Text analysis framework for identifying mutations among non-small cell lung cancer patients from laboratory data.

BACKGROUND: Laboratory data can provide great value to support research aimed at reducing the incidence, prolonging survival and enhancing outcomes of cancer. Data is characterized by the information it carries and the format it holds. Data captured in Alberta's biomarker laboratory repository is free text, cluttered and rouge. Such data format limits its utility and prohibits broader adoption and research development. Text analysis for information extraction of unstructured data can change this and lead to more complete analyses. Previous work on extracting relevant information from free text, unstructured data employed Natural Language Processing (NLP), Machine Learning (ML), rule-based Information Extraction (IE) methods, or a hybrid combination between them. METHODS: In our study, text analysis was performed on Alberta Precision Laboratories data which consisted of 95,854 entries from the Southern Alberta Dataset (SAD) and 6944 entries from the Northern Alberta Dataset (NAD). The data covers all of Alberta and is completely population-based. Our proposed framework is built around rule-based IE methods. It incorporates topics such as Syntax and Lexical analyses to achieve deterministic extraction of data from biomarker laboratory data (i.e., Epidermal Growth Factor Receptor (EGFR) test results). Lexical analysis compromises of data cleaning and pre-processing, Rich Text Format text conversion into readable plain text format, and normalization and tokenization of text. The framework then passes the text into the Syntax analysis stage which includes the rule-based method of extracting relevant data. Rule-based patterns of the test result are identified, and a Context Free Grammar then generates the rules of information extraction. Finally, the results are linked with the Alberta Cancer Registry to support real-world cancer research studies. RESULTS: Of the original 5512 entries in the SAD dataset and 5017 entries in the NAD dataset which were filtered for EGFR, the framework yielded 5129 and 3388 extracted EGFR test results from the SAD and NAD datasets, respectively. An accuracy of 97.5% was achieved on a random sample of 362 tests. CONCLUSIONS: We presented a text analysis framework to extract specific information from unstructured clinical data. Our proposed framework has shown that it can successfully extract relevant information from EGFR test results.

The association between neighborhood-level income and cancer stage at diagnosis and survival in Alberta.

BACKGROUND: Socioeconomic status (SES) is associated with a range of health outcomes, including cancer diagnosis and survival. However, the evidence for this association is inconsistent between countries with and without single-payer health care systems. In this study, the relationships between neighborhood-level income, cancer stage at diagnosis, and cancer-specific mortality in Alberta, Canada, were evaluated. METHODS: The Alberta Cancer Registry was used to identify all primary cancer diagnoses between 2010 and 2020. Average neighborhood income was determined by linking the Canadian census to postal codes and was categorized into quintiles on the basis of income distribution in Alberta. Multivariable multinomial logistic regression was used to model the association between income quintile and stage at diagnosis, and the Fine-Gray proportional subdistribution hazards model was used to estimate the association between SES and cancer-specific mortality. RESULTS: Out of the 143,818 patients with cancer included in the study, those in lower income quintiles were significantly more likely to be diagnosed at stage III (odds ratio [OR], 1.07; 95% CI [confidence interval], 1.06-1.09) or IV (OR, 1.12; 95% CI, 1.11-1.14) after adjusting for age and sex. Lower income quintiles also had significantly worse cancer-specific survival for breast, colorectal, liver, lung, non-Hodgkin lymphoma, oral cavity, pancreas, and prostate cancers. CONCLUSIONS: Disparities were observed in cancer outcomes across neighborhood-level income groups in Alberta, which demonstrates that health inequities by SES exist in countries with single-payer health care systems. Further research is needed to better understand the underlying causes and to develop strategies to mitigate these disparities.

External Validation of the FLIPI Risk Score Measured at Diagnosis and POD24 Among Individuals With Follicular Lymphoma at the Time of Subsequent Relapse.

