Ikonopedia will Help Enhance Efficiency and Patient Safety

PHOENIX, August 26, 2021 – Ikonopedia announced today that it has added Banner Health, one of the largest non-profit healthcare systems in the country, as a customer and will implement its entire suite of structured breast imaging reporting and MQSA management tools.  The installation is designed to help streamline processes, improve reporting efficiency and optimize facility operations across the Banner Health network.

The Banner Health installation will begin with 18 inpatient acute care facilities across the six states Banner is in: Arizona, California, Colorado, Nebraska, Nevada and Wyoming.  Banner Health is recognized as a top health system in the country for clinical quality, excellent customer service and innovation. Headquartered in Phoenix, Banner Health owns and operates 30 hospitals, including three academic medical centers, and other related health entities and services in six states.

Ikonopedia is an innovative cloud-based structured breast reporting and MQSA management system designed to dramatically improve reporting efficiency and optimize facility operations. All findings are saved as discrete data, which allows Ikonopedia to prevent errors, maintain BI-RADS-compliant language and automate many time-consuming processes.  Ikonopedia makes it possible to eliminate laterality errors, automatically choose exam-appropriate patient letters and pull forward findings from past exams along with many other time-saving features.

Ikonopedia’s integrated risk assessment tool is now available in dozens of languages and risk data is used to create alerts for the radiologist, populate the clinical section of the report, and automatically update the patient letter. A high-risk patient alert identifies patients with a 20% or greater lifetime risk and information about the score is instantly viewable.

Said Emily Crane, CEO of Ikonopedia: “Banner Health is widely recognized for their quality and excellence of breast healthcare.  We are pleased to partner with Banner Health to help optimize efficiency and patient safety with intuitive reporting, risk assessment and quality improvement tools.”

About Ikonopedia

Ikonopedia was founded by three expert breast imaging Radiologists: László Tabár, MD is the author of 6 books in 10 languages on mammography and a world-renowned educator;  A. Thomas Stavros, MD is the author of one of the most popular reference books in the field of breast ultrasound; and Michael J. Vendrell, MD is an expert in breast MRI and CAD design with extensive experience in breast-imaging software. For more information, visit www.ikonopedia.com.

#   #   #

Media Contacts:

Emily Crane
Ikonopedia
801.673.4272
emily.crane@ikonopedia.com

Ikonopedia “Insight” is a colorful, interactive data visualization tool that provides valuable insight into your patient data

Ikonopedia “Insight” helps breast imaging facilities utilize data to provide better care and improve practice efficiency. “Insight” uses customers’ patient intake information, imaging data and clinical risk assessments to provide end-to-end visualization of patient care, from screening to treatment and follow up.

This interactive visualization tool lets you dive deep to answer questions you never thought possible. Unlike other breast reporting systems, Ikonopedia stores all data including exam findings as discrete data that can be brought to life in our new “Insight” module.

Data is displayed in interactive dashboards with colorful charts and graphs.  If you want to know more about the data behind a particular bar-graph or pie-chart, you can click on those items to open new visualization elements — giving you actionable understanding of your patient data.

Screening Distribution Visualisation

BI-RADS® Distribution Visualisation

As radiologists face increasing exam volume and data complexity, Ikonopedia Analytics provides easy access to high level clinical and administrative data and trends, such as exam counts over a period of time, rates of malignancy in certain patient types, exam reading times for physicians, mobile site productivity and more.  Ikonopedia Analytics uses data already entered into the system to generate a variety of BI-RADS® compliant static reports that are available for both internal evaluation and external audits, such as MQSA compliance audits.

“Insight” leverages Ikonopedia’s structured reporting modalities to enable customers to learn more about patient demographics (identify those who may need more frequent screenings for follow up to improve quality of care, etc.), identify organizational operational trends (where staffing adjustments may be needed to address patient volume load), identify personnel and potential training gaps (who is under performing/over performing within the department). Examples of clinical and administrative dashboards include:

  • Screening population risk distribution by age, by breast density, by ethnicity, by BI-RADS® results;
  • Breast density population distribution by age; by risk; by BI-RADS® results;
  • Time for Interval cancers between negative results and diagnosis;
  • Time to resolution for BI-RADS®-0 exams;
  • Screening compliance by referring physician;
  • Breast MR exam volume compared to practice’s high risk patient population.

