John Kornak

Dr. John Kornak

orcid

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 June 2023 in Radiology
Verified
Journal Article
Closed access
VAVignesh A. Arasu
Vignesh A. Arasu
LHLaurel A. Habel
Laurel A. Habel
NANinah S. Achacoso
Ninah S. Achacoso
DBDiana S. M. Buist
Diana S. M. Buist
JCJason B. Cord
Jason B. Cord
CLCatherine Lee
Catherine Lee
Background Although several clinical breast cancer risk models are used to guide screening and prevention, they have only moderate discrimination. Purpose To compare selected existing mammography artificial intelligence (AI) algorithms and the Breast Cancer Surveillance Consortium (BCSC) risk model for prediction of 5-year risk. Materials and Methods This retrospective case-cohort study included data in women with a negative screening mammographic examination (no visible evidence of cancer) in 2016, who were followed until 2021 at Kaiser Permanente Northern California. Women with prior breast cancer or a highly penetrant gene mutation were excluded. Of the 324 009 eligible women, a random subcohort was selected, regardless of cancer status, to which all additional patients with breast cancer were added. The index screening mammographic examination was used as input for five AI algorithms to generate continuous scores that were compared with the BCSC clinical risk score. Risk estimates for incident breast cancer 0 to 5 years after the initial mammographic examination were calculated using a time-dependent area under the receiver operating characteristic curve (AUC). Results The subcohort included 13 628 patients, of whom 193 had incident cancer. Incident cancers in eligible patients (additional 4391 of 324 009) were also included. For incident cancers at 0 to 5 years, the time-dependent AUC for BCSC was 0.61 (95% CI: 0.60, 0.62). AI algorithms had higher time-dependent AUCs than did BCSC, ranging from 0.63 to 0.67 (Bonferroni-adjusted P < .0016). Time-dependent AUCs for combined BCSC and AI models were slightly higher than AI alone (AI with BCSC time-dependent AUC range, 0.66-0.68; Bonferroni-adjusted P < .0016). Conclusion When using a negative screening examination, AI algorithms performed better than the BCSC risk model for predicting breast cancer risk at 0 to 5 years. Combined AI and BCSC models further improved prediction. © RSNA, 2023 Supplemental material is available for this article.

1 October 2016 in American Journal of Roentgenology
Verified
Journal Article
Closed access
JHJessica H. Hayward
Jessica H. Hayward
KRKimberly M. Ray
Kimberly M. Ray
DWDorota J. Wisner
Dorota J. Wisner
JKJohn Kornak
John Kornak
WLWeiwen Lin
Weiwen Lin
ESEdward A. Sickles
Edward A. Sickles
OBJECTIVE. The objective of the present study is to evaluate the effect of comparison with multiple prior mammograms on the outcomes of screening mammography relative to comparison with a single prior mammogram. MATERIALS AND METHODS. We retrospectively analyzed 46,288 consecutive screening mammograms performed at our institution for 22,792 women. We divided these examinations into three groups: those interpreted without comparison with prior mammograms, those interpreted in comparison with one prior examination, and those interpreted in comparison with two or more prior examinations. For each group, we determined the rate of examination recall. We also calculated the positive predictive value of recall (i.e., positive predictive value level 1 [PPV1]) and the cancer detection rate (CDR) for both the group of examinations compared with a single prior mammogram and the group compared with multiple prior mammograms. Generalized estimating equations with the logistic link function were used to determine the r...

23 May 2022 in JCI Insight
Verified
Journal Article
Open access
PDF file
MDMatthew S. Durstenfeld
Matthew S. Durstenfeld
MPMichael J. Peluso
Michael J. Peluso
JKJohn Daniel Kelly
John Daniel Kelly
SWSithu Win
Sithu Win
SSShreya Swaminathan
Shreya Swaminathan
PHPriscilla Y. Hsue
Priscilla Y. Hsue
Shortness of breath, chest pain, and palpitations occur as postacute sequelae of COVID-19, but whether symptoms are associated with echocardiographic abnormalities, cardiac biomarkers, or markers of systemic inflammation remains unknown. In a cross-sectional analysis, we assessed symptoms, performed echocardiograms, and measured biomarkers among adults more than 8 weeks after confirmed SARS-CoV-2 infection. We modeled associations between symptoms and baseline characteristics, echocardiographic findings, and biomarkers using logistic regression. We enrolled 102 participants at a median of 7.2 months following COVID-19 onset; 47 individuals reported dyspnea, chest pain, or palpitations. Median age was 52 years, and 41% of participants were women. Female sex, hospitalization, IgG antibody against SARS-CoV-2 receptor binding domain, and C-reactive protein were associated with symptoms. Regarding echocardiographic findings, 4 of 47 participants (9%) with symptoms had pericardial effusions compared with 0 of 55 participants without symptoms; those with effusions had a median of 4 symptoms compared with a median of 1 symptom in those without effusions. There was no strong evidence for a relationship between symptoms and echocardiographic functional parameters or other biomarkers. Among adults more than 8 weeks after SARS-CoV-2 infection, SARS-CoV-2 RBD antibodies, markers of inflammation, and, possibly, pericardial effusions are associated with cardiopulmonary symptoms. Investigation into inflammation as a mechanism underlying postacute sequelae of COVID-19 is warranted.

