Ammar J.

Ammar J.

Mumbai, Maharashtra, India
3K followers 500+ connections

Join to follow

Articles by Ammar

  • The Best of Both Worlds: Hybrid human expert + AI coaching
    Apr 3, 2024

    The Best of Both Worlds: Hybrid human expert + AI coaching

    Collaborative cases: Where human machine synergy outcomes outperform either There was a time when a monk would advise…

    7 Comments
  • Conversational Coaching Agents: Beyond the screen
    Mar 20, 2024

    Conversational Coaching Agents: Beyond the screen

    Agents Galore: Need something? There’s a chatbot for that! The date is November, 2023. Developers gained unprecedented…

  • Game on: Behavioral modification through AI
    Mar 13, 2024

    Game on: Behavioral modification through AI

    Seriously Fun: The art of making boring, fun through games The concept of 'Serious Games' isn't new. Its roots trace…

  • Predictive Analytics: A crystal ball for personal health insights
    Mar 6, 2024

    Predictive Analytics: A crystal ball for personal health insights

    Data: The Big, the Diverse, and the Real-Time I was curious on the of the term Big Data, and found something very…

    2 Comments
  • The Role of AI in Personalised Healthcare
    Feb 21, 2024

    The Role of AI in Personalised Healthcare

    Contextual Personalisation: AI's personalised approach to health As I've traversed through the realms of healthcare and…

    14 Comments
  • X-Labs @ Fitterfly
    Jun 19, 2023

    X-Labs @ Fitterfly

    Outcomes matter When it comes to chronic disease management and Metabolic health, Fitterfly has always been at the…

    1 Comment
  • On Transitions
    Oct 1, 2022

    On Transitions

    Yesterday was officially my last day at Qure. And it has been a brilliant 4 years of learnings, un-learnings, and some…

    3 Comments
See all articles

Activity

Join now to see all activity

Experience

  • Fitterfly Graphic

    Fitterfly

    Mumbai, Maharashtra, India

  • -

    Mumbai, Maharashtra, India

  • -

  • -

  • -

    Mumbai Area, India

  • -

    Mumbai Area, India

  • -

    Mumbai Area, India

Education

Publications

  • Teleradiology and technology innovations in radiology: status in India and its role in increasing access to primary health care

    The Lancet Regional Health - Southeast Asia

    See publication

  • Frequency of Missed Findings on Chest Radiographs (CXRs) in an International, Multicenter Study: Application of AI to Reduce Missed Findings

    MDPI Diagnostics

    Background: Missed findings in chest X-ray interpretation are common and can have serious consequences. Methods: Our study included 2407 chest radiographs (CXRs) acquired at three Indian and five US sites. To identify CXRs reported as normal, we used a proprietary radiology report search engine based on natural language processing (mPower, Nuance). Two thoracic radiologists reviewed all CXRs and recorded the presence and clinical significance of abnormal findings on a 5-point scale (1—not…

    Background: Missed findings in chest X-ray interpretation are common and can have serious consequences. Methods: Our study included 2407 chest radiographs (CXRs) acquired at three Indian and five US sites. To identify CXRs reported as normal, we used a proprietary radiology report search engine based on natural language processing (mPower, Nuance). Two thoracic radiologists reviewed all CXRs and recorded the presence and clinical significance of abnormal findings on a 5-point scale (1—not important; 5—critical importance). All CXRs were processed with the AI model (Qure.ai) and outputs were recorded for the presence of findings. Data were analyzed to obtain area under the ROC curve (AUC). Results: Of 410 CXRs (410/2407, 18.9%) with unreported/missed findings, 312 (312/410, 76.1%) findings were clinically important: pulmonary nodules (n = 157), consolidation (60), linear opacities (37), mediastinal widening (21), hilar enlargement (17), pleural effusions (11), rib fractures (6) and pneumothoraces (3). AI detected 69 missed findings (69/131, 53%) with an AUC of up to 0.935. The AI model was generalizable across different sites, geographic locations, patient genders and age groups. Conclusion: A substantial number of important CXR findings are missed; the AI model can help to identify and reduce the frequency of important missed findings in a generalizable manner.

