Brain & Behaviour Lab is a borderless-lab @ImperialCollege & @unibt, Director: Prof. Aldo Faisal @AnalogAldo. Account co-managed by @ali_shafti & @analogaldo
Joined December 2012
- Tweets 638
- Following 254
- Followers 1,475
- Likes 195
203 Photos and videos
FaisalLab retweeted
22 Mar 2023
Delighted to co-lead today’s @reformthintank roundtable discussion on how smart use #healthcare #wearable data & #AI can transform public health & care @ai4healthcentre @FaisalLab reform.uk/event/the-power-of…
3
3
1,824
22 Jan 2023
DISCLAIMER: We have prior to publication patented the pipeline, the movement fingerprint features, the sensor placements & the biomarker discovery process of the AI, patents.google.com/patent/CA…
22 Jan 2023
THANKS: This would have not been possible as a team effort, with fantastic PostDoc, PhDs, and close collaborators in neurology, paediatrics, physiotherapy, genetics. Not fundable without our funders (BRCs, DRF, UKRI, MRC, EPSRC) and last but not least our wonderful patients!
1
1
1,144
22 Jan 2023
THANKS: This would have not been possible as a team effort, with fantastic PostDoc, PhDs, and close collaborators in neurology, paediatrics, physiotherapy, genetics. Not fundable without our funders (BRCs, DRF, UKRI, MRC, EPSRC) and last but not least our wonderful patients!
22 Jan 2023
BONUS 4/4: A holistic picture of health, requires the complete study of human behaviour, movement behaviour is the ultimate phenotype, it is the sole driver of evolutionary fitness of biological mechanisms (and their disease failures). This is Ethology Omics = #Ethomics
1
2,245
22 Jan 2023
BONUS 4/4: A holistic picture of health, requires the complete study of human behaviour, movement behaviour is the ultimate phenotype, it is the sole driver of evolutionary fitness of biological mechanisms (and their disease failures). This is Ethology Omics = #Ethomics
22 Jan 2023
BONUS 3/4 We can measure gene expression rates from the behavioural fingerprints alone (no biosamples needed, left) VS best ML model using “gold”standard showed correlation with gene expression (right). This result kicks-off what we call #behavioral #transcriptomics
2
1,174
22 Jan 2023
BONUS 3/4 We can measure gene expression rates from the behavioural fingerprints alone (no biosamples needed, left) VS best ML model using “gold”standard showed correlation with gene expression (right). This result kicks-off what we call #behavioral #transcriptomics
22 Jan 2023
BONUS 2/4: Our approach works both with natural behaviour data, e.g. when patients were eating or in playroom as well as during clinical assessments. This may be the start of a universal approach to disease monitoring in general, especially outside the clinic in our daily lives.
1
1,068
22 Jan 2023
BONUS 2/4: Our approach works both with natural behaviour data, e.g. when patients were eating or in playroom as well as during clinical assessments. This may be the start of a universal approach to disease monitoring in general, especially outside the clinic in our daily lives.
22 Jan 2023
BONUS 1/3: 1. Our full-body behaviour fingerprints are not affected by patients loosing the ability to walk (unlike the need for 2 “gold”standard markers before/after). 2. Our is not confused by aging (DMD “gold”standard goes up&down as child grows paralysed), our’s only progress
1
913
22 Jan 2023
BONUS 1/3: 1. Our full-body behaviour fingerprints are not affected by patients loosing the ability to walk (unlike the need for 2 “gold”standard markers before/after). 2. Our is not confused by aging (DMD “gold”standard goes up&down as child grows paralysed), our’s only progress
22 Jan 2023
With the vast majority of drugs & treatments not making it to market & failing in the 3 clinical trial stages, our view is to be hollistic about patient capabilities. This allows for shorter, smaller & less risky trials, making treatment development viable for #neglected#diseases
1
595
22 Jan 2023
With the vast majority of drugs & treatments not making it to market & failing in the 3 clinical trial stages, our view is to be hollistic about patient capabilities. This allows for shorter, smaller & less risky trials, making treatment development viable for #neglected#diseases
22 Jan 2023
What does this mean: First of all,we basically showed how poor established gold-standard clinical behavioural/observational assessments operate when compared to AI derived biomarkers. The gold-standard ain’t so golden, yet they are used as primary endpoints in drug development.
1
2
548
22 Jan 2023
What does this mean: First of all,we basically showed how poor established gold-standard clinical behavioural/observational assessments operate when compared to AI derived biomarkers. The gold-standard ain’t so golden, yet they are used as primary endpoints in drug development.
