Temporal phenotyping by mining healthcare data to derive lines of therapy for cancer

Extraction of Unstructured Electronic Health Records to Evaluate Glioblastoma Treatment Patterns

PURPOSE

Data on lines of therapy (LOTs) for cancer treatment are important for clinical oncology research, but LOTs are not explicitly recorded in electronic health records (EHRs). We present an efficient approach for clinical data abstraction and a flexible algorithm to derive LOTs from EHR-based medication data on patients with glioblastoma multiforme (GBM).

METHODS

Nonclinicians were trained to abstract the diagnosis of GBM from EHRs, and their accuracy was compared with abstraction performed by clinicians. The resulting data were used to build a cohort of patients with confirmed GBM diagnosis. An algorithm was developed to derive LOTs using structured medication data, accounting for the addition and discontinuation of therapies and drug class. Descriptive statistics were calculated and time-to-next-treatment (TTNT) analysis was performed using the Kaplan-Meier method.

RESULTS

Treating clinicians as the gold standard, nonclinicians abstracted GBM diagnosis with a sensitivity of 0.98, specificity 1.00, positive predictive value 1.00, and negative predictive value 0.90, suggesting that nonclinician abstraction of GBM diagnosis was comparable with clinician abstraction. Of 693 patients with a confirmed diagnosis of GBM, 246 patients contained structured information about the types of medications received. Of them, 165 (67.1%) received a first-line therapy (1L) of temozolomide, and the median TTNT from the start of 1L was 179 days.

CONCLUSION

We described a workflow for extracting diagnosis of GBM and LOT from EHR data that combines nonclinician abstraction with algorithmic processing, demonstrating comparable accuracy with clinician abstraction and highlighting the potential for scalable and efficient EHR-based oncology research.

Concepts of lines of therapy in cancer treatment: findings from an expert interview-based study

OBJECTIVE

The concept of lines of therapy (LOT) in cancer treatment is often considered for decision making in tumor boards and clinical management, but lacks a common definition across medical specialties. The complexity and heterogeneity of malignancies and treatment modalities contribute to an inconsistent understanding of LOT among physicians. This study assesses the heterogeneity of understandings of the LOT concept, its major dimensions, and criteria from the perspective of physicians of different specialties with an oncological focus in Germany. Semi-structured expert interviews with nine physicians were conducted and evaluated using qualitative content analysis.

RESULTS

Most interviewees agreed that there is no single definition for LOT and found it difficult to explicate their understanding. A majority of experts stated that they had already encountered misunderstandings with colleagues regarding LOT and that they had problems with deciphering LOT from the medical records of their patients. Disagreement emerged about the roles of the following within the LOT concept: maintenance therapy, treatment intention, different therapy modalities, changing pharmaceutical agents, and therapy breaks. Respondents predominantly considered the same criteria as decisive for the definition of LOT as for a change in LOT (e.g., the occurrence of a progression event or tumor recurrence).

Real-world evaluation of imipenem/cilastatin/relebactam across US medical centres

We assessed 160 patients who received imipenem/cilastatin/relebactam for ≥2 days. At treatment initiation, the median Charlson Comorbidity Index was 5, 45% were in the intensive care unit, and 19% required vasopressor support. The in-hospital mortality rate was 24%. These data advance our understanding of real-world indications and outcomes of imipenem/cilastatin/relebactam use.

Frontline pembrolizumab monotherapy for metastatic non-small cell lung cancer with PD-L1 expression ≥50%: real-world outcomes in a US community oncology setting

Background

This study investigated real-world time on treatment (rwToT) and overall survival (OS) for patients with metastatic non-small cell lung cancer (mNSCLC) who initiated first-line (1L) pembrolizumab monotherapy. We also explored discontinuation reasons and subsequent treatments, stratified by number of cycles among those who completed ≥17 cycles of 1L pembrolizumab.

Methods

Patients with mNSCLC without actionable genetic aberrations, Eastern Cooperative Oncology Group performance status (ECOG PS) 0-2 and unknown, and PD-L1 TPS ≥ 50% starting 1L pembrolizumab monotherapy between 24-Oct-2016 and 31-Dec-2018 within The US Oncology Network were identified retrospectively and evaluated using structured data, with a data cutoff of 30-Sep-2021. Patient characteristics and disposition were summarized using descriptive statistics. OS and rwToT were evaluated using Kaplan-Meier method for all ECOG PS and PS 0-1. A subgroup of patients who completed ≥17 cycles were evaluated using supplemental chart review data to discern reasons for discontinuation.

