Showing papers by "Amy Chadburn published in 2020"

Routine Laboratory Blood Tests Predict SARS-CoV-2 Infection Using Machine Learning.

Abstract: Background Accurate diagnostic strategies to identify SARS-CoV-2 positive individuals rapidly for management of patient care and protection of health care personnel are urgently needed. The predominant diagnostic test is viral RNA detection by RT-PCR from nasopharyngeal swabs specimens, however the results are not promptly obtainable in all patient care locations. Routine laboratory testing, in contrast, is readily available with a turn-around time (TAT) usually within 1-2 hours. Method We developed a machine learning model incorporating patient demographic features (age, sex, race) with 27 routine laboratory tests to predict an individual's SARS-CoV-2 infection status. Laboratory testing results obtained within 2 days before the release of SARS-CoV-2 RT-PCR result were used to train a gradient boosting decision tree (GBDT) model from 3,356 SARS-CoV-2 RT-PCR tested patients (1,402 positive and 1,954 negative) evaluated at a metropolitan hospital. Results The model achieved an area under the receiver operating characteristic curve (AUC) of 0.854 (95% CI: 0.829-0.878). Application of this model to an independent patient dataset from a separate hospital resulted in a comparable AUC (0.838), validating the generalization of its use. Moreover, our model predicted initial SARS-CoV-2 RT-PCR positivity in 66% individuals whose RT-PCR result changed from negative to positive within 2 days. Conclusion This model employing routine laboratory test results offers opportunities for early and rapid identification of high-risk SARS-CoV-2 infected patients before their RT-PCR results are available. It may play an important role in assisting the identification of SARS-CoV-2 infected patients in areas where RT-PCR testing is not accessible due to financial or supply constraints.

Routine laboratory blood tests predict SARS-CoV-2 infection using machine learning

Abstract: Background: Accurate diagnostic strategies to rapidly identify SARS-CoV-2 positive individuals for management of patient care and protection of health care personnel are urgently needed The predominant diagnostic test is viral RNA detection by RT-PCR from nasopharyngeal swabs specimens, however the results are not promptly obtainable in all patient care locations Routine laboratory testing, in contrast, is readily available with a turn-around time (TAT) usually within 1-2 hours Method: We developed a machine learning model incorporating patient demographic features (age, sex, race) with 27 routine laboratory tests to predict an individual9s SARS-CoV-2 infection status Laboratory test results obtained within two days before the release of SARS-CoV-2-RT-PCR result were used to train a gradient boosted decision tree (GBDT) model from 3,356 SARS-CoV-2 RT-PCR tested patients (1,402 positive and 1,954 negative) evaluated at a metropolitan hospital Results: The model achieved an area under the receiver operating characteristic curve (AUC) of 0854 (95% CI: 0829-0878) Application of this model to an independent patient dataset from a separate hospital resulted in a comparable AUC (0838), validating the generalization of its use Moreover, our model predicted initial SARS-CoV-2 RT-PCR positivity in 66% individuals whose RT-PCR result changed from negative to positive within two days Conclusion: This model employing routine laboratory test results offers opportunities for early and rapid identification of high-risk SARS-CoV-2 infected patients before their RT-PCR results are available It may play an important role in assisting the identification of SARS-COV-2 infected patients in areas where RT-PCR testing is not accessible due to financial or supply constraints

Chronic Myelogenous Leukemia Diagnosed in the Setting of Untreated Chronic Lymphocytic Leukemia/Small Lymphocytic Lymphoma.

Abstract: Chronic myeloid leukemia (CML) is rarely reported to occur in treated chronic lymphocytic leukemia/small lymphocytic lymphoma (CLL/SLL). In this article, we report a woman in her 70s, diagnosed with CLL/SLL in 2000, untreated, who subsequently presented 12 years later with de novo CML, BCR-ABL1+. Her IGHV mutated CLL/SLL based on the initial sample in our laboratory showed homozygous and heterozygous 13q14.3 deletions, whereas her CML, at presentation, showed a 46,XX,t(9;22)(q34;q11.2)[7]/46,XX[18] karyotype with a p190 BCR-ABL1 transcript. The tumor burden of each clone varied with treatment, including when treated with dasatinib, used to target both clones. In addition, the cytogenetic abnormalities evolved over time and treatments and included acquisition of an extra chromosome 8 in the CML clone and a novel K1992T ATM missense mutation (47% allele frequency) in the CLL/SLL clone. The patient's last bone marrow biopsy, 5 years after her CML diagnosis and 17 years after the CLL/SLL diagnosis, showed residual CML with extensive involvement by CLL/SLL (80%). Cytogenetic studies showed a 46,XX karyotype, while FISH identified 13q14.3 deletion and the BCR-ABL1 translocation in the CLL/SLL and CML clones, respectively. To date, this is the fourth case of concurrent CML, BCR-ABL1+ arising in untreated CLL/SLL. Here we show dynamic variation in the size of the 2 clonal processes reflecting the variable responsiveness to specific therapies. In addition to the unusual BCR-ABL1+ p190 transcript in the patient's CML, a novel ATM K1992T mutation was identified in the CLL/SLL population.