Reconstructing the patient's natural history from electronic health records.

The automatic extraction of a patient's natural history from Electronic Health Records (EHRs) is a critical step towards building intelligent systems that can reason about clinical variables and support decision making. Although EHRs contain a large amount of valuable information about the patient's medical care, this information can only be fully understood when analyzed in a temporal context. Any intelligent system should then be able to extract medical concepts, date expressions, temporal relations and the temporal ordering of medical events from the free texts of EHRs; yet, this task is hard to tackle, due to the domain specific nature of EHRs, writing quality and lack of structure of these texts, and more generally the presence of redundant information. In this paper, we introduce a new Natural Language Processing (NLP) framework, capable of extracting the aforementioned elements from EHRs written in Spanish using rule-based methods. We focus on building medical timelines, which include disease diagnosis and its progression over time. By using a large dataset of EHRs comprising information about patients suffering from lung cancer, we show that our framework has an adequate level of performance by correctly building the timeline for 843 patients from a pool of 989 patients, achieving a precision of 0.852.

Profiling Lung Cancer Patients Using Electronic Health Records.

If Electronic Health Records contain a large amount of information about the patient's condition and response to treatment, which can potentially revolutionize the clinical practice, such information is seldom considered due to the complexity of its extraction and analysis. We here report on a first integration of an NLP framework for the analysis of clinical records of lung cancer patients making use of a telephone assistance service of a major Spanish hospital. We specifically show how some relevant data, about patient demographics and health condition, can be extracted; and how some relevant analyses can be performed, aimed at improving the usefulness of the service. We thus demonstrate that the use of EHR texts, and their integration inside a data analysis framework, is technically feasible and worth of further study.

Concordance between circulating tumor cells and clinical status during follow-up in anaplastic lymphoma kinase (ALK) non-small-cell lung cancer patients.

BACKGROUND: The identification of anaplastic lymphoma kinase (ALK) rearrangements is found in approximately 5% of non-small-cell lung cancers (NSCLCs). However, the development of liquid biopsies as a diagnostic tool is less developed in these cases. This study investigates the use of CTCs during treatment, together with an extended follow-up to correlate with clinical evolution. PATIENTS AND METHODS: A total of 13 patients out of a cohort of 212 patients with lung adenocarcinoma, presented ALK rearrangements (6%) confirmed by tumor biopsy. A total of 60 serial blood samples were collected from these patients who were prospectively enrolled in the study. RESULTS: All patients had a positive CTC count at baseline (mean = 3). The median follow-up was 9 months (range 1-17 months). Three patients underwent surgery and their CTC counts decreased after the procedure but still remained detectable. After radiotherapy, 3 cases showed an average decrease of 5 CTCs. A total of 6 patients were treated with ALK inhibitors and a partial response was observed in 3 of them, who also presented decreased CTC counts. The other 3 patients presented primary resistance, and their CTC counts were higher than those obtained prior to progression. CONCLUSION: We believe that the use of CTCs for dynamic monitoring of NSCLC with ALK rearrangement and to detect disease persistence or recurrence may be a reliable technique. CTC counts may also have potential use to monitor the efficacy of ALK inhibitors, facilitating detection of resistance to treatment.

Dynamic circulating tumor DNA quantificaton for the individualization of non-small-cell lung cancer patients treatment.

BACKGROUND: Liquid biopsy has evolved from being a promising line to becoming a validated approach for biomarker testing. However, its utility for individualization of therapy has been scarcely reported. In this study, we show how monitoring levels of EGFR mutation in plasma can be useful for the individualization of treatment. RESULTS: Longitudinal EGFR mutation levels in plasma always correlated with tumor response ascertained by RECIST criteria. Moreover, decreasing EGFR mutation levels were detected in all patients benefiting from locoregional radiotherapy, whereas the opposite occurred when a patient progressed soon after radiotherapy treatment. Similarly, increasing EGFR mutation levels anticipated disease progression after TKI dose reduction, discontinuation of treatment, or reduced bioavailability due to drug interactions. In addition, EGFR mutation levels were useful to monitor treatment outcome of new therapies and constituted a decisive factor when the clinical situation of the patient did not correlate with responses ascertained by radiologist. Finally, our results indicate that cancer associated body fluids (pleural, pericardial or cerebrospinal fluid) are certainly a suitable source for biomarker testing that can extend EGFR mutation detection to biofluids other than blood. MATERIALS AND METHODS: A total of 180 serial plasma samples from 18 non-small-cell lung cancer patients who carried an activating EGFR mutation were investigated by digital PCR. CONCLUSIONS: Monitoring levels of EGFR mutation in plasma allows resolving doubts that frequently arise in daily clinical practice and constitutes a major step towards achieving personalized medicine.