Results

Of the 505 patients with mNSCLC with PD-L1 TPS ≥50%, 61% had ECOG PS 0-1, 23% had ECOG PS 2, and 65% had nonsquamous histology. Median rwToT and OS of pembrolizumab were 7.0 (95% CI, 6.0-8.4) months and 24.5 (95% CI, 20.1-29.3) months, respectively. In the subgroup with ECOG PS 0-1, they were 7.6 months (95% CI, 6.2-9.2) and 28.8 months (95% CI, 22.4-37.5), respectively. Of the 103 patients who completed ≥17 cycles, 57 (55.3%) patients received 17 - 34 cycles and 46 (44.7%) patients received ≥35 cycles. Approximately 7.7% of the study population received pembrolizumab beyond 35 cycles. Most common reasons for discontinuation were disease progression (38.6%) and toxicity (19.3%) among patients who received 17-34 cycles of pembrolizumab, and disease progression (13.0%) and completion of therapy (10.9%) among patients who received ≥35 cycles.

Conclusion

Consistent with findings from KEYNOTE-024 and other real-world studies, this study demonstrates the long-term effectiveness of pembrolizumab monotherapy as 1L treatment for mNSCLC with PD-L1 TPS ≥50%. Among patients who completed ≥17 cycles, nearly half completed ≥35 cycles. Disease progression and toxicity were the most common reasons for discontinuation among patients who received 17-34 cycles of pembrolizumab. Reasons for discontinuation beyond 35 cycles need further exploration.

Real-World Data Quality Framework for Oncology Time to Treatment Discontinuation Use Case: Implementation and Evaluation Study

BACKGROUND

The importance of real-world evidence is widely recognized in observational oncology studies. However, the lack of interoperable data quality standards in the fragmented health information technology landscape represents an important challenge. Therefore, adopting validated systematic methods for evaluating data quality is important for oncology outcomes research leveraging real-world data (RWD).

OBJECTIVE

This study aims to implement real-world time to treatment discontinuation (rwTTD) for a systemic anticancer therapy (SACT) as a new use case for the Use Case Specific Relevance and Quality Assessment, a framework linking data quality and relevance in fit-for-purpose RWD assessment.

METHODS

To define the rwTTD use case, we mapped the operational definition of rwTTD to RWD elements commonly available from oncology electronic health record-derived data sets. We identified 20 tasks to check the completeness and plausibility of data elements concerning SACT use, line of therapy (LOT), death date, and length of follow-up. Using descriptive statistics, we illustrated how to implement the Use Case Specific Relevance and Quality Assessment on 2 oncology databases (Data sets A and B) to estimate the rwTTD of an SACT drug (target SACT) for patients with advanced head and neck cancer diagnosed on or after January 1, 2015.

RESULTS

A total of 1200 (24.96%) of 4808 patients in Data set A and 237 (5.92%) of 4003 patients in Data set B received the target SACT, suggesting better relevance of the former in estimating the rwTTD of the target SACT. The 2 data sets differed with regard to the terminology used for SACT drugs, LOT format, and target SACT LOT distribution over time. Data set B appeared to have less complete SACT records, longer lags in incorporating the latest data, and incomplete mortality data, suggesting a lack of fitness for estimating rwTTD.

CONCLUSIONS

The fit-for-purpose data quality assessment demonstrated substantial variability in the quality of the 2 real-world data sets. The data quality specifications applied for rwTTD estimation can be expanded to support a broad spectrum of oncology use cases.

Using natural language processing and patient journey clustering for temporal phenotyping of antimicrobial therapies for cat bite abscesses

BACKGROUND

Temporal phenotyping of patient journeys, which capture the common sequence patterns of interventions in the treatment of a specific condition, is useful to support understanding of antimicrobial usage in veterinary patients. Identifying and describing these phenotypes can inform antimicrobial stewardship programs designed to fight antimicrobial resistance, a major health crisis affecting both humans and animals, in which veterinarians have an important role to play.

OBJECTIVE

This research proposes a framework for extracting temporal phenotypes of patient journeys from clinical practice data through the application of natural language processing (NLP) and unsupervised machine learning (ML) techniques, using cat bite abscesses as a model condition. By constructing temporal phenotypes from key events, the relationship between antimicrobial administration and surgical interventions can be described, and similar treatment patterns can be grouped together to describe outcomes associated with specific antimicrobial selection.

METHODS

Cases identified as having a cat bite abscess as a diagnosis were extracted from VetCompass Australia, a database of veterinary clinical records. A classifier was trained and used to label the most clinically relevant event features in each record as chosen by a group of veterinarians. The labeled records were processed into coded character strings, where each letter represents a summary of specific types of treatments performed at a given visit. The sequences of letters representing the cases were clustered based on weighted Levenshtein edit distances with KMeans+ + to identify the main variations of the patient treatment journeys, including the antimicrobials used and their duration of administration.

RESULTS

A total of 13,744 records that met the selection criteria was extracted and grouped into 8436 cases. There were 9 clinically distinct event sequence patterns (temporal phenotypes) of patient journeys identified, representing the main sequences in which surgery and antimicrobial interventions are performed. Patients receiving amoxicillin and surgery had the shortest duration of antimicrobial administration (median of 3.4 days) and patients receiving cefovecin with no surgical intervention had the longest antimicrobial treatment duration (median of 27 days).

