Zafar Iqbal

Subject Matter Expert (EMR, RIS/PACS, HL7). More than 10 years of healthcare IT experience. 3D Printing & ML is future.

[Vish Rao @VishRao5]

@natBME 📄 Paper (open access): https://t.co/rfSKrnMOmr
💻 Code: https://t.co/BoXWJmGWOK
📰 Harvard Medical School story: https://t.co/QgIBRd8kGT

[Vish Rao @VishRao5]

Medical AI is built for adults, and newborns are left behind.

Out today in Nature Biomedical Engineering (@natBME): we took an AI model built to check breathing tube placement on adult X-rays and adapted it for newborns by sending it to 30 NICUs in 20 countries and territories. Learning from just 50 X-rays at each, it pinpointed the tube tip and the base of the windpipe more accurately than hospitals' own models at 29 of 30 sites, even at hospitals it had never trained on.

Why it matters: only 17% of FDA-authorized AI medical devices are labeled for use in children, largely because pediatric data is scarce and hard to share. Out of the box, the adult model misplaced the tube tip on newborn X-rays by more than 5 cm, about the length of a newborn's windpipe, in 37% of cases.

So instead of pooling data, the model travels: it's fine-tuned on 50 X-rays at one hospital, then passed to the next. We simulated this using real X-rays from 30 NICUs, an approach designed so patient data never has to leave a hospital.

Across 30 NICUs:
• Large errors (over 5 cm) fell from 37% to 2.6%
• Better at flagging dangerously deep breathing tubes at 27 of 30 sites
• Gains grew with every hospital added, with no plateau

It's been surreal working with such a diverse global team. My goal is closing the gap between AI development and real impact for patients. This is one step: it removes a major feasibility barrier, scarce and siloed pediatric data, and could help open the door to a new generation of pediatric AI.

Paper, code and figures below 👇

Grateful to @pranavrajpurkar, @emma_ychen and our team of 75 researchers across 20 countries and territories (full team below)

@harvardmed @PennMedicine @BrighamWomens @StanfordMed @GreatOrmondSt @KU_Leuven @UAlberta @UniklinikEssen @TelAvivUni @OsakaMetUniv_en @AUB_Lebanon @AUBMC_Official @SidraMedicine @ChildrensColo @SLU_Official @Newark_Beth @MedUnivSC

[Zafar Iqbal @zafarology]

"Manual result entry from lab instruments into software remains the primary source of report transcription errors, delayed sample turnaround times, and audit trail gaps."

#LIMS #LabCare #PathologyResearch #HealthTech #LaboratoryAutomation #eCareSolutions #HL7 #ASTM

[Zafar Iqbal @zafarology]

@AlrayyanTV Amazing

[قناة الريان الفضائية @AlrayyanTV]

🎥 تقرير | اعتمدت سدرة للطب، عضو مؤسسة قطر، مؤخرًا أداة جديدة تعمل بالذكاء الاصطناعي ضمن قسم الطوارئ ووحدة التصوير التشخيصي، بهدف دعم الأطباء في اكتشاف الكسور والخلوع في صور الأشعة للأطفال.

#برنامج_تراحيب | #قناة_الريان | #قطر

[HIMSS @HIMSS]

Join us in Dubai on 25 April to meet regional experts & gain insights into Middle East Health. Network with 200+ healthcare leaders and delve into topics like generative AI, genome and precision medicine, and digital tools' impact.

Register here: https://t.co/VScGvHBAx2

[HIMSS @HIMSS]

The past 3 days were a wild ride. #HIMSS23Europe, you blew our minds and put them back together. 🤯🧠

Shout-out to everyone who tuned in on social, too. You might not have been here IRL this time, but #HIMSS24Europe is coming to Rome! 📅 Mark your calendars for 29-31 May 2024.

