LIVIVO - Search results -

Search results

Result 1 - 10 of total 152

Search options

Article ; Online: Infusing behavior science into large language models for activity coaching.

Hegde, Narayan / Vardhan, Madhurima / Nathani, Deepak / Rosenzweig, Emily / Speed, Cathy / Karthikesalingam, Alan / Seneviratne, Martin

PLOS digital health

2024 Volume 3, Issue 4, Page(s) e0000431

Abstract: Large language models (LLMs) have shown promise for task-oriented dialogue across a range of domains. The use of LLMs in health and fitness coaching is under-explored. Behavior science frameworks such as COM-B, which conceptualizes behavior change in ... ...

Abstract	Large language models (LLMs) have shown promise for task-oriented dialogue across a range of domains. The use of LLMs in health and fitness coaching is under-explored. Behavior science frameworks such as COM-B, which conceptualizes behavior change in terms of capability (C), Opportunity (O) and Motivation (M), can be used to architect coaching interventions in a way that promotes sustained change. Here we aim to incorporate behavior science principles into an LLM using two knowledge infusion techniques: coach message priming (where exemplar coach responses are provided as context to the LLM), and dialogue re-ranking (where the COM-B category of the LLM output is matched to the inferred user need). Simulated conversations were conducted between the primed or unprimed LLM and a member of the research team, and then evaluated by 8 human raters. Ratings for the primed conversations were significantly higher in terms of empathy and actionability. The same raters also compared a single response generated by the unprimed, primed and re-ranked models, finding a significant uplift in actionability and empathy from the re-ranking technique. This is a proof of concept of how behavior science frameworks can be infused into automated conversational agents for a more principled coaching experience.
Language	English
Publishing date	2024-04-02
Publishing country	United States
Document type	Journal Article
ISSN	2767-3170
ISSN (online)	2767-3170
DOI	10.1371/journal.pdig.0000431
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

This service is chargeable due to the Delivery terms set by subito. Orders including an article and supplementary material will be classified as separate orders. In these cases, fees will be demanded for each order.

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article ; Online: Detecting shortcut learning for fair medical AI using shortcut testing.

Brown, Alexander / Tomasev, Nenad / Freyberg, Jan / Liu, Yuan / Karthikesalingam, Alan / Schrouff, Jessica

Nature communications

2023 Volume 14, Issue 1, Page(s) 4314

Abstract: Machine learning (ML) holds great promise for improving healthcare, but it is critical to ensure that its use will not propagate or amplify health disparities. An important step is to characterize the (un)fairness of ML models-their tendency to perform ... ...

Abstract	Machine learning (ML) holds great promise for improving healthcare, but it is critical to ensure that its use will not propagate or amplify health disparities. An important step is to characterize the (un)fairness of ML models-their tendency to perform differently across subgroups of the population-and to understand its underlying mechanisms. One potential driver of algorithmic unfairness, shortcut learning, arises when ML models base predictions on improper correlations in the training data. Diagnosing this phenomenon is difficult as sensitive attributes may be causally linked with disease. Using multitask learning, we propose a method to directly test for the presence of shortcut learning in clinical ML systems and demonstrate its application to clinical tasks in radiology and dermatology. Finally, our approach reveals instances when shortcutting is not responsible for unfairness, highlighting the need for a holistic approach to fairness mitigation in medical AI.
MeSH term(s)	Health Facilities ; Machine Learning
Language	English
Publishing date	2023-07-18
Publishing country	England
Document type	Journal Article ; Research Support, Non-U.S. Gov't
ZDB-ID	2553671-0
ISSN	2041-1723 ; 2041-1723
ISSN (online)	2041-1723
ISSN	2041-1723
DOI	10.1038/s41467-023-39902-7
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Article ; Online: Measure by measure: Resting heart rate across the 24-hour cycle.

Speed, Cathy / Arneil, Thomas / Harle, Robert / Wilson, Alex / Karthikesalingam, Alan / McConnell, Michael / Phillips, Justin

PLOS digital health

2023 Volume 2, Issue 4, Page(s) e0000236

Abstract: Background: Photoplethysmography (PPG) sensors, typically found in wrist-worn devices, can continuously monitor heart rate (HR) in large populations in real-world settings. Resting heart rate (RHR) is an important biomarker of morbidities and mortality, ...