CONCLUSION

Our study demonstrates methods to extract and provide an overview of temporal phenotypes of patient journeys, which can be applied to text-based clinical records for multiple species or clinical conditions. We demonstrate the effectiveness of this approach to derive real-world evidence of treatment impacts using cat bite abscesses as a model condition to describe patterns of antimicrobial therapy prescriptions and their outcomes.

A methodology of phenotyping ICU patients from EHR data: High-fidelity, personalized, and interpretable phenotypes estimation

OBJECTIVE

Computing phenotypes that provide high-fidelity, time-dependent characterizations and yield personalized interpretations is challenging, especially given the complexity of physiological and healthcare systems and clinical data quality. This paper develops a methodological pipeline to estimate unmeasured physiological parameters and produce high-fidelity, personalized phenotypes anchored to physiological mechanics from electronic health record (EHR).

METHODS

A methodological phenotyping pipeline is developed that computes new phenotypes defined with unmeasurable computational biomarkers quantifying specific physiological properties in real time. Working within the inverse problem framework, this pipeline is applied to the glucose-insulin system for ICU patients using data assimilation to estimate an established mathematical physiological model with stochastic optimization. This produces physiological model parameter vectors of clinically unmeasured endocrine properties, here insulin secretion, clearance, and resistance, estimated for individual patient. These physiological parameter vectors are used as inputs to unsupervised machine learning methods to produce phenotypic labels and discrete physiological phenotypes. These phenotypes are inherently interpretable because they are based on parametric physiological descriptors. To establish potential clinical utility, the computed phenotypes are evaluated with external EHR data for consistency and reliability and with clinician face validation.

RESULTS

The phenotype computation was performed on a cohort of 109 ICU patients who received no or short-acting insulin therapy, rendering continuous and discrete physiological phenotypes as specific computational biomarkers of unmeasured insulin secretion, clearance, and resistance on time windows of three days. Six, six, and five discrete phenotypes were found in the first, middle, and last three-day periods of ICU stays, respectively. Computed phenotypic labels were predictive with an average accuracy of 89%. External validation of discrete phenotypes showed coherence and consistency in clinically observable differences based on laboratory measurements and ICD 9/10 codes and clinical concordance from face validity. A particularly clinically impactful parameter, insulin secretion, had a concordance accuracy of 83%±27%.

CONCLUSION

The new physiological phenotypes computed with individual patient ICU data and defined by estimates of mechanistic model parameters have high physiological fidelity, are continuous, time-specific, personalized, interpretable, and predictive. This methodology is generalizable to other clinical and physiological settings and opens the door for discovering deeper physiological information to personalize medical care.

Real-world utilization of immune checkpoint inhibitors in extensive stage small-cell lung cancer in community settings

Aim: This study examined real-world treatment patterns for extensive-stage small-cell lung cancer (ES-SCLC) after immune checkpoint inhibitors (ICIs) became available for frontline use. Methods: Adult patients with ES-SCLC initiating 1L systemic treatment were identified from electronic health records. Results: Among patients with recurrent/progressive ES-SCLC, the most common treatment classes were platinum-based chemotherapy (81.1% of 228) and ICI monotherapy (35.1% of 191) in 1L and 2L, respectively. Among patients with de novo ES-SCLC, the most common treatment classes were ICI + platinum-based chemotherapy (64.4% of 1268) and other chemotherapy (44.9% of 512) in 1L and 2L, respectively. Among patients who received no ICI in 1L, 62.6%-70.3% received it in 2L and 62.6-68.5% in 3L. Some who received 1L ICI were re-treated with ICI in subsequent lines (14.5-18.8% in 2L, 18.2-50.0% in 3L). Conclusion: Real-world ICI utilization in ES-SCLC, particularly ICI re-challenge, demonstrates high unmet needs in this patient population.

Analytical methods for identifying sequences of utilization in health data: a scoping review

BACKGROUND

Healthcare, as with other sectors, has undergone progressive digitalization, generating an ever-increasing wealth of data that enables research and the analysis of patient movement. This can help to evaluate treatment processes and outcomes, and in turn improve the quality of care. This scoping review provides an overview of the algorithms and methods that have been used to identify care pathways from healthcare utilization data.

METHOD

This review was conducted according to the methodology of the Joanna Briggs Institute and the Preferred Reporting Items for Systematic Reviews Extension for Scoping Reviews (PRISMA-ScR) Checklist. The PubMed, Web of Science, Scopus, and EconLit databases were searched and studies published in English between 2000 and 2021 considered. The search strategy used keywords divided into three categories: the method of data analysis, the requirement profile for the data, and the intended presentation of results. Criteria for inclusion were that health data were analyzed, the methodology used was described and that the chronology of care events was considered. In a two-stage review process, records were reviewed by two researchers independently for inclusion. Results were synthesized narratively.