2 March 2015 in Alzheimer's Research & Therapy
Verified
Journal Article
Open access
PDF file
SSSharon J Sha
Sharon J Sha
PGPia M Ghosh
Pia M Ghosh
SLSuzee E Lee
Suzee E Lee
CCChiara Corbetta-Rastelli
Chiara Corbetta-Rastelli
WJWillian J Jagust
Willian J Jagust
GRGil D Rabinovici
Gil D Rabinovici
Introduction: Group comparisons demonstrate greater visuospatial and memory deficits and temporoparietal-predominant degeneration on neuroimaging in patients with corticobasal syndrome (CBS) found to have Alzheimer’s disease (AD) pathology versus those with underlying frontotemporal lobar degeneration (FTLD). The value of these features in predicting underlying AD pathology in individual patients is unknown. The goal of this study is to evaluate the utility of modified clinical criteria and visual interpretations of magnetic resonance imaging (MRI) and fluorodeoxyglucose positron emission tomography (FDG-PET) for predicting amyloid deposition (as a surrogate of Alzheimer’s disease neuropathology) in patients presenting with CBS. Methods: In total, 25 patients meeting CBS core criteria underwent amyloid (Pittsburgh compound B; PIB) PET scans. Clinical records, MRI, and FDG scans were reviewed blinded to PIB results. Modified clinical criteria were used to classify CBS patients as temporoparietal variant CBS (tpvCBS) or frontal variant CBS (fvCBS). MRI and FDG-PET were classified based on the predominant atrophy/hypometabolism pattern (frontal or temporoparietal). Results: A total of 9 out of 13 patients classified as tpvCBS were PIB+, compared to 2out of 12 patients classified as fvCBS (P < 0.01, sensitivity 82%, specificity 71% for PIB+ status). Visual MRI reads had 73% sensitivity and 46% specificity for PIB+ status with moderate intra-rater reliability (Cohen’s kappa = 0.42). Visual FDG reads had higher sensitivity (91%) for PIB+ status with perfect intra-rater reliability (kappa = 1.00), though specificity was low (50%). PIB results were confirmed in all 8 patients with available histopathology (3 PIB+ with confirmed AD, 5 PIB- with FTLD). Conclusions: Splitting CBS patients into frontal or temporoparietal clinical variants can help predict the likelihood of underlying AD, but criteria require further refinement. Temporoparietal-predominant neuroimaging patterns are sensitive but not specific for AD.

13 September 2022 in Cancers
Verified
Journal Article
Open access
PDF file
WLWen Li
Wen Li
NLNu Ngoc Le
Nu Ngoc Le
NONatsuko Onishi
Natsuko Onishi
DNDavid C. Newitt
David C. Newitt
LWLisa J. Wilmes
Lisa J. Wilmes
NHNola Hylton
Nola Hylton
This study tested the hypothesis that a change in the apparent diffusion coefficient (ADC) measured in diffusion-weighted MRI (DWI) is an independent imaging marker, and ADC performs better than functional tumor volume (FTV) for assessing treatment response in patients with locally advanced breast cancer receiving neoadjuvant immunotherapy. A total of 249 patients were randomized to standard neoadjuvant chemotherapy with pembrolizumab (pembro) or without pembrolizumab (control). DCE-MRI and DWI, performed prior to and 3 weeks after the start of treatment, were analyzed. Percent changes of tumor ADC metrics (mean, 5th to 95th percentiles of ADC histogram) and FTV were evaluated for the prediction of pathologic complete response (pCR) using a logistic regression model. The area under the ROC curve (AUC) estimated for the percent change in mean ADC was higher in the pembro cohort (0.73, 95% confidence interval [CI]: 0.52 to 0.93) than in the control cohort (0.63, 95% CI: 0.43 to 0.83). In the control cohort, the percent change of the 95th percentile ADC achieved the highest AUC, 0.69 (95% CI: 0.52 to 0.85). In the pembro cohort, the percent change of the 25th percentile ADC achieved the highest AUC, 0.75 (95% CI: 0.55 to 0.95). AUCs estimated for percent change of FTV were 0.61 (95% CI: 0.39 to 0.83) and 0.66 (95% CI: 0.47 to 0.85) for the pembro and control cohorts, respectively. Tumor ADC may perform better than FTV to predict pCR at an early treatment time-point during neoadjuvant immunotherapy.

1 December 2019 in Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring
Verified
Journal Article
Open access
JKJohn Kornak
John Kornak
JFJulie Fields
Julie Fields
WKWalter Kremers
Walter Kremers
SFSara Farmer
Sara Farmer
HHHilary W. Heuer
Hilary W. Heuer
ACARTFL/LEFFTDS Consortium
ARTFL/LEFFTDS Consortium
Introduction: Conventional Z‐scores are generated by subtracting the mean and dividing by the standard deviation. More recent methods linearly correct for age, sex, and education, so that these “adjusted” Z‐scores better represent whether an individual's cognitive performance is abnormal. Extreme negative Z‐scores for individuals relative to this normative distribution are considered indicative of cognitive deficiency.Methods: In this article, we consider nonlinear shape constrained additive models accounting for age, sex, and education (correcting for nonlinearity). Additional shape constrained additive models account for varying standard deviation of the cognitive scores with age (correcting for heterogeneity of variance).Results: Corrected Z‐scores based on nonlinear shape constrained additive models provide improved adjustment for age, sex, and education, as indicated by higher adjusted‐R2.Discussion: Nonlinearly corrected Z‐scores with respect to age, sex, and education with age‐varying residual standard deviation allow for improved detection of non‐normative extreme cognitive scores.