    See publication

  • Performance of a Chest Radiography AI Algorithm for Detection of Missed or Mislabeled Findings: A Multicenter Study

    MDPI Diagnostics

    Purpose: We assessed whether a CXR AI algorithm was able to detect missed or mislabeled chest radiograph (CXR) findings in radiology reports. Methods: We queried a multi-institutional radiology reports search database of 13 million reports to identify all CXR reports with addendums from 1999–2021. Of the 3469 CXR reports with an addendum, a thoracic radiologist excluded reports where addenda were created for typographic errors, wrong report template, missing sections, or uninterpreted signoffs.…

    Purpose: We assessed whether a CXR AI algorithm was able to detect missed or mislabeled chest radiograph (CXR) findings in radiology reports. Methods: We queried a multi-institutional radiology reports search database of 13 million reports to identify all CXR reports with addendums from 1999–2021. Of the 3469 CXR reports with an addendum, a thoracic radiologist excluded reports where addenda were created for typographic errors, wrong report template, missing sections, or uninterpreted signoffs. The remaining reports contained addenda (279 patients) with errors related to side-discrepancies or missed findings such as pulmonary nodules, consolidation, pleural effusions, pneumothorax, and rib fractures. All CXRs were processed with an AI algorithm. Descriptive statistics were performed to determine the sensitivity, specificity, and accuracy of the AI in detecting missed or mislabeled findings. Results: The AI had high sensitivity (96%), specificity (100%), and accuracy (96%) for detecting all missed and mislabeled CXR findings. The corresponding finding-specific statistics for the AI were nodules (96%, 100%, 96%), pneumothorax (84%, 100%, 85%), pleural effusion (100%, 17%, 67%), consolidation (98%, 100%, 98%), and rib fractures (87%, 100%, 94%). Conclusions: The CXR AI could accurately detect mislabeled and missed findings. Clinical Relevance: The CXR AI can reduce the frequency of errors in detection and side-labeling of radiographic findings.

    See publication

  • Can Artificial Intelligence Reliably Report Chest X-Rays?: Radiologist Validation of an Algorithm trained on 2.3 Million X-Rays

    Arxiv Preprint

    Background: Chest X-rays are the most commonly performed, cost-effective diagnostic imaging tests ordered by physicians. A clinically validated AI system that can reliably separate normals from abnormals can be invaluable particularly in low-resource settings. The aim of this study was to develop and validate a deep learning system to detect various abnormalities seen on a chest X-ray. Methods: A deep learning system was trained on 2.3 million chest X-rays and their corresponding radiology…

    Background: Chest X-rays are the most commonly performed, cost-effective diagnostic imaging tests ordered by physicians. A clinically validated AI system that can reliably separate normals from abnormals can be invaluable particularly in low-resource settings. The aim of this study was to develop and validate a deep learning system to detect various abnormalities seen on a chest X-ray. Methods: A deep learning system was trained on 2.3 million chest X-rays and their corresponding radiology reports to identify various abnormalities seen on a Chest X-ray. The system was tested against - 1. A three-radiologist majority on an independent, retrospectively collected set of 2000 X-rays(CQ2000) 2. Radiologist reports on a separate validation set of 100,000 scans(CQ100k). The primary accuracy measure was area under the ROC curve (AUC), estimated separately for each abnormality and for normal versus abnormal scans. Results: On the CQ2000 dataset, the deep learning system demonstrated an AUC of 0.92(CI 0.91-0.94) for detection of abnormal scans, and AUC(CI) of 0.96(0.94-0.98), 0.96(0.94-0.98), 0.95(0.87-1), 0.95(0.92-0.98), 0.93(0.90-0.96), 0.89(0.83-0.94), 0.91(0.87-0.96), 0.94(0.93-0.96), 0.98(0.97-1) for the detection of blunted costophrenic angle, cardiomegaly, cavity, consolidation, fibrosis, hilar enlargement, nodule, opacity and pleural effusion. The AUCs were similar on the larger CQ100k dataset except for detecting normals where the AUC was 0.86(0.85-0.86). Interpretation: Our study demonstrates that a deep learning algorithm trained on a large, well-labelled dataset can accurately detect multiple abnormalities on chest X-rays. As these systems improve in accuracy, applying deep learning to widen the reach of chest X-ray interpretation and improve reporting efficiency will add tremendous value in radiology workflows and public health screenings globally.