RESULTS

The literature search yielded 2,865 entries; 51 studies met the inclusion criteria. Health data from different countries ([Formula: see text]) and of different types of disease ([Formula: see text]) were analyzed with respect to different care events. Applied methods can be divided into those identifying subsequences of care and those describing full care trajectories. Variants of pattern mining or Markov models were mostly used to extract subsequences, with clustering often applied to find care trajectories. Statistical algorithms such as rule mining, probability-based machine learning algorithms or a combination of methods were also applied. Clustering methods were sometimes used for data preparation or result compression. Further characteristics of the included studies are presented.

CONCLUSION

Various data mining methods are already being applied to gain insight from health data. The great heterogeneity of the methods used shows the need for a scoping review. We performed a narrative review and found that clustering methods currently dominate the literature for identifying complete care trajectories, while variants of pattern mining dominate for identifying subsequences of limited length.

Treatment patterns and healthcare resource utilization for triple negative breast cancer in the Brazilian private healthcare system: a database study

In Brazil, data on the management of triple negative breast cancer (TNBC) as well as the burden of the disease in terms of health care resources utilization (HCRU) are scarce. To characterize the treatment patterns and HCRU associated with the management of Brazilian TNBC patients from the perspective of the private healthcare setting. Patients with at least one claim related to ICD-10 C50 from January 2012 until December 2017, and at least one claim for breast cancer treatment were assessed from a private claims database and classified as early and locally advanced, or metastatic. All patients with hormone and/or targeted therapy were excluded. Three thousand and four patients were identified, of which 82.8% were diagnosed in early and locally advanced stages. For early and locally advanced TNBC patients, 75.3% were treated in an adjuvant setting, mainly with anthracycline regimes. For mTNBC patients, bevacizumab regimens were the main treatment prescribed. More than 48% of mTNBC patients were switched to a second line of treatment. HCRU was higher for mTNBC patients when compared to early and locally advanced patients, with higher costs for metastatic disease management. The treatment setting has little influence on the HCRU pattern or the cost of disease management. The highest burden of disease was observed for metastatic management.

Exploring Breast Cancer Systemic Drug Therapy Patterns in Real-World Data

PURPOSE

To explore medications and their administration patterns in real-world patients with breast cancer.

METHODS

A retrospective study was performed using TriNetX, a federated network of deidentified, Health Insurance Portability and Accountability Act-compliant data from 21 health care organizations across North America. Patients diagnosed with breast cancer between January 1, 2013, and May 31, 2022, were included. We investigated a rule-based and unsupervised learning algorithm to extract medications and their administration patterns. To group similar administration patterns, we used three features in k-means clustering: total number of administrations, median number of days between administrations, and standard deviation of the days between administrations. We explored the first three lines of therapy for patients classified into six groups on the basis of their stage at diagnosis (early as stages I-III v late as stage IV) and the sensitivity of the tumor's receptors to targeted therapies: hormone receptor-positive/human epidermal growth factor 2-negative (HR+/ERBB2-), ERBB2-positive (ERBB2+/HR±), or triple-negative (TN; HR-/ERBB2-). To add credence to the derived regimens, we compared them to the National Comprehensive Cancer Network (NCCN): Breast Cancer (version 2.2023) recommendations.

RESULTS

In early-stage HR+/ERBB2- and TN groups, the most common regimens were (1) cyclophosphamide and docetaxel, administered once every 3 weeks for three to six cycles and (2) cyclophosphamide and doxorubicin, administered once every 2 weeks for four cycles, followed by paclitaxel administered once every week for 12 cycles. In the early-stage ERBB2+/HR± group, most patients were administered carboplatin and docetaxel with or without pertuzumab and with trastuzumab (for six or more cycles). Medications most commonly administered in our data set (7,798 patients) agreed with recommendations from the NCCN in terms of medications (regimens), number of administrations (cycles), and days between administrations (cycle length).

CONCLUSION

Although there is a general agreement with the NCCN Guidelines, real-world medication data exhibit variability in the medications and their administration patterns.

A methodology of phenotyping ICU patients from EHR data: high-fidelity, personalized, and interpretable phenotypes estimation

Objective

Computing phenotypes that provide high-fidelity, time-dependent characterizations and yield personalized interpretations is challenging, especially given the complexity of physiological and healthcare systems and clinical data quality. This paper develops a methodological pipeline to estimate unmeasured physiological parameters and produce high-fidelity, personalized phenotypes anchored to physiological mechanics from electronic health record (EHR).

Methods

A methodological phenotyping pipeline is developed that computes new phenotypes defined with unmeasurable computational biomarkers quantifying specific physiological properties in real time. Working within the inverse problem framework, this pipeline is applied to the glucose-insulin system for ICU patients using data assimilation to estimate an established mathematical physiological model with stochastic optimization. This produces physiological model parameter vectors of clinically unmeasured endocrine properties, here insulin secretion, clearance, and resistance, estimated for individual patient. These physiological parameter vectors are used as inputs to unsupervised machine learning methods to produce phenotypic labels and discrete physiological phenotypes. These phenotypes are inherently interpretable because they are based on parametric physiological descriptors. To establish potential clinical utility, the computed phenotypes are evaluated with external EHR data for consistency and reliability and with clinician face validation.