“The adoption of risk-based screening based on a woman’s personal risk factors is critical to take breast cancer screening to the next level, improving both patient outcomes and quality of life,” said László Tabár, MD, and co-founder of Ikonopedia.  “In order to make that possible, radiologists must be able to easily visualize patient specific risk and density data to make informed decisions about modality combinations, surveillance intervals and when to initiate regular screening. This new analytics module provides these capabilities in an intuitive format that can be customized and tracked over time.”

Ikonopedia is an innovative structured breast reporting and MQSA management system designed to dramatically improve reporting efficiency, and optimize facility operations. All findings are saved as discrete data which allows Ikonopedia to prevent errors, maintain BI-RADS-compliant language and automate many time-consuming processes.  Ikonopedia makes it possible to eliminate laterality errors, automatically choose exam-appropriate patient letters and pull forward findings from past exams along with many other time-saving features.

Ikonopedia’s integrated risk assessment tool is now available in dozens of languages and risk data is used to create alerts for the radiologist, populate the clinical section of the report, and automatically update the patient letter. A high-risk patient alert identifies patients with a 20% or greater lifetime risk and information about the score is instantly viewable.

About Ikonopedia

Ikonopedia was founded by three expert breast imaging Radiologists: László Tabár, MD is the author of 6 books in 10 languages on mammography and a world renowned educator;  A. Thomas Stavros, MD is the author of one of the most popular reference books in the field of breast ultrasound; and Michael J. Vendrell, MD is an expert in breast MRI and CAD design with extensive experience in breast-imaging software. For more information, visit www.ikonopedia.com.

#   #   #

Media Contacts:

Emily Crane                                                                      

Ikonopedia                                                                 

801.673.4272

emily.crane@ikonopedia.com                                       

This article is a reprint from: Centers for Disease Control and Prevention
 

Local Reactions

Local reactions were reported by the majority of vaccine recipients and at higher rates than placebo recipients. Vaccine recipients reported higher rates of local reactions after dose 2 than dose 1. The frequency of local reactions was higher in the younger age group (aged 18 to 64 years) than the older age group (aged ≥65 years) (90.5% vs 83.9% after dose 2). Pain at the injection site was the most frequent and severe reported solicited local reaction among vaccine recipients. After dose 1, the younger age group reported pain more frequently than the older age group (86.9% vs 74.0%); a similar pattern was observed after dose 2 (90.1% vs 83.4%). Axillary swelling or tenderness was the second most frequently reported local reaction. Axillary swelling or tenderness was reported more frequently in the younger age group than the older age group (16.0% vs 8.4% after dose 2). Injection site redness and swelling following either dose were reported less frequently. Redness and swelling were slightly more common after dose 2. No grade 4 local reactions were reported. Overall, the median onset of local reactions in the vaccine group was 1 day after either dose, with a median duration between 2 and 3 days. (Table 1Table 2)

Table 1. Local reactions in persons aged 18-64 years, Moderna COVID-19 vaccine and placebo

Table 1. Local reactions in persons aged 18-64 years, Moderna COVID-19 vaccine and placebo
Dose 1 Dose 2
Moderna Vaccine
N=11401
Placebo
N=11404
Moderna Vaccine
N=10357
Placebo
N=10317
Any Local, n (%)
Any 9960 (87.4) 2432 (21.3) 9371 (90.5) 2134 (20.7)
Grade 3 452 (4.0) 39 (0.3) 766 (7.4) 41 (0.4)
Paina, n (%)
Any 9908 (86.9) 2179 (19.1) 9335 (90.1) 1942 (18.8)
Grade 3 367 (3.2) 23 (0.2) 479 (4.6) 21 (0.2)
Rednessa, n (%)
Any 345 (3.0) 46 (0.4) 928 (9.0) 42 (0.4)
Severe 34 (0.3) 11 (<0.1) 206 (2.0) 12 (0.1)
Swellingb, n (%)
Any 768 (6.7) 33 (0.3) 1309 (12.6) 35 (0.3)
Grade 3 62 (0.5) 3 (<0.1) 176 (1.7) 4 (<0.1)
Axillary Swelling/Tendernessc, n (%)
Any 1322 (11.6) 567 (5.0) 1654 (16.0) 444 (4.3)
Grade 3 36 (0.3) 13 (0.1) 45 (0.4) 10 (<0.1)

a Pain grade 3: any use of prescription pain reliever or prevented daily activity; grade 4: required emergency room visit or hospitalization.

b Swelling grade 3: >100mm/>10cm; grade 4: necrosis/exfoliative dermatitis.

c Axillary swelling or tenderness was collected as a solicited local adverse reaction (i.e., lymphadenopathy: localized axillary swelling or tenderness ipsilateral to the vaccination arm); grade 3: any use of prescription pain reliever or prevented daily activity; grade 4: required emergency room visit or hospitalization.

