Herbert A. Fritsche
Research Subjects
Herbert A. Fritsche has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Rowan G. Bullock
Aspira Women's Health, Trumbull, CT
2 shared publications Charles J. Dunton
Aspira Women's Health, Trumbull, CT
1 shared publicationDaniel R. Ure
Aspira Women's Health, Trumbull, CT
1 shared publicationElizabeth Carney
Peaceful Pet Passages, York, PA, USA
1 shared publicationErin Stewart
Aspira Women's Health, Trumbull, CT
1 shared publication- Ferras Albitar
NeoGenomics Laboratories, Irvine, CA
1 shared publication
Latest Publications
- Open Access
- 7 June 2022
- Published by American Society of Clinical Oncology (ASCO) in JCO Clinical Cancer Informatics
- Vol. 6 (6) , e2100192
Analytical Validation of a Deep Neural Network Algorithm for the Detection of Ovarian Cancer
PURPOSE: Early detection of ovarian cancer, the deadliest gynecologic cancer, is crucial for reducing mortality. Current noninvasive risk assessment measures include protein biomarkers in combination with other clinical factors, which vary in their accuracy. Machine learning can be applied to optimizing the combination of these features, leading to more accurate assessment of malignancy. However, the low prevalence of the disease can make rigorous validation of these tests challenging and can result in unbalanced performance. METHODS: MIA3G is a deep feedforward neural network for ovarian cancer risk assessment, using seven protein biomarkers along with age and menopausal status as input features. The algorithm was developed on a heterogenous data set of 1,067 serum specimens from women with adnexal masses (prevalence = 31.8%). It was subsequently validated on a cohort almost twice that size (N = 2,000). RESULTS: In the analytical validation data set (prevalence = 4.9%), MIA3G demonstrated a sensitivity of 89.8% and a specificity of 84.02%. The positive predictive value was 22.45%, and the negative predictive value was 99.38%. When stratified by cancer type and stage, MIA3G achieved sensitivities of 94.94% for epithelial ovarian cancer, 76.92% for early-stage cancer, and 98.04% for late-stage cancer. CONCLUSION: The balanced performance of MIA3G leads to a high sensitivity and high specificity, a combination that may be clinically useful for providers in evaluating the appropriate management strategy for their patients. Limitations of this work include the largely retrospective nature of the data set and the unequal, albeit random, assignment of histologic subtypes between the training and validation data sets. Future directions may include the addition of new biomarkers or other modalities to strengthen the performance of the algorithm.
- 7 June 2022
- Published by American Society of Clinical Oncology (ASCO) in JCO Clinical Cancer Informatics
- Vol. 6 (6) , e2100192
Open AccessAnalytical Validation of a Deep Neural Network Algorithm for the Detection of Ovarian Cancer
PURPOSE: Early detection of ovarian cancer, the deadliest gynecologic cancer, is crucial for reducing mortality. Current noninvasive risk assessment measures include protein biomarkers in combination with other clinical factors, which vary in their accuracy. Machine learning can be applied to optimizing the combination of these features, leading to more accurate assessment of malignancy. However, the low prevalence of the disease can make rigorous validation of these tests challenging and can result in unbalanced performance. METHODS: MIA3G is a deep feedforward neural network for ovarian cancer risk assessment, using seven protein biomarkers along with age and menopausal status as input features. The algorithm was developed on a heterogenous data set of 1,067 serum specimens from women with adnexal masses (prevalence = 31.8%). It was subsequently validated on a cohort almost twice that size (N = 2,000). RESULTS: In the analytical validation data set (prevalence = 4.9%), MIA3G demonstrated a sensitivity of 89.8% and a specificity of 84.02%. The positive predictive value was 22.45%, and the negative predictive value was 99.38%. When stratified by cancer type and stage, MIA3G achieved sensitivities of 94.94% for epithelial ovarian cancer, 76.92% for early-stage cancer, and 98.04% for late-stage cancer. CONCLUSION: The balanced performance of MIA3G leads to a high sensitivity and high specificity, a combination that may be clinically useful for providers in evaluating the appropriate management strategy for their patients. Limitations of this work include the largely retrospective nature of the data set and the unequal, albeit random, assignment of histologic subtypes between the training and validation data sets. Future directions may include the addition of new biomarkers or other modalities to strengthen the performance of the algorithm.