Results

The phenotype computation was performed on a cohort of 109 ICU patients who received no or short-acting insulin therapy, rendering continuous and discrete physiological phenotypes as specific computational biomarkers of unmeasured insulin secretion, clearance, and resistance on time windows of three days. Six, six, and five discrete phenotypes were found in the first, middle, and last three-day periods of ICU stays, respectively. Computed phenotypic labels were predictive with an average accuracy of 89%. External validation of discrete phenotypes showed coherence and consistency in clinically observable differences based on laboratory measurements and ICD 9/10 codes and clinical concordance from face validity. A particularly clinically impactful parameter, insulin secretion, had a concordance accuracy of 83% ± 27%.

Conclusion

The new physiological phenotypes computed with individual patient ICU data and defined by estimates of mechanistic model parameters have high physiological fidelity, are continuous, time-specific, personalized, interpretable, and predictive. This methodology is generalizable to other clinical and physiological settings and opens the door for discovering deeper physiological information to personalize medical care.

Identifying Patient Populations in Texts Describing Drug Approvals Through Deep Learning-Based Information Extraction: Development of a Natural Language Processing Algorithm

BACKGROUND

New drug treatments are regularly approved, and it is challenging to remain up-to-date in this rapidly changing environment. Fast and accurate visualization is important to allow a global understanding of the drug market. Automation of this information extraction provides a helpful starting point for the subject matter expert, helps to mitigate human errors, and saves time.

OBJECTIVE

We aimed to semiautomate disease population extraction from the free text of oncology drug approval descriptions from the BioMedTracker database for 6 selected drug targets. More specifically, we intended to extract (1) line of therapy, (2) stage of cancer of the patient population described in the approval, and (3) the clinical trials that provide evidence for the approval. We aimed to use these results in downstream applications, aiding the searchability of relevant content against related drug project sources.

METHODS

We fine-tuned a state-of-the-art deep learning model, Bidirectional Encoder Representations from Transformers, for each of the 3 desired outputs. We independently applied rule-based text mining approaches. We compared the performances of deep learning and rule-based approaches and selected the best method, which was then applied to new entries. The results were manually curated by a subject matter expert and then used to train new models.

RESULTS

The training data set is currently small (433 entries) and will enlarge over time when new approval descriptions become available or if a choice is made to take another drug target into account. The deep learning models achieved 61% and 56% 5-fold cross-validated accuracies for line of therapy and stage of cancer, respectively, which were treated as classification tasks. Trial identification is treated as a named entity recognition task, and the 5-fold cross-validated F₁-score is currently 87%. Although the scores of the classification tasks could seem low, the models comprise 5 classes each, and such scores are a marked improvement when compared to random classification. Moreover, we expect improved performance as the input data set grows, since deep learning models need to be trained on a large enough amount of data to be able to learn the task they are taught. The rule-based approach achieved 60% and 74% 5-fold cross-validated accuracies for line of therapy and stage of cancer, respectively. No attempt was made to define a rule-based approach for trial identification.

CONCLUSIONS

We developed a natural language processing algorithm that is currently assisting subject matter experts in disease population extraction, which supports health authority approvals. This algorithm achieves semiautomation, enabling subject matter experts to leverage the results for deeper analysis and to accelerate information retrieval in a crowded clinical environment such as oncology.

Missing data matter: an empirical evaluation of the impacts of missing EHR data in comparative effectiveness research

OBJECTIVES

The impacts of missing data in comparative effectiveness research (CER) using electronic health records (EHRs) may vary depending on the type and pattern of missing data. In this study, we aimed to quantify these impacts and compare the performance of different imputation methods.

MATERIALS AND METHODS

We conducted an empirical (simulation) study to quantify the bias and power loss in estimating treatment effects in CER using EHR data. We considered various missing scenarios and used the propensity scores to control for confounding. We compared the performance of the multiple imputation and spline smoothing methods to handle missing data.

RESULTS

When missing data depended on the stochastic progression of disease and medical practice patterns, the spline smoothing method produced results that were close to those obtained when there were no missing data. Compared to multiple imputation, the spline smoothing generally performed similarly or better, with smaller estimation bias and less power loss. The multiple imputation can still reduce study bias and power loss in some restrictive scenarios, eg, when missing data did not depend on the stochastic process of disease progression.

DISCUSSION AND CONCLUSION

Missing data in EHRs could lead to biased estimates of treatment effects and false negative findings in CER even after missing data were imputed. It is important to leverage the temporal information of disease trajectory to impute missing values when using EHRs as a data resource for CER and to consider the missing rate and the effect size when choosing an imputation method.