Note: No grade 4 local reactions were reported.

Table 2. Local reactions in persons aged ≥65 years, Moderna COVID-19 vaccine and placebo

Table 2. Local reactions in persons aged ≥65 years, Moderna COVID-19 vaccine and placebo
Dose 1 Dose 2
Moderna Vaccine
N=3762
Placebo
N=3746
Moderna Vaccine
N=3587
Placebo
N=3549
Any Local, n (%)
Any 2805 (74.6) 566 (15.1) 3010 (83.9) 473 (13.3)
Grade 3 77 (2.0) 39 (1.0) 212 (5.9) 29 (0.8)
Paina, n (%)
Any 2782 (74.0) 481(12.8) 2990 (83.4) 421 (11.9)
Grade 3 50 (1.3) 32 (0.9) 96 (2.7) 17 (0.5)
Rednessa, n (%)
Any 86 (2.3) 19 (0.5) 265 (7.4) 13 (0.4)
Grade 3 8 (0.2) 2 (<0.1) 75 (2.1) 3 (<0.1)
Swellingb, n (%)
Any 166 (4.4) 19 (0.5) 386 (10.8) 13 (0.4)
Grade 3 20 (0.5) 3 (<0.1) 69 (1.9) 7 (0.2)
Axillary Swelling/Tendernessc, n (%)
Any 231 (6.1) 155 (4.1) 302 (8.4)  90 (2.5)
Grade 3 12 (0.3) 14 (0.4) 21 (0.6) 8 (0.2)

a Pain grade 3: any use of prescription pain reliever or prevented daily activity; grade 4: required emergency room visit or hospitalization.

b Swelling grade 3: >100mm/>10cm; grade 4: necrosis/exfoliative dermatitis.

c Axillary swelling or tenderness was collected as a solicited local adverse reaction (i.e. lymphadenopathy: localized axillary swelling or tenderness ipsilateral to the vaccination arm); grade 3: any use of prescription pain reliever or prevented daily activity; grade 4: required emergency room visit or hospitalization.

Note: No grade 4 local reactions were reported.

Systemic Reactions

Systemic reactions were reported by the majority of vaccine recipients and at higher rates than placebo recipients. The frequency of systemic reactions was higher in the younger age group than the older age group (81.9% vs 71.9% after dose 2). Within each age group, the frequency and severity of systemic reactions was higher after dose 2 than dose 1. For both age groups, fatigue, headache and myalgia were the most common. The majority of systemic reactions were mild or moderate in severity, after both doses and in both age groups. Fever was more common after the second dose and in the younger group (17.6%) compared to the older group (10.2%). Among vaccine recipients, the median onset of systemic reactions was 1 to 2 days after either dose, with a median duration of 2 days. Grade 4 fever (>40.0°C) was reported by four vaccine recipients after dose 1 and 11 vaccine recipients after dose 2. There was one report of grade 4 fatigue and one report of grade 4 arthralgia, both in the younger age group after dose 1. In the older age group, there was one report of grade 4 nausea or vomiting after dose 2. No other systemic grade 4 reactions were reported. (Table 3Table 4)

Table 3. Systemic reactions in persons aged 18-64 years, Moderna COVID-19 vaccine and placebo