Abstract	Background: Photoplethysmography (PPG) sensors, typically found in wrist-worn devices, can continuously monitor heart rate (HR) in large populations in real-world settings. Resting heart rate (RHR) is an important biomarker of morbidities and mortality, but no universally accepted definition nor measurement criteria exist. In this study, we provide a working definition of RHR and describe a method for accurate measurement of this biomarker, recorded using PPG derived from wristband measurement across the 24-hour cycle. Methods: 433 healthy subjects wore a wrist device that measured activity and HR for up to 3 months. HR during inactivity was recorded and the duration of inactivity needed for HR to stabilise was ascertained. We identified the lowest HR during each 24-hour cycle (true RHR) and examined the time of day or night this occurred. The variation of HR during inactivity through the 24-hour cycle was also assessed. The sample was also subdivided according to daily activity levels for subset analysis. Findings: Adequate data was obtained for 19,242 days and 18,520 nights. HR stabilised in most subjects after 4 minutes of inactivity. Mean (SD) RHR for the sample was 54.5 (8.0) bpm (day) and 50.5 (7.6) bpm (night). RHR values were highest in the least active group (lowest MET quartile). A circadian variation of HR during inactivity was confirmed, with the lowest values being between 0300 and 0700 hours for most subjects. Interpretation: RHR measured using a PPG-based wrist-worn device is significantly lower at night than in the day, and a circadian rhythm of HR during inactivity was confirmed. Since RHR is such an important health metric, clarity on the definition and measurement methodology used is important. For most subjects, a minimum rest time of 4 minutes provides a reliable measurement of HR during inactivity and true RHR in a 24-hour cycle is best measured between 0300 and 0700 hours. Funding: This study was funded by Google.
Language	English
Publishing date	2023-04-28
Publishing country	United States
Document type	Journal Article
ISSN	2767-3170
ISSN (online)	2767-3170
DOI	10.1371/journal.pdig.0000236
Database	MEDical Literature Analysis and Retrieval System OnLINE

Order via subito

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article ; Online: Type II endoleaks: when and how.

Grima, Matthew J / Karthikesalingam, Alan

The Journal of cardiovascular surgery

2017 Volume 58, Issue 6, Page(s) 889–894

Abstract: Although most type II endoleaks are self-limiting, the most common indication for secondary intervention after endovascular aneurysm repair (EVAR) is type II endoleak. However, it is still debatable when to treat them. Furthermore, different intervention ...

Abstract	Although most type II endoleaks are self-limiting, the most common indication for secondary intervention after endovascular aneurysm repair (EVAR) is type II endoleak. However, it is still debatable when to treat them. Furthermore, different intervention techniques are available to treat type II endoleaks. The aim of this review is to look at current evidence and updates on type II endoleaks after EVAR for abdominal aortic aneurysm and their management.
MeSH term(s)	Aortic Aneurysm, Abdominal/diagnostic imaging ; Aortic Aneurysm, Abdominal/epidemiology ; Aortic Aneurysm, Abdominal/surgery ; Blood Vessel Prosthesis Implantation/adverse effects ; Endoleak/diagnostic imaging ; Endoleak/epidemiology ; Endoleak/therapy ; Endovascular Procedures/adverse effects ; Humans ; Predictive Value of Tests ; Risk Factors ; Treatment Outcome
Language	English
Publishing date	2017-12
Publishing country	Italy
Document type	Journal Article ; Review
ZDB-ID	80143-4
ISSN	1827-191X ; 0021-9509
ISSN (online)	1827-191X
ISSN	0021-9509
DOI	10.23736/S0021-9509.17.10072-8
Database	MEDical Literature Analysis and Retrieval System OnLINE

In stock of ZB MED Cologne/Königswinter

Zs.A 469: Show issues

Location:
Je nach Verfügbarkeit (siehe Angabe bei Bestand)
bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular
Jg. 1995 - 2021: Lesesall (1.OG)
ab Jg. 2022: Lesesaal (EG)

Order via subito

Details ▾
- See ZB MED holdings
- Order with fees

Article ; Online: Generative models improve fairness of medical classifiers under distribution shifts.

