Facilitation strategies were used to overcome barriers identified in the i-PARIHS core domains. Compared to before the intervention, staff surveys showed improvement in perceived usefulness, perceived understanding and interpretation skills for PROMs. Staff perceptions about lack of time to use PROMs during visits remained a major perceived barrier post-implementation.
Conclusion
The i-PARIHS framework was useful for guiding the implementation of PROMs in routine oncology care. The four core i-PARIHS constructs (Facilitation, Innovation, Context and Recipients) identified factors that directly impacted implementation, with Facilitation having a particularly important role to overcome these barriers. Oncology clinics and health systems considering implementing PROMs should consider having a dedicated Facilitator available during PROM implementation.
Secondary lymphedema is associated with adverse physical and psychosocial consequences among women with breast cancer (BC). This article describes the prevalence and incidence of lymphedema between 6 ...and 18 months after BC treatment; personal, treatment, and behavioral correlates of lymphedema status; and the presence of other upper-body symptoms (UBS) and function (UBF).
A population-based sample of Australian women (n = 287) with recently diagnosed, invasive BC were evaluated on five occasions using bioimpedance spectroscopy. Lymphedema was diagnosed when the ratio of impedance values, comparing treated and untreated sides, was three standard deviations more than normative data. UBF was assessed using the validated Disability of the Arm, Shoulder, and Hand questionnaire.
From 6 to 18 months after surgery, 33% (n = 62) of the sample were classified as having lymphedema; of these, 40% had long-term lymphedema. Although older age, more extensive surgery or axillary node dissection, and experiencing one or more treatment-related complication(s) or symptom(s) at baseline were associated with increased odds, lower socioeconomic status, having a partner, greater child care responsibilities, being treated on the dominant side, participation in regular activity, and having good UBF were associated with decreased odds of lymphedema. Not surprisingly, lymphedema leads to reduced UBF; however, BC survivors report high prevalences of other UBS (34% to 62%), irrespective of their lymphedema status.
Lymphedema is a public health issue deserving greater attention. More systematic surveillance for earlier detection and the potential benefits of physical activity to prevent lymphedema and mitigate symptoms warrant further clinical integration and research.
ABSTRACTLymphedema treatment aims to alleviate symptoms, prevent progression, and reduce risk for skin infection. Mainstream treatment options have been investigated in more than 160 studies. ...Findings from these studies have been included in at least 1 of more than 20 literature reviews. A critique of these reviews was undertaken to summarize efficacy findings. The quality of the reviews was evaluated, and gaps in the research were identified to better guide clinical practice. Overall, there was wide variation in review methods. The quality of studies included in reviews, in study design and reporting overall, has been poor. Reviews consistently concluded that complex physical therapy is effective at reducing limb volume. Volume reductions were also reported after the use of compression garments, pumps, and manual lymphatic drainage. However, greatest improvements were reported when these treatments formed a combined treatment program. Large, well-designed, evaluated, and reported randomised, controlled trials are needed to evaluate and compare treatments. Consistent outcome measures will allow better quality reviews and meta-analysis in the future.
Numerous intervention studies have attempted to increase cervical screening uptake among immigrant women, nonetheless their screening participation remains low. This systematic review and ...meta-analysis aimed to summarise the evidence on interventions to improve cervical screening among immigrant women globally and identify their effectiveness. Databases PubMed, EMBASE, Scopus, PsycINFO, ERIC, CINAHL and CENTRAL were systematically searched from inception to October 12, 2021, for intervention studies, including randomised and clinical controlled trials (RCT, CCT) and one and two group pre-post studies. Peer-reviewed studies involving immigrant and refugee women, in community and clinical settings, were eligible. Comparator interventions were usual or minimal care or attention control. Data extraction, quality appraisal and risk of bias were assessed by two authors independently using COVIDENCE software. Narrative synthesis of findings was carried out, with the main outcome measure defined as the cervical screening uptake rate difference pre- and post-intervention followed by random effects meta-analysis of trials and two group pre-post studies, using Comprehensive Meta-Analysis software, to calculate pooled rate ratios and adjustment for publication bias, where found. The protocol followed PRISMA guidelines and was registered prospectively with PROSPERO (CRD42020192341). 1,900 studies were identified, of which 42 (21 RCTS, 4 CCTs, and 16 pre-post studies) with 44,224 participants, were included in the systematic review, and 28 with 35,495 participants in the meta-analysis. Overall, the uptake difference rate for interventions ranged from -6.7 to 96%. Meta-analysis demonstrated a pooled rate ratio of 1.15 (95% CI 1.03-1.29), with high heterogeneity. Culturally sensitive, multicomponent interventions, using different modes of information delivery and self-sampling modality were most promising. Interventions led to at least 15% increase in cervical screening participation among immigrant women. Interventions designed to overcome logistical barriers and use multiple channels to communicate culturally appropriate health promotion messages are most effective at achieving cervical screening uptake among immigrant women.