Table 3. Systemic reactions in persons aged 18-64 years, Moderna COVID-19 vaccine and placebo
Dose 1 Dose 2
Moderna Vaccine
N=11405
Placebo
N=11406
Moderna Vaccine
N=10358
Placebo
N=10320
Any systemic, n (%)
Any 6503 (57.0) 5063 (44.4) 8484 (81.9) 3967 (38.4)
Grade 3 363 (3.2) 248 (2.2) 1801 (17.4) 215 (2.1)
Grade 4 5 (<0.1) 4 (<0.1) 10 (<0.1) 2 (<0.1)
Fevera, n (%)
Any 105 (0.9) 39 (0.3) 1806 (17.4) 38 (0.4)
Grade 3 10 (<0.1) 1 (<0.1) 168 (1.6) 1 (<0.1)
Grade 4 4 (<0.1) 4 (<0.1) 10 (<0.1) 1 (<0.1)
Headacheb, n (%)
Any 4031(35.4) 3303 (29.0) 6500 (62.8) 2617 (25.4)
Grade 3 219 (1.9) 162 (1.4) 515 (5.0) 124 (1.2)
Fatiguec, n (%)
Any 4384 (38.5) 3282 (28.8) 7002 (67.6) 2530 (24.5)
Grade 3 120 (1.1) 83 (0.7) 1099 (10.6) 81 (0.8)
Grade 4 1 (<0.1) 0 (0) 0 (0) 0 (0)
Myalgiac, n (%)
Any 2698 (23.7) 1626 (14.3) 6353 (61.3) 1312 (12.7)
Grade 3 73 (0.6) 38 (0.3) 1032 (10.0) 39 (0.4)
Arthralgiac, n (%)
Any 1892 (16.6) 1327 (11.6) 4685 (45.2) 1087 (10.5)
Grade 3 47 (0.4) 29 (0.3) 603 (5.8) 36 (0.3)
Grade 4 1 (<0.1) 0 (0) 0 (0) 0 (0)
Nausea/Vomitingd, n (%)
Any 1069 (9.3) 908 (8.0) 2209 (21.3) 754 (7.3)
Grade 3 6 (<0.1) 8 (<0.1) 8 (<0.1) 8 (<0.1)
Chillse, n (%)
Any 1051 (9.2) 730 (6.4) 5001 (48.3) 611 (5.9)
Grade 3 17 (0.1) 8 (<0.1) 151 (1.5) 14 (0.1)

a Fever – Grade 3: ≥39.0 – ≤40.0°C or ≥102.1 – ≤104.0°F; Grade 4: >40.0°C or >104.0°F
b Headache – Grade 3: significant; any use of prescription pain reliever or prevented daily activity; Grade 4: required emergency room visit or hospitalization.
c Fatigue, Myalgia, Arthralgia – Grade 3: significant; prevented daily activity; Grade 4: required emergency room visit or hospitalization.
d Nausea/Vomiting – Grade 3: prevented daily activity, required outpatient intravenous hydration; Grade 4: required emergency room visit or hospitalization for hypotensive shock.
e Chills – Grade 3: prevented daily activity and required medical intervention; Grade 4: required emergency room visit or hospitalization.

Table 4. Systemic reactions in persons aged ≥65 years, Moderna COVID-19 vaccine and placebo

Table 4. Systemic reactions in persons aged ≥65 years, Moderna COVID-19 vaccine and placebo
Dose 1 Dose 2
Moderna Vaccine
N=3761
Placebo
N=3748
Moderna Vaccine
N=3589
Placebo
N=3549
Any systemic, n (%)
Any 1818 (48.3) 1335 (35.6) 2580 (71.9) 1102 (31.1)
Grade 3 84 (2.2) 63 (1.7) 387 (10.8) 58 (1.6)
Grade 4 0 (0) 0 (0) 2 (<0.1) 1 (<0.1)
Fevera, n (%)
Any 10 (0.3) 7 (0.2) 366 (10.2) 5 (0.1)
Grade 3 1 (<0.1) 1 (<0.1) 18 (0.5) 0 (0)
Grade 4 0 (0) 2 (<0.1) 1 (<0.1) 1 (<0.1)
Headacheb, n (%)
Any 921 (33.3) 443 (11.8) 1665 (46.4) 635 (17.9)
Grade 3 30 (0.8) 34 (0.9) 107 (3.0) 32 (0.9)
Fatiguec, n (%)
Any 1251 (38.5) 851 (22.7) 2094 (58.4) 695 (19.6)
Grade 3 120 (1.1) 23 (0.6) 248 (6.9) 20 (0.6)
Myalgiac, n (%)
Any 743 (19.8) 443 (11.8) 1683 (46.9) 385 (10.8)
Grade 3 17 (0.5) 9 (0.3) 201 (5.6) 10 (0.3)
Arthralgiac, n (%)
Any 618 (16.4) 456 (12.2) 1252 (34.9) 381 (10.7)
Grade 3 13 (0.3) 8 (0.2) 122 (3.4) 7 (0.2)
Nausea/Vomitingd, n (%)
Any 194 (5.2) 166 (4.4) 425 (11.8) 129 (3.6)
Grade 3 4 (0.1) 4 (0.1) 10 (0.3) 3 (<0.1)
Grade 4 0 (0) 0 (0) 1 (<0.1) 0 (0)
Chillse, n (%)
Any 202 (5.4) 148 (4.0) 1099 (30.6) 144 (4.1)
Grade 3 7 (0.2) 6 (0.2) 27 (0.8) 2 (<0.1)