    See publication

  • Fabrication of Nearly Hemispherical Polymer Lenses Using Water Droplets as Moulds

    IETE Technical Review

    In this paper, we present a novel method of fabricating nearly hemispherical polymer lenses using water droplets as moulds. Owing to the naturally forming meniscus of water, the surface of the lens is smooth. This technique allowed us to fabricate small lenses of diameter ∼1 mm, which makes them easy to integrate with lab-on-chip platforms. The focal length of the convex lenses was estimated to be ∼1 mm. Due to their hemispherical nature, these lenses have a high numerical aperture. The method…

    In this paper, we present a novel method of fabricating nearly hemispherical polymer lenses using water droplets as moulds. Owing to the naturally forming meniscus of water, the surface of the lens is smooth. This technique allowed us to fabricate small lenses of diameter ∼1 mm, which makes them easy to integrate with lab-on-chip platforms. The focal length of the convex lenses was estimated to be ∼1 mm. Due to their hemispherical nature, these lenses have a high numerical aperture. The method is simple and cost effective as it eliminates the need for specialized and expensive equipment such as surface plasma cleaner. We fabricated both concave and convex lenses in polydimethylsiloxane (PDMS) using water droplets and PDMS lenses as moulds.

    Other authors
    See publication

  • A paperfluidic device for dental applications using a novel patterning technique

    Analytical Methods

    Dental caries is an irreversible and potentially debilitating disease that can ultimately lead to the loss of the affected tooth structure. Due to a lack of awareness, caries is detected much later after its onset. Moreover, people do not have access to dental care or information in the rural areas of several developing countries. Hence, there is a need for a cheap and disposable point-of-care screening test to determine one's oral health. To cater to this unmet need, we have developed a…

    Dental caries is an irreversible and potentially debilitating disease that can ultimately lead to the loss of the affected tooth structure. Due to a lack of awareness, caries is detected much later after its onset. Moreover, people do not have access to dental care or information in the rural areas of several developing countries. Hence, there is a need for a cheap and disposable point-of-care screening test to determine one's oral health. To cater to this unmet need, we have developed a paperfluidic chip that measures salivary pH to estimate its buffering capacity and also tests susceptibility to caries by checking for salivary reductase. The results of our paper-based reductase assay of 72 samples correlated well with the results obtained using the standard tube-based assay performed in dental clinics. Further, the results of the paper-based pH test matched with those of the caries test, i.e. those with lower saliva pH showed higher susceptibility to caries (since acidic environments promote caries). Here, we also report a new and green technique to chemically pattern paper by printing olive oil through an inkjet printer and turning paper (cellulose) hydrophobic in the oil-treated regions through heat-assisted esterification. In addition to patterning hydrophobic regions on paper, the same inkjet printer was used to print all the assay reagents, thus making our paperfluidic chip completely printable. Since our device is cheap, disposable and can be easily manufactured in large volumes by printing, it is suitable for regular monitoring of oral health as well as providing a basic screening test to those without routine access to dentists.

    Other authors
    See publication

More activity by Ammar

View Ammar’s full profile

  • See who you know in common
  • Get introduced
  • Contact Ammar directly
Join to view full profile

Other similar profiles

Explore more posts

Explore collaborative articles

We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.

Explore More

Others named Ammar J.

19 others named Ammar J. are on LinkedIn

See others named Ammar J.

Add new skills with these courses

See all courses