A platform for phenotyping disease progression and associated longitudinal risk factors in large-scale EHRs, with application to incident diabetes complications in the UK Biobank

Objective

Modern healthcare data reflect massive multi-level and multi-scale information collected over many years. The majority of the existing phenotyping algorithms use case-control definitions of disease. This paper aims to study the time to disease onset and progression and identify the time-varying risk factors that drive them.

Materials and Methods

We developed an algorithmic approach to phenotyping the incidence of diseases by consolidating data sources from the UK Biobank (UKB), including primary care electronic health records (EHRs). We focused on defining events, event dates, and their censoring time, including relevant terms and existing phenotypes, excluding generic, rare, or semantically distant terms, forward-mapping terminology terms, and expert review. We applied our approach to phenotyping diabetes complications, including a composite cardiovascular disease (CVD) outcome, diabetic kidney disease (DKD), and diabetic retinopathy (DR), in the UKB study.

Results

We identified 49 049 participants with diabetes. Among them, 1023 had type 1 diabetes (T1D), and 40 193 had type 2 diabetes (T2D). A total of 23 833 diabetes subjects had linked primary care records. There were 3237, 3113, and 4922 patients with CVD, DKD, and DR events, respectively. The risk prediction performance for each outcome was assessed, and our results are consistent with the prediction area under the ROC (receiver operating characteristic) curve (AUC) of standard risk prediction models using cohort studies.

Discussion and Conclusion

Our publicly available pipeline and platform enable streamlined curation of incidence events, identification of time-varying risk factors underlying disease progression, and the definition of a relevant cohort for time-to-event analyses. These important steps need to be considered simultaneously to study disease progression.

Supporting patients and clinicians during the breast cancer care path with AI: The Arianna solution

The onset of cancer disease is a traumatic experience for both patients and their families that suddenly change the patient's life and is accompanied by important physical, emotional, and psycho-social problems. The complexity of this scenario has been exacerbated by the COVID-19 pandemic which dramatically affected the continuity of the provision of optimal care to chronic patients. Telemedicine can support the management of oncology care paths by furnishing a suite of effective and efficient tools to monitor the therapies of cancer patients. In particular, this is a suitable setting for therapies that are administered at home. In this paper, we present an AI-based system, called Arianna, designed and implemented to support and monitor patients treated by the professionals belonging to the Breast Cancer Unit Network (BCU-Net) along the entire clinical path of breast cancer treatment. We describe in this work the three modules composing the Arianna system (the tools for patients and clinicians, and the symbolic AI-based module). The system has been validated in a qualitative way and we demonstrated how the Arianna solution reached a high level of acceptability by all types of end-users by making it suitable for a concrete integration into the daily practice of the BCU-Net.

Scanning the medical phenome to identify new diagnoses after recovery from COVID-19 in a US cohort

OBJECTIVE

COVID-19 survivors are at risk for long-term health effects, but assessing the sequelae of COVID-19 at large scales is challenging. High-throughput methods to efficiently identify new medical problems arising after acute medical events using the electronic health record (EHR) could improve surveillance for long-term consequences of acute medical problems like COVID-19.

MATERIALS AND METHODS

We augmented an existing high-throughput phenotyping method (PheWAS) to identify new diagnoses occurring after an acute temporal event in the EHR. We then used the temporal-informed phenotypes to assess development of new medical problems among COVID-19 survivors enrolled in an EHR cohort of adults tested for COVID-19 at Vanderbilt University Medical Center.

RESULTS

The study cohort included 186 105 adults tested for COVID-19 from March 5, 2020 to November 1, 2021; of which 30 088 (16.2%) tested positive. Median follow-up after testing was 412 days (IQR 274-528). Our temporal-informed phenotyping was able to distinguish phenotype chapters based on chronicity of their constituent diagnoses. PheWAS with temporal-informed phenotypes identified increased risk for 43 diagnoses among COVID-19 survivors during outpatient follow-up, including multiple new respiratory, cardiovascular, neurological, and pregnancy-related conditions. Findings were robust to sensitivity analyses, and several phenotypic associations were supported by changes in outpatient vital signs or laboratory tests from the pretesting to postrecovery period.

CONCLUSION

Temporal-informed PheWAS identified new diagnoses affecting multiple organ systems among COVID-19 survivors. These findings can inform future efforts to enable longitudinal health surveillance for survivors of COVID-19 and other acute medical conditions using the EHR.

Machine learning approaches for electronic health records phenotyping: a methodical review

OBJECTIVE

Accurate and rapid phenotyping is a prerequisite to leveraging electronic health records for biomedical research. While early phenotyping relied on rule-based algorithms curated by experts, machine learning (ML) approaches have emerged as an alternative to improve scalability across phenotypes and healthcare settings. This study evaluates ML-based phenotyping with respect to (1) the data sources used, (2) the phenotypes considered, (3) the methods applied, and (4) the reporting and evaluation methods used.