a Fever – Grade 3: ≥39.0 – ≤40.0°C or ≥102.1 – ≤104.0°F; Grade 4: >40.0°C or >104.0°F
b Headache – Grade 3: significant; any use of prescription pain reliever or prevented daily activity; Grade 4: requires emergency room visit or hospitalization.
c Fatigue, Myalgia, Arthralgia – Grade 3: significant; prevented daily activity; Grade 4: required emergency room visit or hospitalization.
d Nausea/Vomiting – Grade 3: prevented daily activity, required outpatient intravenous hydration; Grade 4: Requires emergency room visit or hospitalization for hypotensive shock.
e Chills – Grade 3: prevented daily activity and required medical intervention; Grade 4: required emergency room visit or hospitalization.

Unsolicited Adverse Events

A higher frequency of unsolicited adverse events was reported in the vaccine group compared to the placebo group and was primarily attributed to local and systemic reactogenicity following vaccination. Reports of lymphadenopathy were imbalanced with 1.1 % of persons in the vaccine group and 0.6% in the placebo group reporting such events; lymphadenopathy is plausibly related to the vaccine. Lymphadenopathy occurred in the arm and neck region and was reported within 2 to 4 days after vaccination. The median duration of lymphadenopathy was 1 to 2 days. Bell’s palsy was reported by three vaccine recipients and one placebo recipient. One case of Bell’s palsy in the vaccine group was considered a serious adverse event. Currently available information is insufficient to determine a causal relationship with the vaccine.

Serious Adverse Events

Serious adverse events were defined as any untoward medical occurrence that resulted in death, was life-threatening, required inpatient hospitalization or prolongation of existing hospitalization, or resulted in persistent disability or incapacity. The proportions of participants who reported at least one serious adverse event were 1% in the vaccine group and 1% in the placebo group. The most common serious adverse events occurring at higher rates in the vaccine group than the placebo group were myocardial infarction (5 cases in vaccine group vs. 3 cases in placebo group), cholecystitis (3 vs. 0), and nephrolithiasis (3 vs. 0). Three serious adverse events were considered by the U.S. Food and Drug Administration (FDA) as possibly related to vaccine: the one report of intractable nausea/vomiting and two reports of facial swelling in persons who had a previous history of cosmetic filler injections. The possibility that the vaccine contributed to the serious adverse event reports of rheumatoid arthritis (n=1), peripheral edema/dyspnea with exertion (n=1), and autonomic dysfunction (n=1) cannot be excluded.

Data source: FDA briefing documentexternal icon

Reduces the Complexity of Reporting for Screening and Diagnostic MRI Exams to Deliver Time-Saving and Patient Safety Benefits

RICHARDSON, Texas, November 12, 2020 Ikonopedia announced today the release of its newly updated next-generation breast MRI reporting module.  The intuitive new interface is designed to reduce the complexity of reporting for screening and diagnostic MRI exams and is compliant to the ACR BI-RADS Atlas Fifth Edition.

The new breast MRI module leverages the intuitive icon-based interface of Ikonopedia’s Mammography and Ultrasound structured reporting modalities to deliver a variety of physician efficiency and patient safety benefits.  Reporting capabilities have been expanded and instinctual organization guides radiologists through BI-RADS criteria to reach an accurate, BI-RADS-compliant, and natural sounding description of lesions. New functionality in the MRI diagnostic modality includes ten lesion assessment categories that adhere to BI-RADS.  The MRI screening modality has been updated to include a new contrast selection dialog as well as to synchronize with the new MRI diagnostic modality.