Ktena, Ira / Wiles, Olivia / Albuquerque, Isabela / Rebuffi, Sylvestre-Alvise / Tanno, Ryutaro / Roy, Abhijit Guha / Azizi, Shekoofeh / Belgrave, Danielle / Kohli, Pushmeet / Cemgil, Taylan / Karthikesalingam, Alan / Gowal, Sven

Nature medicine

2024 Volume 30, Issue 4, Page(s) 1166–1173

Abstract: Domain generalization is a ubiquitous challenge for machine learning in healthcare. Model performance in real-world conditions might be lower than expected because of discrepancies between the data encountered during deployment and development. ... ...

Abstract	Domain generalization is a ubiquitous challenge for machine learning in healthcare. Model performance in real-world conditions might be lower than expected because of discrepancies between the data encountered during deployment and development. Underrepresentation of some groups or conditions during model development is a common cause of this phenomenon. This challenge is often not readily addressed by targeted data acquisition and 'labeling' by expert clinicians, which can be prohibitively expensive or practically impossible because of the rarity of conditions or the available clinical expertise. We hypothesize that advances in generative artificial intelligence can help mitigate this unmet need in a steerable fashion, enriching our training dataset with synthetic examples that address shortfalls of underrepresented conditions or subgroups. We show that diffusion models can automatically learn realistic augmentations from data in a label-efficient manner. We demonstrate that learned augmentations make models more robust and statistically fair in-distribution and out of distribution. To evaluate the generality of our approach, we studied three distinct medical imaging contexts of varying difficulty: (1) histopathology, (2) chest X-ray and (3) dermatology images. Complementing real samples with synthetic ones improved the robustness of models in all three medical tasks and increased fairness by improving the accuracy of clinical diagnosis within underrepresented groups, especially out of distribution.
MeSH term(s)	Artificial Intelligence ; Machine Learning
Language	English
Publishing date	2024-04-10
Publishing country	United States
Document type	Journal Article
ZDB-ID	1220066-9
ISSN	1546-170X ; 1078-8956
ISSN (online)	1546-170X
ISSN	1078-8956
DOI	10.1038/s41591-024-02838-6
Database	MEDical Literature Analysis and Retrieval System OnLINE

In stock of ZB MED Cologne/Königswinter

Zs.A 4212: Show issues			Location: Je nach Verfügbarkeit (siehe Angabe bei Bestand) bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular Jg. 1995 - 2021: Lesesall (2.OG) ab Jg. 2022: Lesesaal (EG)
Zs.MG 39: Show issues

Order via subito

Details ▾
- See ZB MED holdings
- Order with fees

Article ; Online: Developing Specific Reporting Standards in Artificial Intelligence Centred Research.

Sounderajah, Viknesh / Ashrafian, Hutan / Karthikesalingam, Alan / Markar, Sheraz R / Normahani, Pasha / Collins, Gary S / Bossuyt, Patrick M / Darzi, Ara

Annals of surgery

2022 Volume 275, Issue 3, Page(s) e547–e548

MeSH term(s)	Artificial Intelligence ; Biomedical Research ; Research Design/standards
Language	English
Publishing date	2022-01-06
Publishing country	United States
Document type	Journal Article
ZDB-ID	340-2
ISSN	1528-1140 ; 0003-4932
ISSN (online)	1528-1140
ISSN	0003-4932
DOI	10.1097/SLA.0000000000005294
Database	MEDical Literature Analysis and Retrieval System OnLINE

In stock of ZB MED Cologne/Königswinter

Uk I Zs.35/1: Show issues

Location:
Je nach Verfügbarkeit (siehe Angabe bei Bestand)
bis Jg. 2021: Bestellungen von Artikeln über das Online-Bestellformular
ab Jg. 2022: Lesesaal (EG)

Order via subito

Details ▾
- See ZB MED holdings
- Order with fees

Article ; Online: Multicentre Post-EVAR Surveillance Evaluation Study (EVAR-SCREEN).