[Yahoo Finance @YahooFinance]

If you want to invest like Warren Buffett keep these 3 things in mind:
1. Focus on the long-term
2. Buy what you know
3. It's okay if you miss sometimes

[World of Statistics @stats_feed]

Age when their business started:

🇺🇸 Bill Gates (Microsoft) - 19
🇺🇸 Mark Zuckerberg (Facebook) - 19
🇺🇸 Walt Disney (Disney) - 21
🇺🇸 Steve Jobs (Apple) - 21
🇮🇳 Ritesh Agarwal (OYO) - 22
🇺🇸 Bill Clerico (WePay) - 22
🇺🇸 Jack Dorsey (Twitter) - 23
🇺🇸 Larry Page (Google) - 25
🇺🇸 Sergey Brin (Google) - 25
🇮🇳 Dhirajlal Ambani (Reliance) - 25
🇨🇳 Jack Ma (Alibaba) - 29
🇺🇸 Elon Musk (SpaceX) - 30
🇺🇸 Jeff Bezos (Amazon) - 30
🇺🇸 Oprah Winfrey (Harpo) - 32
🇺🇸 Estée Lauder (Estée Lauder) - 38
🇺🇸 Henry Ford (Ford) - 39
🇺🇸 Vera Wang (Vera Wang) - 40
🇺🇸 Jeffrey Brotman (Costco) - 40
🇺🇸 Robert Noyce (Intel) - 41
🇫🇷 Christian Dior (Dior) - 41
🇺🇸 John Warnock (Adobe) - 42
🇺🇸 Ralph Roberts (Comcast) - 43
🇺🇸 Donald Fisher (The Gap) - 44
🇺🇸 Sam Walton (Walmart) - 44
🇺🇸 Bob Parsons (GoDaddy) - 47
🇯🇵 Yoshisuke Aikawa (Nissan) - 48
🇮🇪 Tony Ryan (Ryanair) - 48
🇺🇸 Bernie Marcus (Home Depot) - 49
🇺🇸 Gary Burrell (Garmin) - 52
🇨🇭 Henri Nestlé (Nestle) - 52
🇺🇸 Ray Kroc (McDonalds) - 52
🇮🇳 J. C. Mahindra (Mahindra) - 53
🇹🇭 Chaleo Yoovidhya (Red Bull) - 53
🇺🇸 John Pemberton (Coca-Cola) - 54
🇯🇵 Kawasaki Shozo (Kawasaki) - 59
🇺🇸 Charles Flint (IBM) - 61
🇺🇸 Bill Porter (E-trade) - 63
🇺🇸 Colonel Sanders (KFC) - 65

[Historic Vids @historyinmemes]

Muhammad Ali dodges 21 punches in 10 seconds (1977)

[American College of Cardiology @ACCinTouch]

Registration is now open for #ACCMidEastMed!

This meeting will deliver an engaging forum to examine evidence-based strategies & contemporary best practices targeted to your region to reach our common objective of improving ❤️ health of patients w/ CVD. https://t.co/llnlrIiv3K

[Zafar Iqbal @zafarology]

@PeninsulaQatar Mother

[Zafar Iqbal @zafarology]

@PeninsulaQatar Al waab

[Bloomberg @business]

Rep. Richard Hudson (R-NC) asks TikTok CEO Shou Chew: "Does TikTok access the home WiFi network?" https://t.co/Fmv8MED8z0

[Journal of Brown Hospital Medicine @BrownJHM]

Brain concussion (C.Giza) #medEd

[Ziyad HIJAZI @structuralheart]

I’m honored to be the guest speaker at the next AEPC meeting to be held in Dublin, Ireland to deliver the Hausdorf lecture! The meeting will take place April 26-29, 2023!! Early bird registration deadline January 30, 2023! Hope to see you in Dublin!

[@PICS_Society @PICS_Society]

Register now for PICS istanbul March 15-18 2023, the premier global meeting in congenital/structural ❤️ disease interventions. https://t.co/ryuAUvWBdW Live cases, new valve technology, challenges cases. Click here for video: https://t.co/WtdTvAqCaE

[Matters of the Heart 🫀 @MattersoftheH14]

Aortic stenosis

[Meet Kevin ❇️ @realMeetKevin]

In 2022, @elonmusk sold approximately $23 BILLION of $TSLA. In 2022 through December 16, retail investors bought $15.2b of Tesla stock (Vanda).

Retail hodlers would have had to buy 50% more Tesla stock just to offset Elon Musk’s selling pressure from the HODL order book.