BACKGROUND: The Follicular lymphoma international prognostic index (FLIPI) risk score and POD24 have previously been shown to have prognostic value in follicular lymphoma (FL), but the extent to which they can inform prognosis at the time of subsequent relapse is uncertain. PATIENTS AND METHODS: We conducted a longitudinal cohort study of individuals diagnosed with FL between 2004 and 2010 in Alberta, Canada who received front-line therapy and subsequently relapsed. FLIPI covariates were measured prior to the initiation of front-line therapy. Median overall survival (OS), progression-free survival (PFS2), and time to next treatment (TTNT2) were estimated from the time of relapse. RESULTS: A total of 216 individuals were included. The FLIPI risk score was highly prognostic at the time of relapse for OS (c-statistic = 0.70; HR[High vs. Low] = 7.38; 95% CI: 3.05-17.88), PFS2 (c-statistic = 0.68; HR[High vs. Low] = 5.84; 95% CI: 2.93-11.62) and TTNT2 (c-statistic = 0.68; HR[High vs. Low] = 5.72; 95% CI: 2.87-11.41). POD24 was not prognostic at the time of relapse for either OS, PFS2, or TTNT2 (c-statistic = 0.55). CONCLUSION: The FLIPI score measured at diagnosis may help with the risk stratification of individuals with relapsed FL.

Improvement in patient-reported pain among patients with metastatic cancer and its association with opioid prescribing.

PURPOSE: Opioids are a mainstay of cancer pain management; however, patients with metastatic cancer are often excluded from studies, leading to a lack of evidence on whether increased prescribing (dosage and/or duration) results in improved outcomes for this population. This study aimed to investigate whether increased opioid prescribing is associated with an improvement in patient-reported pain among patients with metastatic cancer. PATIENTS AND METHODS: A retrospective cohort of all adult patients diagnosed with stage IV cancers, who completed at least two patient-reported outcomes (PROs) within 30 days of each other, was identified from administrative data. Opioid prescriptions were categorized by dosage level and number of prescription days. Multivariable logistic regression was used to investigate the association between opioid prescribing and clinically important improvement in pain score (≥ 1 point change on the Edmonton Symptom Assessment System). RESULTS: A total of 2169 patients were included, 770 (35.5%) of whom had active opioid prescription between PROs, with an average daily dosage of 86.1 mg of oral morphine equivalent. Active prescription was associated with improvement in pain (OR = 2.17, P < 0.001). However, among patients with active prescription, neither dosage nor number of prescription days was significantly associated with pain improvement. CONCLUSION: Opioid prescription is important for treating cancer-related pain; however, increased dosage or duration may not be leading to greater improvements in pain. Patients with metastatic cancer who are receiving increased opioid prescribing may have difficult-to-treat pain and may benefit from multidisciplinary pain management strategies to supplement opioid prescription and improve outcomes.

Impact of the COVID-19 pandemic on cancer diagnoses, stage and survival in Alberta.

BACKGROUND: The COVID-19 pandemic is suspected to have affected cancer care and outcomes among patients in Canada. In this study, we evaluated the impact of the state of emergency period during the COVID-19 pandemic (Mar. 17 to June 15, 2020) on cancer diagnoses, stage at diagnosis and 1-year survival in Alberta. METHODS: We included new diagnoses of the 10 most prevalent cancer types from Jan. 1, 2018, to Dec. 31, 2020. We followed patients up to Dec. 31, 2021. We used interrupted time series analysis to examine the impact of the first COVID-19-related state of emergency in Alberta on the number of cancer diagnoses. We used multivariable Cox regression to compare 1-year survival of the patients who received a diagnosis during 2020 after the state of emergency with those who received a diagnosis during 2018 and 2019. We also performed stage-specific analyses. RESULTS: We observed significant reductions in diagnoses of breast cancer (incidence rate ratio [IRR] 0.67, 95% confidence interval [CI] 0.59-0.76), prostate cancer (IRR 0.64, 95% CI 0.56-0.73) and colorectal cancer (IRR 0.64, 95% CI 0.56- 0.74) and melanoma (IRR 0.57, 95% CI 0.47-0.69) during the state of emergency period compared with the period before it. These decreases largely occurred among early-stage rather than late-stage diagnoses. Patients who received a diagnosis of colorectal cancer, non-Hodgkin lymphoma and uterine cancer in 2020 had lower 1-year survival than those diagnosed in 2018; no other cancer sites had lower survival. INTERPRETATION: The results from our analyses suggest that health care disruptions during the COVID-19 pandemic in Alberta considerably affected cancer outcomes. Given that the largest impact was observed among early-stage cancers and those with organized screening programs, additional system capacity may be needed to mitigate future impact.