Grima, Matthew J / Karthikesalingam, Alan / Holt, Peter J

European journal of vascular and endovascular surgery : the official journal of the European Society for Vascular Surgery

2019 Volume 57, Issue 4, Page(s) 521–526

Abstract: Objective: Surveillance imaging is considered mandatory after endovascular aneurysm repair (EVAR), but many patients are lost to follow up and the impact of this is poorly understood. This study aimed to examine compliance with post-operative ... ...

Abstract	Objective: Surveillance imaging is considered mandatory after endovascular aneurysm repair (EVAR), but many patients are lost to follow up and the impact of this is poorly understood. This study aimed to examine compliance with post-operative surveillance in the UK and the impact of mal-/non-compliance on endograft re-interventions and survival. Methods: EVAR-SCREEN centres reported EVAR for intact infrarenal abdominal aortic aneurysms (AAA) from 1 January 2007 to 31 December 2010, with follow up included up to 31 July 2014. Non-compliance was defined by the presence of a single 18 month period in which no surveillance imaging was performed. The outcomes were reported in compliant and non-compliant groups with survival analysis. Results: EVAR was performed in 1414 patients in 10 UK centres. At the end of the study period there were 378 patients with five years of follow up available for analysis. Compliance with surveillance was 66% (61-68%). Compliance varied widely, from 9% to 88% between centres. Age (hazard ratio [HR] 1.03, 95% confidence interval [CI] 1.01-1.05; p = .02) and distance from hospital (HR 1.01, 95% CI 1.00-1.01; p < .001) were independent predictors of non-compliance. Non-compliant patients had lower all cause mortality in the first three years after EVAR, whereas compliant patients had lower all cause mortality 4-5 years after EVAR (p < .001). No significant difference in re-intervention rates was found between compliant and non-compliant patients. Conclusion: A substantial proportion of patients were non-compliant with surveillance after EVAR in the UK with considerable variation between centres. The survival benefit for EVAR after three years appeared to be related to compliance with surveillance which has implications for the future delivery of EVAR.
MeSH term(s)	Aged ; Aged, 80 and over ; Aortic Aneurysm, Abdominal/diagnostic imaging ; Aortic Aneurysm, Abdominal/mortality ; Aortic Aneurysm, Abdominal/surgery ; Aortography/methods ; Blood Vessel Prosthesis ; Blood Vessel Prosthesis Implantation/adverse effects ; Blood Vessel Prosthesis Implantation/instrumentation ; Blood Vessel Prosthesis Implantation/mortality ; Computed Tomography Angiography ; Endovascular Procedures/adverse effects ; Endovascular Procedures/instrumentation ; Endovascular Procedures/mortality ; Female ; Humans ; Male ; Patient Compliance ; Population Surveillance ; Postoperative Complications/diagnostic imaging ; Postoperative Complications/mortality ; Postoperative Complications/surgery ; Predictive Value of Tests ; Prosthesis Design ; Reoperation ; Retrospective Studies ; Risk Factors ; Time Factors ; Treatment Outcome ; Ultrasonography, Doppler, Duplex ; United Kingdom
Language	English
Publishing date	2019-02-06
Publishing country	England
Document type	Comparative Study ; Journal Article ; Multicenter Study ; Observational Study ; Research Support, Non-U.S. Gov't
ZDB-ID	1225869-6
ISSN	1532-2165 ; 1078-5884
ISSN (online)	1532-2165
ISSN	1078-5884
DOI	10.1016/j.ejvs.2018.10.032
Database	MEDical Literature Analysis and Retrieval System OnLINE

In stock of ZB MED Cologne/Königswinter

Zs.A 2283: Show issues			Location: Je nach Verfügbarkeit (siehe Angabe bei Bestand) bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular Jg. 1995 - 2021: Lesesall (2.OG) ab Jg. 2022: Lesesaal (EG)
Zs.MO 381: Show issues

Order via subito

Details ▾
- See ZB MED holdings
- Order with fees

Article ; Online: Benefits and pitfalls of national mortality audits.

