Matthew S Alkaitis MD, PhD is a Clinical Assistant Professor in the Division of Hospital medicine and Stanford School of Medicine. He received his PhD in biochemistry from the University of Oxford, in collaboration the National Institutes of Health as part of the NIH’s graduate partnership program. He received his MD from Harvard Medical school and completed his residency in internal medicine at Stanford. Dr. Alkaitis’ research interests span basic biochemistry, clinical informatics, natural language processing, genetics of hematologic malignancies and methods of cell-free DNA detection. His primary medical education interest is expanding accessibility of modern computational and bioinformatics techniques for clinical research.

Clinical Focus

  • Internal Medicine

Academic Appointments

  • Clinical Assistant Professor, Medicine

Professional Education

  • Residency: Stanford University Internal Medicine Residency (2023) CA
  • Medical Education: Harvard Medical School (2020) MA

All Publications

  • Development of Circulating Tumor DNA (ctDNA) for Molecular Measurable Residual Disease (MRD) in Acute Myeloid Leukemia (AML) Gunaratne, R., Zhou, C., Tai, J. W., Schwede, M., Tanaka, K., Alkaitis, M., Yin, R., Sworder, B. J., Mannis, G., Majeti, R., Khodadoust, M. S., Kurtz, D. M., Zhang, T. Y. AMER SOC HEMATOLOGY. 2023
  • Comparison of History of Present Illness Summaries Generated by a Chatbot and Senior Internal Medicine Residents. JAMA internal medicine Nayak, A., Alkaitis, M. S., Nayak, K., Nikolov, M., Weinfurt, K. P., Schulman, K. 2023

    View details for DOI 10.1001/jamainternmed.2023.2561

    View details for PubMedID 37459091

  • Automated NLP Extraction of Clinical Rationale for Treatment Discontinuation in Breast Cancer. JCO clinical cancer informatics Alkaitis, M. S., Agrawal, M. N., Riely, G. J., Razavi, P., Sontag, D. 2021; 5: 550-560


    Key oncology end points are not routinely encoded into electronic medical records (EMRs). We assessed whether natural language processing (NLP) can abstract treatment discontinuation rationale from unstructured EMR notes to estimate toxicity incidence and progression-free survival (PFS).We constructed a retrospective cohort of 6,115 patients with early-stage and 701 patients with metastatic breast cancer initiating care at Memorial Sloan Kettering Cancer Center from 2008 to 2019. Each cohort was divided into training (70%), validation (15%), and test (15%) subsets. Human abstractors identified the clinical rationale associated with treatment discontinuation events. Concatenated EMR notes were used to train high-dimensional logistic regression and convolutional neural network models. Kaplan-Meier analyses were used to compare toxicity incidence and PFS estimated by our NLP models to estimates generated by manual labeling and time-to-treatment discontinuation (TTD).Our best high-dimensional logistic regression models identified toxicity events in early-stage patients with an area under the curve of the receiver-operator characteristic of 0.857 ± 0.014 (standard deviation) and progression events in metastatic patients with an area under the curve of 0.752 ± 0.027 (standard deviation). NLP-extracted toxicity incidence and PFS curves were not significantly different from manually extracted curves (P = .95 and P = .67, respectively). By contrast, TTD overestimated toxicity in early-stage patients (P < .001) and underestimated PFS in metastatic patients (P < .001). Additionally, we tested an extrapolation approach in which 20% of the metastatic cohort were labeled manually, and NLP algorithms were used to abstract the remaining 80%. This extrapolated outcomes approach resolved PFS differences between receptor subtypes (P < .001 for hormone receptor+/human epidermal growth factor receptor 2- v human epidermal growth factor receptor 2+ v triple-negative) that could not be resolved with TTD.NLP models are capable of abstracting treatment discontinuation rationale with minimal manual labeling.

    View details for DOI 10.1200/CCI.20.00139

    View details for PubMedID 33989016

    View details for PubMedCentralID PMC8462597

  • Recoupling the cardiac nitric oxide synthases: tetrahydrobiopterin synthesis and recycling. Current heart failure reports Alkaitis, M. S., Crabtree, M. J. 2012; 9 (3): 200-10


    Nitric oxide (NO), a key regulator of cardiovascular function, is synthesized from L-arginine and oxygen by the enzyme nitric oxide synthase (NOS). This reaction requires tetrahydrobiopterin (BH4) as a cofactor. BH4 is synthesized from guanosine triphosphate (GTP) by GTP cyclohydrolase I (GTPCH) and recycled from 7,8-dihydrobiopterin (BH2) by dihydrofolate reductase. Under conditions of low BH4 bioavailability relative to NOS or BH2, oxygen activation is "uncoupled" from L-arginine oxidation, and NOS produces superoxide (O (2) (-) ) instead of NO. NOS-derived superoxide reacts with NO to produce peroxynitrite (ONOO(-)), a highly reactive anion that rapidly oxidizes BH4 and propagates NOS uncoupling. BH4 depletion and NOS uncoupling contribute to overload-induced heart failure, hypertension, ischemia/reperfusion injury, and atrial fibrillation. L-arginine depletion, methylarginine accumulation, and S-glutathionylation of NOS also promote uncoupling. Recoupling NOS is a promising approach to treating myocardial and vascular dysfunction associated with heart failure.

    View details for DOI 10.1007/s11897-012-0097-5

    View details for PubMedID 22711313

    View details for PubMedCentralID PMC3406312