| 1. |
- Robinson, Yohan, 1977, et al.
(författare)
-
AI och framtidens försvarsmedicin
- 2020
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- Medicinskt legitimerad personal är, och kommer med stor sannolikhet fortsattatt vara, en knapp resurs inom Försvarsmaktens sjukvårdsorganisation. I denna rapport ges en översikt över pågående och planerade ansatser baserade påartificiell intelligens (AI) inom akutsjukvård med särskild tonvikt på omhändertagandet av traumapatienter, där lösningarna skulle kunna bidra till att Försvarsmakten kan bibehålla sin sjukvårdskapacitet i kritiska lägen. Rapporten är ett resultat av samarbetet mellan FM, FOI, FMV, FHS och KI, och vänder sig i första hand till Försvarsmaktens strategiska ledning.Användningen av AI-teknik i framtida beslutsstöd kan skapa nya möjligheter till avlastning av personal och resurseffektivisering. Tekniken ger möjligheter att i realtid samla in, bearbeta och analysera stora mängder blandadinformation om förbands hälsoläge och fysiska stridsvärde. Bedömning av skadade kan t.ex. göras av triagedrönare och den efterföljande evakueringen kanunderlättas av intelligenta autonoma plattformar. Införandet av AI-system ställer dock vårdgivaren inför svåra etiska och medikolegala överväganden.Försvarsmedicin har en central roll i Försvarsmaktens krigföringsförmåga och för samhällets uthållighet. För att nyttja hela AI-teknikens framfart till Försvarsmaktens nytta måste dess innebörd och konsekvens för försvarsmedicinen förstås. Därför rekommenderar denna studie att Försvarsmaktens framtida satsningar inom AI och autonomi inkluderar den försvarsmedicinska teknikutveckling som är beskriven i denna rapport.
|
|
| 2. |
- Ge, Chenjie, 1991, et al.
(författare)
-
Enlarged Training Dataset by Pairwise GANs for Molecular-Based Brain Tumor Classification
- 2020
-
Ingår i: IEEE Access. - 2169-3536 .- 2169-3536. ; 8:1, s. 22560-22570
-
Tidskriftsartikel (refereegranskat)abstract
- This paper addresses issues of brain tumor subtype classification using Magnetic Resonance Images (MRIs) from different scanner modalities like T1 weighted, T1 weighted with contrast-enhanced, T2 weighted and FLAIR images. Currently most available glioma datasets are relatively moderate in size, and often accompanied with incomplete MRIs in different modalities. To tackle the commonly encountered problems of insufficiently large brain tumor datasets and incomplete modality of image for deep learning, we propose to add augmented brain MR images to enlarge the training dataset by employing a pairwise Generative Adversarial Network (GAN) model. The pairwise GAN is able to generate synthetic MRIs across different modalities. To achieve the patient-level diagnostic result, we propose a post-processing strategy to combine the slice-level glioma subtype classification results by majority voting. A two-stage course-to-fine training strategy is proposed to learn the glioma feature using GAN-augmented MRIs followed by real MRIs. To evaluate the effectiveness of the proposed scheme, experiments have been conducted on a brain tumor dataset for classifying glioma molecular subtypes: isocitrate dehydrogenase 1 (IDH1) mutation and IDH1 wild-type. Our results on the dataset have shown good performance (with test accuracy 88.82%). Comparisons with several state-of-the-art methods are also included.
|
|
| 3. |
- Girma Kebede, Betlehem, et al.