Selection Bias in Real-World Data Studies Used to Support Health Technology Assessments: A Case Study in Metastatic Cancer.

Real-world evidence has been increasingly used to support evaluations of emerging therapies. These investigations are often conducted in settings that may not be representative of the underlying population. The purpose of this investigation was to empirically quantify the magnitude of this selection bias. Individuals diagnosed with solid metastatic cancer in Alberta, Canada, between 2010-2019 were identified using the provincial cancer registry for 13 common metastatic sites. Two outcomes used to support oncology reimbursement decisions were examined: the proportion of individuals who initiated systemic therapy and median overall survival (OS). These outcomes were assessed in the entire population and in a subset of individuals who were referred to a medical oncologist. Among the 23,152 individuals in the entire population, 40.8% (95% CI: 40.2-41.4) initiated systemic therapy, and the median OS from diagnosis was 5.4 months (95% CI: 5.3-5.6). Among those who were referred to a medical oncologist (n = 13,372; 57.8%), 67.4% (95% CI: 66.6-68.2) initiated systemic therapy, and the median OS from diagnosis was 11.2 months (95% CI: 10.9-11.5). The magnitude of bias varied by cancer site where lower referral rates were associated with greater bias. Non-referral is an important source of selection bias in real-world investigations. Studies that rely on limited-catchment real-world data should be interpreted with caution, particularly in metastatic cancer settings.

The impact of population-based EGFR testing in non-squamous metastatic non-small cell lung cancer in Alberta, Canada.

OBJECTIVES: While Epidermal Growth Factor Receptor (EGFR) Tyrosine Kinase Inhibitors have been shown to be effective in phase III randomized trials, the value of targeted therapies has been challenging to evaluate at the population-level. We examined the impact of population-level EGFR testing and treatment on survival outcomes among non-squamous metastatic Non-Small Cell Lung Cancer (NSCLC) patients. MATERIALS AND METHODS: Real-world, population-level data were collected from all de novo non-squamous metastatic NSCLC patients in Alberta, Canada from 2004 to 2020. EGFR testing data were collected through Alberta Precision Laboratories. Differences in survival rates and overall survival (OS) pre (2004-2012) and post initiation (post) (2013-2019) testing periods were evaluated using interrupted time series analyses. The impact of testing and subsequent treatment was evaluated using multivariable Cox Proportional Hazards models. RESULTS: In total, 4,578 non-squamous metastatic NSCLC patients were diagnosed pre-EGFR testing and 4,457 patients were diagnosed post-EGFR testing (2013-2019). Among patients diagnosed in the pre-EGFR testing period, the 6-month, 1-year, and 2-year survival probabilities were 0.39 (95 % CI: 0.38-0.41), 0.22 (95 % CI: 0.21-0.23), and 0.09 (95 % CI: 0.08-0.10), while the survival probabilities for patients diagnosed in the post-EGFR testing period were 0.45 (95 % CI: 0.43-0.46), 0.29 (95 % CI: 0.27-0.30), and 0.16 (95 % CI: 0.15-0.17), respectively. After adjusting for baseline patient and clinical characteristics, OS in the post-EGFR period was significantly improved compared to the pre-EGFR period (HR: 0.81; 95 % CI: 0.78-0.85). Among patients who were treated with systemic therapy, those tested for an EGFR mutation had significantly greater survival than patients who were not tested HR of 0.81 (95 % CI: 0.70-0.95). CONCLUSION: These results show the considerable impact of population-based molecular testing and subsequent targeted therapies on survival among metastatic NSCLC patients. The estimates here can be used in future studies to evaluate the population-level cost-effectiveness of testing and treatment.

