John Kirkpatrick

Overview:

Malignant and benign tumors of the brain, spine and base of skull. Mathematical modelling of tumor metabolism, mass transfer and the response to ionizing radiation. Enhancing clinical outcome in stereotactic radiosurgery, fractionated stereotactic radiotherapy and stereotactic body radiotherapy.

Positions:

Professor of Radiation Oncology

Radiation Oncology
School of Medicine

Professor in Neurosurgery

Neurosurgery
School of Medicine

Member of the Duke Cancer Institute

Duke Cancer Institute
School of Medicine

Education:

Ph.D. 1978

Rice University

M.D. 1999

University of Texas Health Science Center San Antonio

Grants:

Validation of Novel Therapeutic Approach for Leptomeningeal Metastases

Administered By
Neurosurgery
Role
Investigator
Start Date
End Date

BMX-001 AS A THERAPEUTIC AGENT FOR TREATMENT OF MULTIPLE BRAIN METASTASES

Administered By
Radiation Oncology
Role
Principal Investigator
Start Date
End Date

Publications:

An investigation of machine learning methods in delta-radiomics feature analysis.

PURPOSE: This study aimed to investigate the effectiveness of using delta-radiomics to predict overall survival (OS) for patients with recurrent malignant gliomas treated by concurrent stereotactic radiosurgery and bevacizumab, and to investigate the effectiveness of machine learning methods for delta-radiomics feature selection and building classification models. METHODS: The pre-treatment, one-week post-treatment, and two-month post-treatment T1 and T2 fluid-attenuated inversion recovery (FLAIR) MRI were acquired. 61 radiomic features (intensity histogram-based, morphological, and texture features) were extracted from the gross tumor volume in each image. Delta-radiomics were calculated between the pre-treatment and post-treatment features. Univariate Cox regression and 3 multivariate machine learning methods (L1-regularized logistic regression [L1-LR], random forest [RF] or neural networks [NN]) were used to select a reduced number of features, and 7 machine learning methods (L1-LR, L2-LR, RF, NN, kernel support vector machine [KSVM], linear support vector machine [LSVM], or naïve bayes [NB]) was used to build classification models for predicting OS. The performances of the total 21 model combinations built based on single-time-point radiomics (pre-treatment, one-week post-treatment, and two-month post-treatment) and delta-radiomics were evaluated by the area under the receiver operating characteristic curve (AUC). RESULTS: For a small cohort of 12 patients, delta-radiomics resulted in significantly higher AUC than pre-treatment radiomics (p-value<0.01). One-week/two-month delta-features resulted in significantly higher AUC (p-value<0.01) than the one-week/two-month post-treatment features, respectively. 18/21 model combinations were with higher AUC from one-week delta-features than two-month delta-features. With one-week delta-features, RF feature selector + KSVM classifier and RF feature selector + NN classifier showed the highest AUC of 0.889. CONCLUSIONS: The results indicated that delta-features could potentially provide better treatment assessment than single-time-point features. The treatment assessment is substantially affected by the time point for computing the delta-features and the combination of machine learning methods for feature selection and classification.
Authors
Chang, Y; Lafata, K; Sun, W; Wang, C; Chang, Z; Kirkpatrick, JP; Yin, F-F
MLA Citation
Chang, Yushi, et al. “An investigation of machine learning methods in delta-radiomics feature analysis..” Plos One, vol. 14, no. 12, 2019. Pubmed, doi:10.1371/journal.pone.0226348.
URI
https://scholars.duke.edu/individual/pub1423241
PMID
31834910
Source
pubmed
Published In
Plos One
Volume
14
Published Date
Start Page
e0226348
DOI
10.1371/journal.pone.0226348

Pre-operative stereotactic radiosurgery treatment is preferred to post-operative treatment for smaller solitary brain metastases