(författare)
-
Communicative challenges among physicians, patients, and family caregivers in cancer care: An exploratory qualitative study in Ethiopia
- 2020
-
Ingår i: PLoS ONE. - : Public Library of Science (PLoS). - 1932-6203. ; 15:3
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Cancer is a growing concern in Ethiopia. Though communication is essential for the treatment process, few studies have looked at communication in Ethiopian cancer care. Due to the large number of patients and scarcity of resources, it is vital to understand how to manage consultations in order to effectively help as many patients as possible in this challenging work environment. Thus, research is needed to analyze and understand the communicative challenges experienced by physicians, patients, and family caregivers, in order to successfully handle patient care in practice. Objective We explore communication in Ethiopian cancer care and present the main challenges faced by physicians, patients, and family caregivers. Methods This explorative qualitative study was conducted at the Oncology Department of the Tikur Anbessa (Black Lion) Specialized Teaching Hospital (TASH) in Addis Ababa, Ethiopia. A triangulation of data collection methods was used: 91 audio-recorded, semi-structured interviews and 21 video-recordings of authentic interactions during hospital rounds. The aim was to obtain as complete a picture as possible of communication from the perspectives of physicians, patients, and family caregivers. The interviews were analyzed using thematic content analysis and the identified themes were supported by excerpts from the transcribed recordings. Results Eight themes emerged from the data. Workload and time pressure, in combination with restricted space for privacy, limited the possibilities for physicians to deliver detailed information and provide emotional support. Furthermore, patient literacy levels, in combination with no or little cancer awareness, financial problems, reliance on traditional and religious treatments, the stigma of cancer, and a fatalistic attitude, resulted in delays in patients seeking care and participating in positive health behaviors, and, subsequently, often resulted in an unwillingness to openly discuss problems with physicians and adhere to treatment. The study also illustrates the paramount role of family in physician-patient communication in Ethiopia. Though family caregivers provide a valuable interpreting support when patients have limited language skills, they can also prevent patients from sharing information with physicians. Another important finding is that family caregivers were often responsible for making decisions about treatment and avoided telling patients about a poor prognosis, believing that conveying bad news may upset them. All of these themes have important implications for the role of ethically acceptable communication in patient-centered care. Conclusions This study has identified a number of serious challenges for successful and ethically acceptable health communication in Ethiopian cancer care. The study contributes to our understanding of the complexity around the role of family, combined with patients’ dependency on family members for communication, support, and access to care, which creates particular ethical dilemmas for the medical staff. The questions raised by this study concern how to organize consultations to achieve patient-centered health communication, while maintaining a constructive alliance with the family and not jeopardizing the patient’s continued access to care. The integration of communication training for medical students in Ethiopia, with a focus on ethical guidelines for family-centered patient consultation suitable for these circumstances, would be an essential step.
|
|
| 4. |
- Ranisch, Robert, et al.
(författare)
-
Ethics of digital contact tracing apps for the Covid-19 pandemic response
- 2020
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- There is a growing interest in contact tracing apps (CT apps) for pandemic man- agement. These apps raise significant moral concerns. It is therefore crucial to consider ethical requirements before and while implementing such apps. Public trust is of major importance for population uptake of contact tracing apps. Hasty, ill-prepared or badly communicated implementations of CT apps will likely under- mine public trust, and as such, risk impeding general effectiveness. In response to these demands, to meet ethical requirements and find a basis for justified trust, this background introduces an ethical framework for a responsible design and implementation of CT apps. However, even prudently chosen measures of digital contact tracing carry moral costs, which makes it necessary address different trade-offs. This background paper aims to inform developers, researchers and decision-makers be- fore and throughout the process of implementing contact tracing apps.
|
|
| 5. |
- Berbyuk Lindström, Nataliya, 1978, et al.
(författare)
-
Person- and Family-Centeredness in Ethiopian Cancer Care: Improving Communication, Ethics, Decision Making and Health
- 2020
-
Ingår i: JMIR Research Protocols. - : JMIR Publications Inc.. - 1929-0748. ; 9:5
-
Tidskriftsartikel (refereegranskat)abstract
- BACKGROUND: Cancer is a major burden in Ethiopia. The Oncology Department of Tikur Anbessa (Black Lion) Specialized Hospital (TASH) in Addis Ababa is the country's sole specialist unit for cancer care. With only a handful of oncologists, a lack of resources, and a huge patient load, the work is challenging, especially in terms of achieving effective and ethical patient consultations. Patients, usually accompanied by family members, often wait for a long time to receive medical attention and frequently depart without treatment. Handling consultations effectively is essential in order to help patients as much as possible within such limitations. OBJECTIVE: The project addresses three main aims: (1) to enhance and expand the understanding of communicative and associated ethical challenges in Ethiopian cancer care; (2) to enhance and expand the understanding of the implications and use of person- and family-centered solutions to address such communicative challenges in practice, and (3) to plan and evaluate interventions in this area. METHODS: This project develops and consolidates a research collaboration to better understand and mitigate the communicative challenges in Ethiopian cancer care, with a focus on the handling and sharing of decision making, and ethical tensions between patients, staff, and family. Using theoretical models from linguistics, health communication, and health care ethics, multiple sources of data will be analyzed. Data sources currently include semi-structured interviews with the Ethiopian staff, patients, and family caregivers (91), survey data on cancer awareness (150) and attitudes to breaking bad news (450), and video-recordings of medical consultations (45). In addition, we will also develop clinical and methodological solutions to formulate educational interventions. RESULTS: The project was awarded funding by the Swedish Research Council in December 2017 for the period 2018-2021. The research ethics board in Sweden and in Ethiopia approved the conduct of the project in May 2018. The results from the studies will be published in 2020 and 2021. CONCLUSIONS: The project is a first step towards producing unique and seminal knowledge for the specific context of Ethiopia in the area of physician-patient communication research and ethics. It contributes to an understanding of the complexity around the role of family and ethical challenges in relation to patient involvement and decision making in Ethiopia. Improved knowledge in this area can provide a fundamental model for ways to improve cancer care in many other low resource settings in Africa and the Middle East, which share central cultural prerequisites (such as a strong patriarchal family structure, combined with strong and devout religiosity). The project will also serve to develop greater understanding about current challenges in Western health systems associated with greater family and patient participation in decision making. In addition, the project will also contribute to improving the education of Ethiopian health professionals working in cancer care by developing a training program to help them better understand and respond to identified challenges associated with communication.
|
|
| 6. |
- Rexhepi, Hanife, 1984-, et al.