The enhanced breast MRI module has also been optimized for AI input such as Qlarity Imaging’s QuantX, the first U.S. Food and Drug Administration (FDA)-cleared computer-aided diagnosis software for breast MRI analysis.

We’ve been very pleased with the flexibility and efficiency gains from the intuitive user interface in the updated breast MRI reporting tools, particularly the ability to easily describe trackable entries while maintaining BI-RADS verbiage to create complex reports,” said Erica Guzalo, Section Chief, Breast Imaging, Sinai Health Chicago.  “I also appreciate Ikonopedia’s dedication to continually help solve issues and implement new ideas that are beneficial to us, as users.

  “As we, as an industry, move towards more broadly adopting risk-based screening based on a women’s personal risk and breast density, the utilization of breast MRI will continue to grow,” said Michael Vendrell, MD, co-founder of Ikonopedia.  “This new module streamlines reporting workflow to deliver more accurate diagnoses, reduces the risk of reporting errors, and save time as radiologists face increasing exam volume and data complexity.  These are critical new capabilities to improve patient care and safety.” 

Ikonopedia is an innovative structured breast reporting and MQSA management system designed to dramatically improve reporting efficiency, and optimize facility operations. All findings are saved as discrete data which allows Ikonopedia to prevent errors, maintain BI-RADS-compliant language and automate many time-consuming processes.  Ikonopedia makes it possible to eliminate laterality errors, automatically choose exam-appropriate patient letters and pull forward findings from past exams along with many other time-saving features.

Ikonopedia’s integrated risk assessment tool is now available in dozens of languages and risk data is used to create alerts for the radiologist, populate the clinical section of the report, and automatically update the patient letter. A high-risk patient alert identifies patients with a 20% or greater lifetime risk and information about the score is instantly viewable.

About Ikonopedia

Ikonopedia was founded by three expert breast imaging Radiologists: László Tabár, MD is the author of 6 books in 10 languages on mammography and a world renowned educator;  A. Thomas Stavros, MD is the author of one of the most popular reference books in the field of breast ultrasound; and Michael J. Vendrell, MD is an expert in breast MRI and CAD design with extensive experience in breast-imaging software. For more information, visit www.ikonopedia.com.

 

#   #   #

Media Contacts:
Emily Crane
Ikonopedia
801.673.4272

emily.crane@ikonopedia.com

By Rebekah Moan, AuntMinnie.com contributing writer

October 3, 2020 — Women who only speak Spanish have a 27% less likelihood of getting a screening mammogram than English speakers, according to a study presented at the American College of Surgeons (ACS) Clinical Congress 2020. And Spanish speakers aren’t the only ones — by and large, women who speak limited English are less likely to receive breast cancer screening.

The mammography rate of women with limited English-language proficiency was compared with English-speaking women by a research team led by Dr. Jose L. Cataneo, a general surgery resident at the University of Illinois at Chicago/Metropolitan Group Hospitals. They used data from the National Health Interview Survey for their analysis.

The researchers found that women who didn’t speak much English had much lower breast screening rates.

“The impact of language barriers on screening mammography was previously unknown from a national database,” Cataneo said. “It is important because approximately 67 million people in the United States speak a language other than English, and 41 million of those speak Spanish.”

Mammography screening by the numbers

Screening mammography is currently the gold standard for detecting breast cancer. The age range and the frequency vary depending on the governing body, but even still, most clinicians recommend screening mammography to catch cancer early when it’s most treatable.

In the U.S., does speaking exclusively or mostly a language besides English affect mammography screening uptake? That’s precisely what Cataneo and colleagues sought to find out. They used the National Health Interview Survey, an annual survey of U.S. civilian, noninstitutionalized residents. Only using the year 2015, the researchers included 9,653 women ages 40 to 75. Among those, 1,040 had limited English-language proficiency and 712 only spoke Spanish.

The researchers used statistical modeling to match the English speakers with the limited English speakers by age, race-ethnicity, insurance status, and family income. Of the group who spoke limited English, the overall rate of screening mammograms was 12% less than for proficient English speakers: 78% versus 90%. Dividing women into different age groups — 40 to 50, 45 to 75, and 50 to 75 — still resulted in women with limited English getting fewer screening mammograms.