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Background Clinical trials have demonstrated that patient-reported outcome measures (PROMs) can improve mortality and morbidity outcomes when used in clinical practice. Objective This study aimed to ...prospectively investigate the implementation of PROMs in routine oncology. Outcomes measured included improved symptom detection, clinical response to symptom information, and health service outcomes. Methods Two of 12 eligible clinics were randomized to implement symptom PROMs in a medical oncology outpatient department in Australia. Randomization was carried out at the clinic level. Patients in control clinics continued with usual care; those in intervention clinics completed a symptom PROM at presentation. This was a pilot study investigating symptom detection, using binary logistic models, and clinical response to PROMs investigated using multiple regression models. Results A total of 461 patient encounters were included, consisting of 242 encounters in the control and 222 in the intervention condition. Patients in these clinics most commonly had head and neck, lung, prostate, breast, or colorectal cancer and were seen in the clinic for surveillance and oral or systemic treatments for curative, metastatic, or palliative cancer care pathways. Compared with control encounters, the proportion of symptoms detected increased in intervention encounters (odds ratio 1.05, 95% CI 0.99-1.11; P=.08). The odds of receiving supportive care, demonstrated by nonroutine allied health review, increased in the intervention compared with control encounters (odds ratio 3.54, 95% CI 1.26-9.90; P=.02). Conclusions Implementation of PROMs in routine care did not significantly improve symptom detection but increased the likelihood of nonroutine allied health reviews for supportive care. Larger studies are needed to investigate health service outcomes. Trial Registration Australian New Zealand Clinical Trials Registry ACTRN12618000398202;
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, UILJ, UKNU, UL, UM, UPUK
Abstract Objective Cancer-related lymphedema is a debilitating condition that adversely influences function, health and quality of life. The purpose of this study was to assess the prevalence, ...incidence, and risk factors of lower-limb lymphedema pre- through to 24 months post-surgery for gynecological cancer. Methods A clinic-based sample of women (n = 408) with gynecological cancer participated in a prospective, longitudinal study (2008–2011) using self-reported measures (swelling in one or both legs) and objectively measured lymphedema (bioimpedance spectroscopy) at baseline (pre-surgery), six weeks–three months, 6–12 months, and 15–24 months post-surgery. Results At pre-surgery, 15% of women self-reported lymphedema and 27% had measurable evidence of lymphedema. By 24 months post-surgery, incidence of new self-reported or measured lymphedema was 45% and 37%, respectively. Three-quarters of these new cases presented by 12-months post-treatment. While lymphedema was transient for some women, 60% had persistent lymphedema. More extensive lymph node dissection, receipt of chemotherapy and radiation therapy, increasing body mass index, insufficient levels of physical activity, diagnosis of vulvar/vaginal cancer and presence of pre-treatment lymphedema were identified as potential risk factors (p < 0.05). Conclusion Findings support the need for integration of pre-surgical assessment, and prospective, post-treatment surveillance of lymphedema into gynecological cancer care. Future research exploring the role of maintaining healthy body weight, regular physical activity and education about early detection of lymphedema to improve gynecological cancer survivorship is warranted.
Introduction:
Cervical cancer remains a major cause of morbidity and mortality among women from low and lower middle-income countries, as well as underserved population subgroups in high-income ...countries. Migration from South Asia to Australia has increased over the last decade, and immigrant women from this region have been reported as a subgroup, with less than optimal cervical screening participation in Australia. This study examined cervical screening uptake and associated behavioural attitudes among South Asian immigrant women living in Queensland Australia.
Methods:
A cross-sectional, Internet-based survey was used to collect data from a convenience sample of 148 South Asian women living in Queensland. The main outcome measure was receipt of cervical screening test ever (yes/no) and its recency (within 2 years/more than 2 years). The survey also examined participants’ views on barriers towards screening and ways to enhance it.
Results:
Of 148 women who completed the survey, 55.4% (n = 82) reported ever having a cervical screening test before and 43.9% (n = 65) reported having it in previous two years. Not having a previous cervical screening test was significantly associated with duration of stay in Australia for less than five years, not having access to a regular general practitioner (GP), not being employed, having low cervical cancer knowledge level and not knowing if cervical screening test is painful or not. Most commonly reported barriers to screening uptake included considering oneself not at risk, lack of time and lack of information. The most favoured strategy among participants was encouragement by GP and awareness through social media advertisements.
Conclusion:
This study provided insights into factors that need consideration when developing future targeted interventions.
•Endometrial cancer is associated with modifiable risk factors including obesity.•Weight loss and pharmaceutical interventions may prevent endometrial cancer.•Lifestyle interventions were associated ...with reduced endometrial proliferation.•A reduction in circulating insulin levels was seen following lifestyle intervention.•Endometrial cancer prevention research demonstrates promising preliminary evidence.
Endometrial cancer is the most common gynaecological malignancy in Australia. Epidemiological studies have widely documented the association of endometrial cancer with modifiable lifestyle risk factors, most notably obesity. However, preventative strategies for endometrial cancer have not been well reported. The objective of this systematic review was to identify interventions targeted towards modifiable lifestyle risk factors that may reduce the risk of endometrial cancer. Literature published in the past ten years (January 2010 – January 2021) was retrieved from PubMed, Embase and Web of Science literature databases. Of 593 studies potentially eligible, 41 were assessed in full-text, and nine studies were included in the systematic review and synthesis without meta-analysis following the SWiM guidelines. The included studies were highly heterogenous with respect to the type of interventions implemented and the outcomes measured. We identified that diet and physical activity interventions, surgical weight loss interventions, and hormonal interventions were associated with changes in endometrial cancer biomarkers including circulating hormones and tissue markers. We identified a reduction in endometrial proliferation following lifestyle intervention as measured by the ki-67 proliferation index. Furthermore we identified an increase in adiponectin (a circulating biomarker of adiposity) following lifestyle intervention and a reduction in circulating insulin levels following lifestyle intervention. This review highlighted that the area of endometrial cancer prevention research is in its infancy and that further investigation of diet and physical activity interventions, surgical weight loss interventions, and hormonal interventions should be undertaken due to promising preliminary evidence.
PDF