© 2017 The Author(s). Background: While the optimal combination of whole-brain radiotherapy (WBRT), stereotactic radiosurgery (SRS) and surgical resection in the treatment of brain metastases, is controversial, the addition of SRS to surgical resction of solitary metastasis may enhance local control while potentially minimizing toxicity associated with adjuvant WBRT. This study seeks to determine whether pre-operative SRS to the lesion versus post-operative SRS to the resection bed may reduce irradiation of adjacent normal brain tissue. Methods: A retrospective study of 12 patients with 13 surgically resected cerebral metastases was performed. The pre-operative contrast-enhancing tumors and post-operative resection cavities plus any enhancing residual disease were contoured to yield the gross target volume (GTV). In turn these GTV's were uniformly expanded by 3-mm to generate the pre-operative, as well as post-operative planning target volume (PTV.) For each lesion, a 7-static-conformal-beam, non-coplanar plan utilizing 6 MV photons was generated to encompass the PTV within the 85% isodose line. Excess normal brain volume irradiated was defined as the volume outside the GTV receiving the prescribed dose. Results: When lesions were divided into two groups - Group A (pre-operative GTV's < 15 cc, n = 9) and Group B (pre-operative GTV's > 15 cc, n = 4) - the average volume of normal brain irradiated was significantly smaller if pre-operative SRS was used for treatment of lesions in Group A (9.5 vs. 16.8 cc, paired t-test, p = 0.0045). In contrast, this volume was smaller for Group B lesions if post-operative SRS was used for treatment of these lesions (27.6 vs. 51.2 cc, p = 0.252). A comparison of groups with respect to mean volume differences between pre- and post-operative SRS was significantly different (two-sample t-test p = 0.016). GTV and the difference between pre- and post-operative volume were highly correlated (Pearson correlation = -0.875, p < 0.0001). Conclusions: Pre-operative treatment of smaller metastases may result in reduced radiation dose to normal tissue and, thus, reduced treatment-related morbidity compared to post-operative irradiation of the resection cavity.
Authors
Aliabadi, H; Nikpour, AM; Yoo, DS; Herndon, JE; Sampson, JH; Kirkpatrick, JP
MLA Citation
Aliabadi, H., et al. “Pre-operative stereotactic radiosurgery treatment is preferred to post-operative treatment for smaller solitary brain metastases.” Chinese Neurosurgical Journal, vol. 3, no. 1, Oct. 2017. Scopus, doi:10.1186/s41016-017-0092-5.
URI
https://scholars.duke.edu/individual/pub1423575
Source
scopus
Published In
Chinese Neurosurgical Journal
Volume
3
Published Date
DOI
10.1186/s41016-017-0092-5

Offer Hypofractionated SRS… If Her Performance Status Is Good.

MLA Citation
Kirkpatrick, John P., and Peter E. Fecci. “Offer Hypofractionated SRS… If Her Performance Status Is Good..” Int J Radiat Oncol Biol Phys, vol. 105, no. 5, Dec. 2019, pp. 940–41. Pubmed, doi:10.1016/j.ijrobp.2018.07.001.
URI
https://scholars.duke.edu/individual/pub1418111
PMID
31668512
Source
pubmed
Published In
Int J Radiat Oncol Biol Phys
Volume
105
Published Date
Start Page
940
End Page
941
DOI
10.1016/j.ijrobp.2018.07.001

Management of Unruptured AVMs: The Pendulum Swings.

Authors
Chan, MD; Soltys, SG; Halasz, LM; Laack, NN; Minniti, G; Kirkpatrick, JP
MLA Citation
Chan, Michael D., et al. “Management of Unruptured AVMs: The Pendulum Swings..” Int J Radiat Oncol Biol Phys, vol. 105, no. 4, Nov. 2019, pp. 687–89. Pubmed, doi:10.1016/j.ijrobp.2019.08.026.
URI
https://scholars.duke.edu/individual/pub1417071
PMID
31655651
Source
pubmed
Published In
Int J Radiat Oncol Biol Phys
Volume
105
Published Date
Start Page
687
End Page
689
DOI
10.1016/j.ijrobp.2019.08.026

The role of chemotherapy in the treatment of central neurocytoma.

Aim: Central neurocytoma (CN) is a rare WHO grade II central nervous system (CNS) tumor. This is an update on chemotherapeutic agents used in its treatment. Patients & methods: An institutional review board-approved, chart review of patients seen at our institution resulted in a single case treated with chemotherapy and is herein included. We proceeded with a comprehensive literature review. Results: We identified 18 citations, representing 39 cases of adult and pediatric CN treated with chemotherapy. With the addition of our single case, the total number of recurrent CN patients treated with temozolomide (TMZ) is nine. Conclusion: There exists marked heterogeneity in chemotherapy used to treat CN. TMZ is incorporated into treatment regimens in the setting of tumor recurrence: its role merits further study.
MLA Citation
Johnson, Margaret O., et al. “The role of chemotherapy in the treatment of central neurocytoma..” Cns Oncol, vol. 8, no. 3, Nov. 2019. Pubmed, doi:10.2217/cns-2019-0012.
URI
https://scholars.duke.edu/individual/pub1417984
PMID
31686534
Source
pubmed
Published In
Cns Oncology
Volume
8
Published Date
Start Page
CNS41
DOI
10.2217/cns-2019-0012