Prevalence, Treatment Patterns, and Outcomes of Individuals with EGFR Positive Metastatic Non-Small Cell Lung Cancer in a Canadian Real-World Setting: A Comparison of Exon 19 Deletion, L858R, and Exon 20 Insertion EGFR Mutation Carriers.

Real-world evidence surrounding EGFR positive NSCLC patients in Canada is limited. Administrative databases in Alberta, Canada were used to evaluate EGFR testing and mutation prevalence in de novo metastatic NSCLC, as well as the characteristics, treatment patterns, and outcomes of individuals with Exon 19, L858R and Exon20ins mutations. Between 2013-2019, 2974 individuals underwent EGFR testing, of which 451 (15.2%) were EGFR positive. Among EGFR positive individuals, 221 (49.0%) had an Exon 19 mutation, 159 (35.3%) had an L858R mutation, and 18 (4%) had an Exon20ins mutation. The proportion of individuals who initiated 1L systemic therapy was 89.1% for Exon19, 85.5% for L858R, and 72.2% for Exon20ins carriers. The primary front-line systemic therapy was gefitinib or afatinib monotherapy for individuals with Exon 19 (93.4%) and L858R (94.1%) mutations versus platinum combination therapy for individuals with Exon20ins mutations (61.5%). The Exon20ins cohort had worse median overall survival from initiation of 1L systemic therapy (10.5 months [95% CI: 8.0-not estimable]) than the Exon19 (20.6 months [95% CI: 18.4-24.9]), and L858R cohorts (19.1 months [95% CI: 14.5-23.1]). These findings highlight that Exon20ins mutations represent a rare subset of NSCLC in which treatment options are limited and survival outcomes are worse relative to individuals with more common types of EGFR mutations.

Understanding Treatment Patterns and Outcomes among Patients with De Novo Unresectable Locally Advanced or Metastatic Urothelial Cancer: A Population-Level Retrospective Analysis from Alberta, Canada.

Despite a high disease burden, real-world data on treatment patterns in patients with unresectable locally advanced or metastatic urothelial carcinoma (la/mUC) in Canada are limited. This retrospective, longitudinal cohort study describes treatment patterns and survival in a population of patients with de novo unresectable la/mUC from Alberta, Canada, diagnosed between 1 January 2015 and 31 December 2019, followed until mid-2020. The outcomes of interest were systemic therapy treatment patterns and overall survival (OS). Of 206 patients, most (65.0%, n = 134) did not receive any systemic therapies. Of 72 patients (35.0%) who received first-line systemic therapy, the median duration of treatment was 2.8 months (IQR 3.3). Thirty-five patients (48.6% of those who received first-line therapy) received subsequent second-line therapy, for a median of 3.0 months (IQR 3.3). In all patients (n = 206), the median OS from diagnosis was 5.3 months (95% CI, 4.5-7.0). In patients who received treatment, the median OS from the initiation of first-line and second-line systemic therapy was 9.1 (6.4-11.6) and 4.6 months (3.9-19.2), respectively. The majority of patients did not receive first-line systemic therapy, and, in those who did, survival outcomes were poor. This study highlights the significant unmet need for safe and efficacious therapies for patients with la/mUC in Canada.

Treatment patterns and survival outcomes of early-onset colorectal cancer patients in Alberta, Canada: a population-based study.