Cataneo and colleagues also found speaking only Spanish produced a lower probability of getting a screening mammogram: for every 100 English-speaking women who get a screening mammogram, 73 Spanish-only speakers will get one.

On top of that, in the survey, 209 women reported never having a mammogram, which if extrapolated to the entire U.S. female population, equals 450,000 women in the country who are eligible for a screening mammogram but may not have had one, according to statistical software Cataneo used.

Why is it that limited English results in less screening uptake? It likely has to do with poverty, lack of health insurance, and fear, according to the researchers. Possible solutions include more education about breast health, the importance of mammography screening, and advancement in treatment options.

In addition to holding educational seminars in languages other than English, making online mammography scheduling available in other languages could also help, the researchers added.

This article is a reprint from www.auntminnie.com. Click here to view the original article

By Erik L. Ridley, AuntMinnie staff writer

August 27, 2020 –– The combination of an artificial intelligence (AI)-based computer-aided detection (CAD) algorithm with radiologist interpretation can detect more cases of breast cancer on screening mammograms than double reading by radiologists, according to research published online August 27 in JAMA: Oncology.

Click here to read the complete article at AuntMinnie.com

Researchers from the Karolinska University Hospital in Stockholm, Sweden, retrospectively compared three commercially available AI models in a case-control study involving nearly 9,000 women who had undergone screening mammography. They found that one of the models demonstrated sufficient diagnostic performance to merit further prospective evaluation as an independent reader.

What’s more, the best results — 88.6% sensitivity with 93% specificity — were achieved when utilizing that algorithm’s results along with the first radiologist interpretation.

“Combining the first readers with the best algorithm identified more cases positive for cancer than combining the first readers with second readers,” wrote the authors, led by Dr. Mattie Salim. “No other examined combination of AI algorithms and radiologists surpassed this sensitivity level.”

The researchers used a study sample of 8,805 women ages 40 to 74 who had received screening mammography at their academic hospital from 2008 to 2015 and who did not have implants or prior breast cancer. All exams were performed on a full-field digital mammography system from Hologic.

Of these women from the public mammography screening program, 8,066 were a random sample of healthy controls and 739 were diagnosed with breast cancer. These 739 cancer cases included 618 actual screening-detected cancers and 121 clinically detected cancers. In order to mimic the 0.5% screening-detected cancer rate in the source screening cohort, a stratified bootstrapping method was used to increase the simulated number of screenings to 113,663.

The researchers then applied AI CAD software from three different vendors, who asked to remain anonymous. None of the algorithms had been trained on the mammograms in the study.

After processing the images, the CAD software provided a prediction score for each breast ranging from 0 (lowest suspicion) to 1 (highest suspicion). To enable comparison of the algorithm’s results with the recorded radiologist decisions, the researchers elected to choose an algorithm output cutpoint that corresponded as closely as possible to the specificity of that of the first-reader radiologists, i.e. 96.6%.

Breast cancer detection performance
First-reader radiologists Second-reader radiologists Double reading consensus AI algorithm #3 AI algorithm #2 AI algorithm #1 Combination of AI algorithm #1 and first-reader radiologists
Area under the curve n/a n/a n/a 0.920 0.922 0.956 n/a
Sensitivity 77.4% 80.1% 85% 67.4% 67% 81.9% 88.6%
Specificity 96.6% 97.2% 98.5% 96.7% 96.6% 96.6% 93%

The researchers noted that the differences in sensitivity between AI algorithm #1 and the other two algorithms and the first reader were statistically significant (p < 0.001 and p = 0.03, respectively).

In an accompanying commentary, Dr. Constance Lehman, PhD, of Harvard Medical School in Boston said that it’s now time to move beyond simulation and reader studies and enter the critical phase of rigorous, prospective clinical evaluation of AI.

“The need is great and a more rapid pace of research in this domain can be partnered with safe, careful, and effective testing in prospective clinical trials,” she wrote. “If AI models can sort women with cancer detected on their mammograms from those without cancer detected on their mammograms, the value of screening mammography can be made available and affordable to a large population of women globally who currently have no access to the life-saving potential of quality screening mammography.”

Click here to read the complete article at AuntMinnie.com