Abdulla Rashdan, MD, JB, FRCPC (@RashdanAMD) header
Abdulla Rashdan, MD, JB, FRCPC (@RashdanAMD) profile picture

Radiation Oncologist with interest in patient-reported outcomes & experience measures. Health Services Research. Views are my own

Joined July 2020
Photo by Abdulla Rashdan, MD, JB, FRCPC (@RashdanAMD)Photo by Abdulla Rashdan, MD, JB, FRCPC (@RashdanAMD)Photo by Abdulla Rashdan, MD, JB, FRCPC (@RashdanAMD)Photo by Abdulla Rashdan, MD, JB, FRCPC (@RashdanAMD)
Abdulla Rashdan, MD, JB, FRCPC retweeted
Want to learn about global #radonc opportunities? Our physicist Dr. Shada Wadi-Ramahi presents at #ASTRO23 at the International Ed program. Monday 10:45-noon, Room 5. @HSkinnerMDPhD @UPMCPhysicianEd
4
9
2,469
Abdulla Rashdan, MD, JB, FRCPC retweeted
Replying to @NobelPrize
Everyone needs to also read about how @kkariko overcome many obstacles and even a DEMOTION by her university before she made her breakthrough! Never give up! Read this 40 year saga…. 👇
📍Everyone needs to read this 40-year saga of Dr Katalin Karikó, inventor of the mRNA therapy behind Pfizer/BioNTech & Moderna #COVID19 vaccines. Rejected many times, nevertheless she persisted. She will win the Nobel Prize. Oh she’s an *immigrant* too! telegraph.co.uk/global-healt…
39
233
9
982
84,151
Abdulla Rashdan, MD, JB, FRCPC retweeted
Harvard’s Dr. Rinaa Punglia shares updates on the FABREC study—#ASTRO23 #breastcancer
2
8
2,245
Abdulla Rashdan, MD, JB, FRCPC retweeted
Very interesting prospective #QOL #PRO data presented by @VedangMurthy in #bladdercancer pts undergoing RT or cystectomy 👉 good QOL 👉 no difference in urinary/bowel domains 👉 sexual bother scores better with RT #ASTRO23 #radonc @OncoAlert
1
12
24
5,284
Abdulla Rashdan, MD, JB, FRCPC retweeted
CALL FOR PAPERS: Special Section on Patient-Reported Outcomes and Informatics This special section will feature a broad range of applications of technology in the use of PROs across the key steps: deploy, collect, track, review, and document. More at thieme.de/statics/dokumente/…
3
2
5
3,235
Abdulla Rashdan, MD, JB, FRCPC retweeted
Replying to @JeffCaoMDMBA
@JeffCaoMDMBA reinforces the importance of @CROF_FCRO’s role in supporting radiation oncology. Please donate today, join the on-site fun-run and yoga session the #carocomp2023 jsm @caro_acro_ca
1
2
5
595
Abdulla Rashdan, MD, JB, FRCPC retweeted
Big data - but really really big. If you don't feel like reading the paper then listen to the podcast. Let's do a cheer. Go go go oh oh oh --- O......3! 📣😂 @AAPM @MedphysCA @caro_acro_ca @ESTRO_RT @ASTRO_org Pod at: redjournal.org/pb-assets/Hea… Article at: redjournal.org/article/S0360…
6
11
2,011
Abdulla Rashdan, MD, JB, FRCPC retweeted
Abstract titles are now available for #ASCOQLTY23! Preview the research and plan your schedule: brnw.ch/21wCLjn
1
2
6
2,415
☑️Inclusion of #PROs into therapeutic assessment was the most frequently selected priority of future initiatives Hoping that this will 💡#PROs uptake in #realworld especially if it aims to enhance efficiency of care in post-pandemic @JCOOP_ASCO @CaseyJackAllen @GreenupRachel
📖 A diverse set of stakeholders from @ALLIANCE_org ranked patient QOL as most important above all other metrics including survival. More than half felt inclusion of PROs into therapeutic assessment should be a priority ➡️ brnw.ch/21wCGWs @CaseyJackAllen @GreenupRachel
5
14
1,753
Abdulla Rashdan, MD, JB, FRCPC retweeted
PROs: Are all patients equally engaged? @laura_tennerMD & @AparGanti explore current studies that have shown there are differences in PRO results between pts of different backgrounds & discuss solutions. brnw.ch/21wCqJw #ASCODailyNews #healthequity
2
4
3,977
Abdulla Rashdan, MD, JB, FRCPC retweeted
My team and I are aggressively pursuing #BNNs We have applications for dose finding and predicting individual patient outcomes with confidence intervals If you are interested in our services, let me know ...