22 Jan 2023
We used much larger clinical trial data (big thanks EFACTS & Gemelli) to boost prediction of clinical scores from clinical scores. Still our method performed far better at predicting future clinical scores & used at equal precision far fewer patients: FA 7 vs 160 & DMD 9 vs 50
1
1
515
22 Jan 2023
We used much larger clinical trial data (big thanks EFACTS & Gemelli) to boost prediction of clinical scores from clinical scores. Still our method performed far better at predicting future clinical scores & used at equal precision far fewer patients: FA 7 vs 160 & DMD 9 vs 50
22 Jan 2023
Predicting gold-standard clinical scales is ceiling limited by the quality of the traditional “gold”-standard itself. So, we showed that we could predict disease progression 6-12 months into the future for every individual patients, unlike the gold-standard itself … 8/10
1
1
588
22 Jan 2023
Predicting gold-standard clinical scales is ceiling limited by the quality of the traditional “gold”-standard itself. So, we showed that we could predict disease progression 6-12 months into the future for every individual patients, unlike the gold-standard itself … 8/10
22 Jan 2023
7/10 In both diseases we were able to reconstruct cross-sectionally the whole range of “gold”-standard clinical scales, i.e. movement data from the same day as the assessment predicted the clinical scale without requiring an expert clinical observer rating the patient by-eye…
1
1
612
22 Jan 2023
7/10 In both diseases we were able to reconstruct cross-sectionally the whole range of “gold”-standard clinical scales, i.e. movement data from the same day as the assessment predicted the clinical scale without requiring an expert clinical observer rating the patient by-eye…
22 Jan 2023
6/10 From our previous work on capturing real-world motor behaviour in 100s of volunteers we identified sets of digital behaviour fingerprints that characterise human movements. Thus, one pipeline analysed clinical assessment & natural human behaviour in 2 very different diseases
1
1
566
22 Jan 2023
6/10 From our previous work on capturing real-world motor behaviour in 100s of volunteers we identified sets of digital behaviour fingerprints that characterise human movements. Thus, one pipeline analysed clinical assessment & natural human behaviour in 2 very different diseases
22 Jan 2023
5/10 In both papers we did longitudinal natural history studies with patients drawn from range of disease progression states of FA & DMD. Among other things we measured full-body movement data & clinical assessments (ie “gold”-standard measures) @ trial start, middle & end.
1
1
503
22 Jan 2023
5/10 In both papers we did longitudinal natural history studies with patients drawn from range of disease progression states of FA & DMD. Among other things we measured full-body movement data & clinical assessments (ie “gold”-standard measures) @ trial start, middle & end.
22 Jan 2023
3/10 In the 1st @NatureMedicine paper doi.org/10.1038/s41591-022-0… we focus on FA, which has a gene disfunction that results in impaired mitochondrial function, results in motor & heart dysfunction.
1
4
1,053
22 Jan 2023
4/10 In the 2nd @NatureMedicine paper we work with children that have #DuchenneMuscularDystrophy, where muscle loss leads to increasing stiffness & paralysis, here in a cohort with & without loss ambulation doi.org/10.1038/s41591-022-0…
22 Jan 2023
3/10 In the 1st @NatureMedicine paper doi.org/10.1038/s41591-022-0… we focus on FA, which has a gene disfunction that results in impaired mitochondrial function, results in motor & heart dysfunction.
1
2
228
22 Jan 2023
3/10 In the 1st @NatureMedicine paper doi.org/10.1038/s41591-022-0… we focus on FA, which has a gene disfunction that results in impaired mitochondrial function, results in motor & heart dysfunction.
22 Jan 2023
We focus on two very different rare, degenerative, genetic diseases that affect movement & eventually lead to paralysis & death. There are currently no cures for either disease, the practical benefit is to lower risk, cost, patients needed & duration of drug trials.
2/10
1
1
1,356
22 Jan 2023
We focus on two very different rare, degenerative, genetic diseases that affect movement & eventually lead to paralysis & death. There are currently no cures for either disease, the practical benefit is to lower risk, cost, patients needed & duration of drug trials.
2/10
22 Jan 2023
Delighted to announce our #two @NatureMedicine papers have finally come out & received an exclusive #BBC TV radio. We show how one #AI #BehaviorAnalytics framework works out-of-the-box for two very different diseases: #FriedreichsAtaxia (FA) and #DuchenneMuscularDystrophy 1/10
1
1
629
22 Jan 2023
Delighted to announce our #two @NatureMedicine papers have finally come out & received an exclusive #BBC TV radio. We show how one #AI #BehaviorAnalytics framework works out-of-the-box for two very different diseases: #FriedreichsAtaxia (FA) and #DuchenneMuscularDystrophy 1/10
3
7
1,262
FaisalLab retweeted
22 Jan 2023
Read our own news story here 👇
imperial.ac.uk/news/242711/w…
6
11
4,035
FaisalLab retweeted
22 Jan 2023
With huge thanks also to @UKRI_News, @AtaxiaUK, @ucl, @uclh, @GreatOrmondSt and @BBCPallab for pioneering and supporting this exciting advancement in wearable tech and healthcare.
ALT Pallab Ghosh speaking on BBC Breakfast from the Imperial Data Science Institute, text on screen says "15 patients in 6 months".
2
6
14
7,585