BACKGROUND: The incidence of early-onset (<50) colorectal cancer (eoCRC) has been increasing in Canada. Little is known about treatment patterns and outcomes among this patient population in Canada. PATIENTS AND METHODS: We conducted a retrospective population-based cohort study of CRC patients in Alberta (2010-2018) using electronic medical records and administrative claims data. Treatment patterns and CRC-specific mortality were compared between early-onset age groups (<40 and 40-49) and average age-at-onset (60-70) (aoCRC) patients with multivariable logistic regression and cox proportional hazard models. RESULTS: There were 334 and 935 patients in the early-onset groups and 4606 in the aoCRC group. Compared with aoCRC, patients <40 were more likely to receive chemotherapy in stage II colon (OR 3.41, CI 1.75-6.47) and stage III rectal (OR 3.01, CI 1.18-10.21), and to receive systemic therapy (OR 2.40, CI 1.46-4.12) and radiation in stage IV CRC (OR 2.70, CI 1.48-4.92). The 40-49 age group was more likely to receive chemotherapy in stage II colon (OR 2.13, CI 1.25-3.56), and chemoradiation in stage II rectal (OR 2.16, CI 1.25-3.80) and stage III rectal (OR 1.63, CI 1.13-2.40), as well as systemic therapy in stage IV CRC (OR 2.46, CI 1.75-3.52). Survival did not differ between <40 and 60-70 age groups. Survival was significantly higher for the 40-49 age group, but only in stage IV (HR 0.79, CI 0.67-0.94). CONCLUSIONS: EoCRC patients tended to receive more therapy than average age CRC patients with minimal survival gains. Additional research to identify optimal treatment strategies for eoCRC patients is required.

Developing a Prediction Model for Pathologic Complete Response Following Neoadjuvant Chemotherapy in Breast Cancer: A Comparison of Model Building Approaches.

PURPOSE: The optimal characteristics among patients with breast cancer to recommend neoadjuvant chemotherapy is an active area of clinical research. We developed and compared several approaches to developing prediction models for pathologic complete response (pCR) among patients with breast cancer in Alberta. METHODS: The study included all patients with breast cancer who received neoadjuvant chemotherapy in Alberta between 2012 and 2014 identified from the Alberta Cancer Registry. Patient, tumor, and treatment data were obtained through primary chart review. pCR was defined as no residual invasive tumor at surgical excision in breast or axilla. Two types of prediction models for pCR were built: (1) expert model: variables selected on the basis of oncologists' opinions and (2) data-driven model: variables selected by trained machine. These model types were fit using logistic regression (LR), random forests (RF), and gradient-boosted trees (GBT). We compared the models using area under the receiver operating characteristic curve and integrated calibration index, and internally validated using bootstrap resampling. RESULTS: A total of 363 cases were included in the analyses, of which 86 experienced pCR. The RF and GBT fits yielded higher optimism-corrected area under the receiver operating characteristic curves compared with LR for the expert (RF: 0.70; GBT: 0.69; LR: 0.65) and data-driven models (RF: 0.71; GBT: 0.68; LR: 0.64). The LR fit yielded the lowest integrated calibration indices for the expert (LR: 0.037; GBT: 0.05; RF: 0.10) and data-driven models (LR: 0.026; GBT: 0.06; RF: 0.099). CONCLUSION: Our models demonstrated predictive ability for pCR using routinely collected clinical and demographic variables. We show that machine learning fit methods can be used to optimize models for pCR prediction. We also show that additional variables beyond clinical expertise do not considerably improve predictive ability and may not be of value on the basis of the burden of data collection.

Development and validation of a risk prediction model for high-risk adenomas at the time of first screening colonoscopy among screening aged Canadians.

The aim of this study was to develop a risk prediction model for high risk adenomas (HRAs) detected at screening colonoscopy based on readily available participant information. The cohort consisted of 3035 participants aged 50 to 74 years with no history of cancer who underwent a primary screening colonoscopy at a centralized colon cancer screening centre between 2008 and 2016. A multivariable logistic regression model was created using CRC risk factors identified from prior research. Model covariates were collected from a baseline questionnaire and included participant demographics (age and sex), lifestyle parameters (body mass index, alcohol, smoking, and vitamin D supplement use) and medical history (family history of CRC and diabetes). Mean participant age was 58.8 years, and 54.7% were male. 249 participants with HRAs were identified (8.2%). An adjusted c-statistic of 0.67 was calculated, and a specificity and negative predictive value of 97.2% (95% CI: 96.5-97.8) and 92.5% (95% CI: 92.2-92.8) for the detection of HRAs, respectively, were achieved using 20% predicted probability as a high-risk threshold. However, only a sensitivity of 12.1% (95% CI: 8.3-16.8) was achieved. Our model has moderate predictive ability, with strengths in being able to rule out those with an absence of HRAs on screening colonoscopy. Maximizing screening efficiency through improved risk prediction can enhance resource allocation. Ultimately, this model has the potential to improve patient care by reducing unnecessary colonoscopies, limiting this invasive procedure to those most likely to have significant findings.