Bayesian Neural Networks - Capturing The Uncertainty Of The Real World Life is inherently uncertain and probabilistic, and Bayesian Neural Networks (BNNs) are designed to capture and quantify that uncertainty In many real-world applications, it's not sufficient to make a prediction; you also want to know how confident you are in that prediction. For example, in healthcare, a model that says a patient has a 70% chance of having a particular disease is less informative than one that says there's a 70% chance but with a margin of error of ±10%. BNNs are less prone to overfitting, can be more data efficient as they can incorporate priors, and can output a probability distribution for each prediction. Knowing the uncertainty or the probability that a particular prediction is accurate builds trust and confidence with business users. So how do Bayesian Networks Work? The core idea is to replace the fixed weights w in a standard neural network with probability distributions P(w) The famous equation from Bayes is: P(A|B)=P(B|A)P(A) / P(B) In the context of BNNs: A is the model parameters (weights and biases). B is the observed data. P(A∣B) is the posterior distribution of the parameters given the data. P(B∣A) is the likelihood of the data given the parameters. P(A) is the prior distribution of the parameters. P(B) is the evidence, often considered a normalizing constant. Prior Distribution - You start with a prior distribution P(w) over the weights. This represents your initial belief about the model parameters before seeing any data. Posterior Distribution - The goal is to compute the posterior distribution P(w∣D), which represents the updated belief about the weights after observing data D. Bayes theorem along with some approximation methods are used to calculate this distribution. Prediction - Finally, to make a prediction for a new input x, you average over all possible weights, weighted by their posterior probabilities: P(y∣x,D)=∫P(y∣x,w)×P(w∣D)dw This gives you not just a point estimate but a distribution over the possible outputs y, capturing the model's uncertainty. For example: BNNs can be applied to a dataset of MRI scans where each scan is labeled either "Cancer" or "No Cancer." The goal is to build a model that can predict these labels for new, unlabeled MRI scans. A BNN can say, "I'm 80% sure this is cancer, but there's a 20% chance it's not," which is valuable information for clinicians. BNNs are useful wherever uncertainty quantification is important including disease diagnosis, risk assessment, energy forecasting, and real-time decision-making
1
5
13
7,802
Abdulla Rashdan, MD, JB, FRCPC retweeted
#IPOS2023 Mona Magalhaes presented the adaption of @eIMPAQc 🇨🇦for people living with lung cancer #lcsm. Great qual work describing the exact value of symptom to patients/ carers. – at Milan, Lombardy
6
10
823
Abdulla Rashdan, MD, JB, FRCPC retweeted
#IPOS2023 @CG_MazJo using 👩‍🍳 metaphors to describe the ‘active ingredients’ needed to successfully implement #PROs in 🇨🇦. Lots of lessons for us in 🇦🇺! #impsci – at Milan, Lombardy
5
9
742
Abdulla Rashdan, MD, JB, FRCPC retweeted
3
7
4
74
11,941
Abdulla Rashdan, MD, JB, FRCPC retweeted
PRO with combined EBRT plus brachy and spacer ⁦@AmarUKishan⁩ ⁦@KamravaMD⁩ #pcsm ⁦@AndrewKellerMD⁩ sciencedirect.com/science/ar…
1
4
12
1,542
Abdulla Rashdan, MD, JB, FRCPC retweeted
Out now in @JAMAOnc, our viewpoint arguing for better evidence supporting new technologies in RT. The proton ship has sailed (in US), but we have window of opportunity to do the right studies for more recently debuted tech: adaptive RT, MR guided, etc jamanetwork.com/journals/jam…
4
34
7
130
45,407
Don’t miss out on a one-of-a-kind program at the #PCORI23 Annual Meeting Register for free today: pcori.me/3DsgtpV The second keynote session features healthcare research leaders Nakela L. Cook, M.D., MPH, and Vivian W. Pinn, M.D., for a deep dive into the past, present and future of healthcare research.
1
1
5
674
Abdulla Rashdan, MD, JB, FRCPC retweeted
I wonder whether any PROMS or PREMS are part of this story ? @AriErcole HT @open_Outcomes @Outcomes_PROMs @NetworkProms
1
2
7
767