MATERIALS AND METHODS

We searched PubMed and Web of Science for articles published between 2018 and 2022. After screening 850 articles, we recorded 37 variables on 100 studies.

RESULTS

Most studies utilized data from a single institution and included information in clinical notes. Although chronic conditions were most commonly considered, ML also enabled the characterization of nuanced phenotypes such as social determinants of health. Supervised deep learning was the most popular ML paradigm, while semi-supervised and weakly supervised learning were applied to expedite algorithm development and unsupervised learning to facilitate phenotype discovery. ML approaches did not uniformly outperform rule-based algorithms, but deep learning offered a marginal improvement over traditional ML for many conditions.

DISCUSSION

Despite the progress in ML-based phenotyping, most articles focused on binary phenotypes and few articles evaluated external validity or used multi-institution data. Study settings were infrequently reported and analytic code was rarely released.

CONCLUSION

Continued research in ML-based phenotyping is warranted, with emphasis on characterizing nuanced phenotypes, establishing reporting and evaluation standards, and developing methods to accommodate misclassified phenotypes due to algorithm errors in downstream applications.

Treatment patterns and burden of myelosuppression for patients with small cell lung cancer: A SEER-medicare study

PURPOSE

To depict the treatment journey for patients with small cell lung cancer (SCLC) and evaluate health care resource utilization (HCRU) associated with myelosuppression, a complication induced by chemotherapy or chemotherapy plus radiation therapy.

PATIENTS AND METHODS

This was a descriptive, retrospective study of patients with SCLC aged ≥65 years, identified from linked Surveillance, Epidemiology, and End Results (SEER)-Medicare data curated between January 2012 and December 2015. Treatment types (chemotherapy, radiation therapy, surgery) were classified as first, second, or third line, depending on the temporal sequence in which regimens were prescribed. For each year, the proportions of patients completing 4- or 6-cycle chemotherapy regimens, with hospital admissions associated with myelosuppression, or who used granulocyte colony-stimulating factors (G-CSFs), blood/platelet transfusions, or erythropoiesis-stimulating agents (ESAs), were calculated.

RESULTS

Chemotherapy was administered as initial treatment in 7,807/11,907 (65.6%) patients whose treatment journey was recorded. Approximately one-third (n = 3,985) subsequently received radiation therapy. In total, 5,791 (57.8%) patients completed the guideline-recommended 4-6 cycles of chemotherapy. Among all chemotherapy-treated patients, 10,370 (74.3%) experienced ≥1 inpatient admission associated with myelosuppression (anemia, 7,366 [52.8%]; neutropenia, 4,642 [33.3%]; thrombocytopenia, 2,375 [17.0%]; pancytopenia, 1,983 [14.2%]). Supportive care interventions included G-CSF (6,756 [48.4%] patients), ESAs (1,534 [11.0%]), and transfusions (3,674 [26.3%]).

CONCLUSION

Chemotherapy remains a cornerstone of care for patients with SCLC. Slightly over half of patients completed the recommended number of cycles, underscoring the frailty of patients and aggressiveness of SCLC. HCRU associated with myelosuppression was prominent, suggesting a substantial burden on older patients with SCLC.

An Automated Line-of-Therapy Algorithm for Adults With Metastatic Non-Small Cell Lung Cancer: Validation Study Using Blinded Manual Chart Review

BACKGROUND

Extraction of line-of-therapy (LOT) information from electronic health record and claims data is essential for determining longitudinal changes in systemic anticancer therapy in real-world clinical settings.

OBJECTIVE

The aim of this retrospective cohort analysis is to validate and refine our previously described open-source LOT algorithm by comparing the output of the algorithm with results obtained through blinded manual chart review.

METHODS

We used structured electronic health record data and clinical documents to identify 500 adult patients treated for metastatic non-small cell lung cancer with systemic anticancer therapy from 2011 to mid-2018; we assigned patients to training (n=350) and test (n=150) cohorts, randomly divided proportional to the overall ratio of simple:complex cases (n=254:246). Simple cases were patients who received one LOT and no maintenance therapy; complex cases were patients who received more than one LOT and/or maintenance therapy. Algorithmic changes were performed using the training cohort data, after which the refined algorithm was evaluated against the test cohort.

RESULTS

For simple cases, 16 instances of discordance between the LOT algorithm and chart review prerefinement were reduced to 8 instances postrefinement; in the test cohort, there was no discordance between algorithm and chart review. For complex cases, algorithm refinement reduced the discordance from 68 to 62 instances, with 37 instances in the test cohort. The percentage agreement between LOT algorithm output and chart review for patients who received one LOT was 89% prerefinement, 93% postrefinement, and 93% for the test cohort, whereas the likelihood of precise matching between algorithm output and chart review decreased with an increasing number of unique regimens. Several areas of discordance that arose from differing definitions of LOTs and maintenance therapy could not be objectively resolved because of a lack of precise definitions in the medical literature.