SNF-NN: computational method to predict drug-disease interactions using similarity network fusion and neural networks.

BACKGROUND: Drug repositioning is an emerging approach in pharmaceutical research for identifying novel therapeutic potentials for approved drugs and discover therapies for untreated diseases. Due to its time and cost efficiency, drug repositioning plays an instrumental role in optimizing the drug development process compared to the traditional de novo drug discovery process. Advances in the genomics, together with the enormous growth of large-scale publicly available data and the availability of high-performance computing capabilities, have further motivated the development of computational drug repositioning approaches. More recently, the rise of machine learning techniques, together with the availability of powerful computers, has made the area of computational drug repositioning an area of intense activities. RESULTS: In this study, a novel framework SNF-NN based on deep learning is presented, where novel drug-disease interactions are predicted using drug-related similarity information, disease-related similarity information, and known drug-disease interactions. Heterogeneous similarity information related to drugs and disease is fed to the proposed framework in order to predict novel drug-disease interactions. SNF-NN uses similarity selection, similarity network fusion, and a highly tuned novel neural network model to predict new drug-disease interactions. The robustness of SNF-NN is evaluated by comparing its performance with nine baseline machine learning methods. The proposed framework outperforms all baseline methods ([Formula: see text] = 0.867, and [Formula: see text]=0.876) using stratified 10-fold cross-validation. To further demonstrate the reliability and robustness of SNF-NN, two datasets are used to fairly validate the proposed framework's performance against seven recent state-of-the-art methods for drug-disease interaction prediction. SNF-NN achieves remarkable performance in stratified 10-fold cross-validation with [Formula: see text] ranging from 0.879 to 0.931 and [Formula: see text] from 0.856 to 0.903. Moreover, the efficiency of SNF-NN is verified by validating predicted unknown drug-disease interactions against clinical trials and published studies. CONCLUSION: In conclusion, computational drug repositioning research can significantly benefit from integrating similarity measures in heterogeneous networks and deep learning models for predicting novel drug-disease interactions. The data and implementation of SNF-NN are available at http://pages.cpsc.ucalgary.ca/ tnjarada/snf-nn.php .

A review of computational drug repositioning: strategies, approaches, opportunities, challenges, and directions.

Drug repositioning is the process of identifying novel therapeutic potentials for existing drugs and discovering therapies for untreated diseases. Drug repositioning, therefore, plays an important role in optimizing the pre-clinical process of developing novel drugs by saving time and cost compared to the traditional de novo drug discovery processes. Since drug repositioning relies on data for existing drugs and diseases the enormous growth of publicly available large-scale biological, biomedical, and electronic health-related data along with the high-performance computing capabilities have accelerated the development of computational drug repositioning approaches. Multidisciplinary researchers and scientists have carried out numerous attempts, with different degrees of efficiency and success, to computationally study the potential of repositioning drugs to identify alternative drug indications. This study reviews recent advancements in the field of computational drug repositioning. First, we highlight different drug repositioning strategies and provide an overview of frequently used resources. Second, we summarize computational approaches that are extensively used in drug repositioning studies. Third, we present different computing and experimental models to validate computational methods. Fourth, we address prospective opportunities, including a few target areas. Finally, we discuss challenges and limitations encountered in computational drug repositioning and conclude with an outline of further research directions.