- Open Access
- 2 June 2020
- Published by Wiley in Veterinary Medicine and Science
- Vol. 6 (4) , 933-945
Survey of canine use and safety of isoxazoline parasiticides
A veterinarian and pet owner survey (Project Jake) examined the use and safety of isoxazoline parasiticides given to dogs. Data were received during August 1–31, 2018 from a total of 2,751 survey responses. Forty‐two percent (1,157) reported no flea treatment or adverse events (AE), while 58% (1594) had been treated with some parasiticide for flea control, and of those that received a parasiticide, the majority, or 83% (1,325), received an isooxazoline. When any flea treatment was given, AE were reported for 66.6% of respondents, with no apparent AE noted for 36.1%. Project Jake findings were compared to a retrospective analysis of publicly available Food and Drug Administration (FDA) and European Medicines Agency (EMA) reported AE. The number of total AE reported to FDA and EMA were comparable, although a 7 to 10 times higher occurrence of death and seizures was reported from the EMA or from outside the United States (US). Serious AE responses for death, seizures and neurological effects reported in our survey were higher than the FDA but moderately lower than the EMA reports. These sizable global data sets combined with this pre‐ and post‐parasiticide administration survey indicated that isoxazoline neurotoxicity was not flea‐ and tick‐specific. Post‐marketing serious AE were much higher than in Investigational New Drug (IND) submissions. Although the labels have recently been updated, dogs, cats and their caregivers remain impacted by their use. These aggregate data reports support the need for continued cross‐species studies and critical review of product labelling by regulatory agencies and manufacturers.
- 2 June 2020
- Published by Wiley in Veterinary Medicine and Science
- Vol. 6 (4) , 933-945
Open AccessSurvey of canine use and safety of isoxazoline parasiticides
A veterinarian and pet owner survey (Project Jake) examined the use and safety of isoxazoline parasiticides given to dogs. Data were received during August 1–31, 2018 from a total of 2,751 survey responses. Forty‐two percent (1,157) reported no flea treatment or adverse events (AE), while 58% (1594) had been treated with some parasiticide for flea control, and of those that received a parasiticide, the majority, or 83% (1,325), received an isooxazoline. When any flea treatment was given, AE were reported for 66.6% of respondents, with no apparent AE noted for 36.1%. Project Jake findings were compared to a retrospective analysis of publicly available Food and Drug Administration (FDA) and European Medicines Agency (EMA) reported AE. The number of total AE reported to FDA and EMA were comparable, although a 7 to 10 times higher occurrence of death and seizures was reported from the EMA or from outside the United States (US). Serious AE responses for death, seizures and neurological effects reported in our survey were higher than the FDA but moderately lower than the EMA reports. These sizable global data sets combined with this pre‐ and post‐parasiticide administration survey indicated that isoxazoline neurotoxicity was not flea‐ and tick‐specific. Post‐marketing serious AE were much higher than in Investigational New Drug (IND) submissions. Although the labels have recently been updated, dogs, cats and their caregivers remain impacted by their use. These aggregate data reports support the need for continued cross‐species studies and critical review of product labelling by regulatory agencies and manufacturers.
- Open Access
- 1 January 2016
- Published by Ivyspring International Publisher in Journal of Cancer
- Vol. 7 (3) , 297-303
Predicting Prostate Biopsy Results Using a Panel of Plasma and Urine Biomarkers Combined in a Scoring System
Background: Determining the need for prostate biopsy is frequently difficult and more objective criteria are needed to predict the presence of high grade prostate cancer (PCa). To reduce the rate of unnecessary biopsies, we explored the potential of using biomarkers in urine and plasma to develop a scoring system to predict prostate biopsy results and the presence of high grade PCa.
- 1 January 2016
- Published by Ivyspring International Publisher in Journal of Cancer
- Vol. 7 (3) , 297-303
Open AccessPredicting Prostate Biopsy Results Using a Panel of Plasma and Urine Biomarkers Combined in a Scoring System
Background: Determining the need for prostate biopsy is frequently difficult and more objective criteria are needed to predict the presence of high grade prostate cancer (PCa). To reduce the rate of unnecessary biopsies, we explored the potential of using biomarkers in urine and plasma to develop a scoring system to predict prostate biopsy results and the presence of high grade PCa.