(författare)
-
Online electronic healthcare records : Comparing the views of cancer patients and others
- 2020
-
Ingår i: Health Informatics Journal. - : Sage Publications. - 1460-4582 .- 1741-2811. ; 26:4, s. 2915-2929
-
Tidskriftsartikel (refereegranskat)abstract
- This study investigates differences in attitudes towards, and experiences with, online electronic health records between cancer patients and patients with other conditions, highlighting what is characteristic to cancer patients. A national patient survey on online access to electronic health records was conducted, where cancer patients were compared with all other respondents. Overall, 2587 patients completed the survey (response rate 0.61%). A total of 347 respondents (13.4%) indicated that they suffered from cancer. Results showed that cancer patients are less likely than other patients to use online electronic health records due to general interest (p < 0.001), but more likely for getting an overview of their health history (p = 0.001) and to prepare for visits (p < 0.001). Moreover, cancer patients rate benefits of accessing their electronic health records online higher than other patients and see larger positive effects regarding improved communication with and involvement in healthcare.
|
|
| 7. |
- Zhang, C., et al.
(författare)
-
The acute effect of metabolic cofactor supplementation: a potential therapeutic strategy against non-alcoholic fatty liver disease
- 2020
-
Ingår i: Molecular Systems Biology. - : EMBO. - 1744-4292. ; 16:4
-
Tidskriftsartikel (refereegranskat)abstract
- The prevalence of non-alcoholic fatty liver disease (NAFLD) continues to increase dramatically, and there is no approved medication for its treatment. Recently, we predicted the underlying molecular mechanisms involved in the progression of NAFLD using network analysis and identified metabolic cofactors that might be beneficial as supplements to decrease human liver fat. Here, we first assessed the tolerability of the combined metabolic cofactors including l-serine, N-acetyl-l-cysteine (NAC), nicotinamide riboside (NR), and l-carnitine by performing a 7-day rat toxicology study. Second, we performed a human calibration study by supplementing combined metabolic cofactors and a control study to study the kinetics of these metabolites in the plasma of healthy subjects with and without supplementation. We measured clinical parameters and observed no immediate side effects. Next, we generated plasma metabolomics and inflammatory protein markers data to reveal the acute changes associated with the supplementation of the metabolic cofactors. We also integrated metabolomics data using personalized genome-scale metabolic modeling and observed that such supplementation significantly affects the global human lipid, amino acid, and antioxidant metabolism. Finally, we predicted blood concentrations of these compounds during daily long-term supplementation by generating an ordinary differential equation model and liver concentrations of serine by generating a pharmacokinetic model and finally adjusted the doses of individual metabolic cofactors for future human clinical trials.
|
|
| 8. |
- Bryl-Górecka, Paulina, et al.
(författare)
-
Bilberry Supplementation after Myocardial Infarction Decreases Microvesicles in Blood and Affects Endothelial Vesiculation
- 2020
-
Ingår i: Molecular Nutrition & Food Research. - : Wiley-VCH Verlagsgesellschaft. - 1613-4125 .- 1613-4133. ; 64:20
-
Tidskriftsartikel (refereegranskat)abstract
- Scope: Diet rich in bilberries is considered cardioprotective, but the mechanisms of action are poorly understood. Cardiovascular disease is characterized by increased proatherogenic status and high levels of circulating microvesicles (MVs). In an open-label study patients with myocardial infarction receive an 8 week dietary supplementation with bilberry extract (BE). The effect of BE on patient MV levels and its influence on endothelial vesiculation in vitro is investigated.Methods and results: MVs are captured with acoustic trapping and platelet-derived MVs (PMVs), as well as endothelial-derived MVs (EMVs) are quantified with flow cytometry. The in vitro effect of BE on endothelial extracellular vesicle (EV) release is examined using endothelial cells and calcein staining. The mechanisms of BE influence on vesiculation pathways are studied by Western blot and qRT-PCR. Supplementation with BE decreased both PMVs and EMVs. Furthermore, BE reduced endothelial EV release, Akt phosphorylation, and vesiculation-related gene transcription. It also protects the cells from P2X(7)-induced EV release and increase in vesiculation-related gene expression.Conclusion: BE supplementation improves the MV profile in patient blood and reduces endothelial vesiculation through several molecular mechanisms related to the P2X(7)receptor. The findings provide new insight into the cardioprotective effects of bilberries.
|
|
| 9. |
- Kjeldgård, Linnea, 1985-, et al.