Karthikesalingam, Alan / Holt, Peter J

ANZ journal of surgery

2014 Volume 84, Issue 9, Page(s) 601–602

MeSH term(s)	Delayed Diagnosis/statistics & numerical data ; Female ; Humans ; Intraoperative Complications/mortality ; Male ; Medical Audit ; Postoperative Complications/mortality ; Surgical Procedures, Operative/mortality
Language	English
Publishing date	2014-08-26
Publishing country	Australia
Document type	Editorial ; Comment
ZDB-ID	2050749-5
ISSN	1445-2197 ; 1445-1433 ; 0004-8682
ISSN (online)	1445-2197
ISSN	1445-1433 ; 0004-8682
DOI	10.1111/ans.12656
Database	MEDical Literature Analysis and Retrieval System OnLINE

In stock of ZB MED Cologne/Königswinter

Zs.A 180: Show issues

Location:
Je nach Verfügbarkeit (siehe Angabe bei Bestand)
bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular
Jg. 1995 - 2021: Lesesall (1.OG)
ab Jg. 2022: Lesesaal (EG)

Order via subito

Details ▾
- See ZB MED holdings
- Order with fees

Book ; Online: Detecting Shortcut Learning for Fair Medical AI using Shortcut Testing

Brown, Alexander / Tomasev, Nenad / Freyberg, Jan / Liu, Yuan / Karthikesalingam, Alan / Schrouff, Jessica

2022

Abstract	Machine learning (ML) holds great promise for improving healthcare, but it is critical to ensure that its use will not propagate or amplify health disparities. An important step is to characterize the (un)fairness of ML models - their tendency to perform differently across subgroups of the population - and to understand its underlying mechanisms. One potential driver of algorithmic unfairness, shortcut learning, arises when ML models base predictions on improper correlations in the training data. However, diagnosing this phenomenon is difficult, especially when sensitive attributes are causally linked with disease. Using multi-task learning, we propose the first method to assess and mitigate shortcut learning as a part of the fairness assessment of clinical ML systems, and demonstrate its application to clinical tasks in radiology and dermatology. Finally, our approach reveals instances when shortcutting is not responsible for unfairness, highlighting the need for a holistic approach to fairness mitigation in medical AI.
Keywords	Computer Science - Machine Learning
Subject code	006
Publishing date	2022-07-21
Publishing country	us
Document type	Book ; Online
Database	BASE - Bielefeld Academic Search Engine (life sciences selection)

Full text online

Full text

Inter-library loan at ZB MED

Your chosen title can be delivered directly to ZB MED Cologne location if you are registered as a user at ZB MED Cologne.

Article ; Online: Re: evaluating the value and impact of the Victorian Audit of Surgical Mortality.

Karthikesalingam, Alan / Holt, Peter James

ANZ journal of surgery

2013 Volume 83, Issue 10, Page(s) 728–729

MeSH term(s)	Humans ; Medical Audit ; Surgical Procedures, Operative/mortality
Language	English
Publishing date	2013-10-07
Publishing country	Australia
Document type	Letter ; Comment
ZDB-ID	2050749-5
ISSN	1445-2197 ; 1445-1433 ; 0004-8682
ISSN (online)	1445-2197
ISSN	1445-1433 ; 0004-8682
DOI	10.1111/ans.12348
Database	MEDical Literature Analysis and Retrieval System OnLINE

In stock of ZB MED Cologne/Königswinter

Zs.A 180: Show issues

Location:
Je nach Verfügbarkeit (siehe Angabe bei Bestand)
bis Jg. 1994: Bestellungen von Artikeln über das Online-Bestellformular
Jg. 1995 - 2021: Lesesall (1.OG)
ab Jg. 2022: Lesesaal (EG)

Order via subito

Details ▾
- See ZB MED holdings
- Order with fees

To top

More links

Kategorien

Order via subito

Inter-library loan at ZB MED

More links

Kategorien

Order via subito

More links

Kategorien

Order via subito

Inter-library loan at ZB MED

More links

Kategorien

In stock of ZB MED Cologne/Königswinter

Order via subito

More links

Kategorien

In stock of ZB MED Cologne/Königswinter

Order via subito

More links

Kategorien

In stock of ZB MED Cologne/Königswinter

Order via subito

More links

Kategorien

In stock of ZB MED Cologne/Königswinter

Order via subito

More links

Kategorien

In stock of ZB MED Cologne/Königswinter

Order via subito

Full text online

More links

Kategorien

Inter-library loan at ZB MED

More links

Kategorien

In stock of ZB MED Cologne/Königswinter

Order via subito