CONCLUSIONS

Our findings identify common sources of discordance between the LOT algorithm and clinician documentation, providing the possibility of targeted algorithm refinement.

Defining treatment regimens and lines of therapy using real-world data in oncology

Retrospective observational research relies on databases that do not routinely record lines of therapy or reasons for treatment change. Standardized approaches to estimate lines of therapy were developed and evaluated in this study. A number of rules were developed, assumptions varied and macros developed to apply to large datasets. Results were investigated in an iterative process to refine line of therapy algorithms in three different cancers (lung, colorectal and gastric). Three primary factors were evaluated and included in the estimation of lines of therapy in oncology: defining a treatment regimen, addition/removal of drugs and gap periods. Algorithms and associated Statistical Analysis Software (SAS®) macros for line of therapy identification are provided to facilitate and standardize the use of real-world databases for oncology research.

AI and Big Data in Healthcare: Towards a More Comprehensive Research Framework for Multimorbidity

Multimorbidity refers to the coexistence of two or more chronic diseases in one person. Therefore, patients with multimorbidity have multiple and special care needs. However, in practice it is difficult to meet these needs because the organizational processes of current healthcare systems tend to be tailored to a single disease. To improve clinical decision making and patient care in multimorbidity, a radical change in the problem-solving approach to medical research and treatment is needed. In addition to the traditional reductionist approach, we propose interactive research supported by artificial intelligence (AI) and advanced big data analytics. Such research approach, when applied to data routinely collected in healthcare settings, provides an integrated platform for research tasks related to multimorbidity. This may include, for example, prediction, correlation, and classification problems based on multiple interaction factors. However, to realize the idea of this paradigm shift in multimorbidity research, the optimization, standardization, and most importantly, the integration of electronic health data into a common national and international research infrastructure is needed. Ultimately, there is a need for the integration and implementation of efficient AI approaches, particularly deep learning, into clinical routine directly within the workflows of the medical professionals.

Identification of Three Autophagy-Related Long Non-Coding RNAs as a Novel Head and Neck Squamous Cell Carcinoma Prognostic Signature

Head and neck squamous cell carcinoma (HNSCC) has a poor prognosis. Considerable evidence indicates that autophagy and non-coding RNA play essential roles in the biological processes involved in cancers, but associations between autophagy-related long non-coding RNAs (lncRNAs) and HNSCC remain unclear. In the present study, HNSCC RNA sequences and autophagy-related gene data were extracted from The Cancer Genome Atlas database and the Human Autophagy Database. A total of 1,153 autophagy-related lncRNAs were selected via calculating Pearson’s correlation coefficient. Three prognosis-related autophagy lncRNAs were identified via univariate Cox regression, least absolute shrinkage and selection operator analysis, and multivariate Cox regression analysis. We also constructed a prognostic model based on these autophagy-related lncRNAs and evaluated its ability to accurately and independently predict the prognosis of HNSCC patients. The area under the curve (AUC) was 0.864 (3-year) and 0.836 (5-year), and our model can independently predict the prognosis of HNSCC. The prognostic value of the three autophagy lncRNAs was confirmed via analysis of samples from five databases. To further identify the functions of the three lncRNAs, a co-expression network was constructed and pathway analysis was performed. In that analysis the lncRNAs were correlated with 189 related genes and 20 autophagy-related genes, and these lncRNAs mainly involved homologous recombination, the Fanconi anemia pathway, the autophagy-related pathway, and immune-related pathways. In addition, we validated the expression levels of three lncRNAs and autophagy markers (ATG12, BECN1, and MAP1LC3B) based on TIMER, Oncomine, and HPA database analysis. Our results indicated that TTTY15 was increased in HPV positive and HPV negative HNSCC patients, and three autophagy markers were up-regulated in all HNSCCC patients. Lastly, association between three lncRNAs and autophagy markers was performed, and our results showed that TTTY15 and MIF-AS1 were associated with autophagy markers. Collectively, these results suggested that three autophagy-related lncRNAs have prognostic value in HNSCC patients.

Digital systems for improving outcomes in patients with primary immune defects

PURPOSE OF REVIEW

Healthcare has already been impacted by the fourth industrial revolution exemplified by tip of spear technology, such as artificial intelligence and quantum computing. Yet, there is much to be accomplished as systems remain suboptimal, and full interoperability of digital records is not realized. Given the footprint of technology in healthcare, the field of clinical immunology will certainly see improvements related to these tools.

RECENT FINDINGS

Biomedical informatics spans the gamut of technology in biomedicine. Within this distinct field, advances are being made, which allow for engineering of systems to automate disease detection, create computable phenotypes and improve record portability. Within clinical immunology, technologies are emerging along these lines and are expected to continue.

SUMMARY

This review highlights advancements in digital health including learning health systems, electronic phenotyping, artificial intelligence and use of registries. Technological advancements for improving diagnosis and care of patients with primary immunodeficiency diseases is also highlighted.