(författare)
-
Sequence analysis of sickness absence and disability pension in the year before and the three years following a bicycle crash; a nationwide longitudinal cohort study of 6353 injured individuals
- 2020
-
Ingår i: BMC Public Health. - : Springer Science and Business Media LLC. - 1471-2458. ; 20:1
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Bicyclists are the road user group with the highest number of severe injuries in the EU, yet little is known about sickness absence (SA) and disability pension (DP) following such injuries. Aims: To explore long-term patterns of SA and DP among injured bicyclists, and to identify characteristics associated with the specific patterns. Methods: A longitudinal register-based study was conducted, including all 6353 individuals aged 18–59 years and living in Sweden in 2009, who in 2010 had incident in-patient or specialized out-patient healthcare after a bicycle crash. Information about sociodemographic factors, the injury, SA (SA spells > 14 days), and DP was obtained from nationwide registers. Weekly SA/DP states over 1 year before through 3 years after the crash date were used in sequence and cluster analyses. Multinomial logistic regression was used to estimate odds ratios (OR) and 95% confidence intervals (CI) for factors associated with each identified sequence cluster. Results: Seven clusters were identified: “No SA or DP” (58.2% of the cohort), “Low SA or DP” (7.4%), “Immediate SA” (20.3%), “Episodic SA” (5.9%), “Long-term SA” (1.7%), “Ongoing part-time DP” (1.7%), and “Ongoing full-time DP” (4.8%). Compared to the cluster “No SA or DP”, all other clusters had higher ORs for women, and higher age. All clusters but “Low SA and DP” had higher ORs for inpatient healthcare. The cluster “Immediate SA” had a higher OR for: fractures (OR 4.3; CI 3.5–5.2), dislocation (2.8; 2.0–3.9), sprains and strains (2.0; 1.5–2.7), and internal injuries (3.0; 1.3–6.7) compared with external injuries. The cluster “Episodic SA” had higher ORs for: traumatic brain injury, not concussion (4.2; 1.1–16.1), spine and back (4.5; 2.2–9.5), torso (2.5; 1.4–4.3), upper extremities (2.9; 1.9–4.5), and lower extremities (3.5; 2.2–5.5) compared with injuries to the head, face, and neck (not traumatic brain injuries). The cluster “Long-term SA” had higher ORs for collisions with motor vehicles (1.9;1.1–3.2) and traumatic brain injury, not concussion (18.4;2.2–155.2). Conclusion: Sequence analysis enabled exploration of the large heterogeneity of SA and DP following a bicycle crash. More knowledge is needed on how to prevent bicycle crashes and especially those crashes/injuries leading to long-term consequences.
|
|
| 10. |
- Ge, Chenjie, 1991, et al.
(författare)
-
Deep semi-supervised learning for brain tumor classification
- 2020
-
Ingår i: BMC Medical Imaging. - : Springer Science and Business Media LLC. - 1471-2342. ; 20:1
-
Tidskriftsartikel (refereegranskat)abstract
- Background: This paper addresses issues of brain tumor, glioma, classification from four modalities of Magnetic Resonance Image (MRI) scans (i.e., T1 weighted MRI, T1 weighted MRI with contrast-enhanced, T2 weighted MRI and FLAIR). Currently, many available glioma datasets often contain some unlabeled brain scans, and many datasets are moderate in size. Methods: We propose to exploit deep semi-supervised learning to make full use of the unlabeled data. Deep CNN features were incorporated into a new graph-based semi-supervised learning framework for learning the labels of the unlabeled data, where a new 3D-2D consistent constraint is added to make consistent classifications for the 2D slices from the same 3D brain scan. A deep-learning classifier is then trained to classify different glioma types using both labeled and unlabeled data with estimated labels. To alleviate the overfitting caused by moderate-size datasets, synthetic MRIs generated by Generative Adversarial Networks (GANs) are added in the training of CNNs. Results: The proposed scheme has been tested on two glioma datasets, TCGA dataset for IDH-mutation prediction (molecular-based glioma subtype classification) and MICCAI dataset for glioma grading. Our results have shown good performance (with test accuracies 86.53% on TCGA dataset and 90.70% on MICCAI dataset). Conclusions: The proposed scheme is effective for glioma IDH-mutation prediction and glioma grading, and its performance is comparable to the state-of-the-art.
|
|
