Application of Electronic Health Record Text Mining: Real-World Tolerability, Safety, and Efficacy of Adjuvant Melanoma Treatments

A comparison of real-world data on adjuvant treatment in patients with stage III BRAF V600 mutated melanoma - Results of systematic literature research

BACKGROUND

Over the past decade, PD-1-based immune checkpoint inhibitors (ICI) and targeted therapies (TT) with BRAF and MEK inhibitors transformed melanoma treatment. Both are widely used in the adjuvant setting. However, for patients with a BRAF V600 mutation, the optimal adjuvant therapy remains unclear due to the lack of head-to-head comparison studies.

METHODS

We conducted a systematic review of real-world data on adjuvant therapy in stage III melanoma to determine the best option for patients with BRAF V600 mutations. Kaplan-Meier curves were generated for TT and ICI using Digitizelt software.

RESULTS

Nine publications with 3625 patients were included. TT showed better relapse-free survival (RFS) at 6, 12, 24, and 36 months than ICI. A similar trend was observed for distant metastasis-free survival (DMFS), with no apparent difference in overall survival.

CONCLUSION

Real-world data suggest that adjuvant TT may be associated with better RFS and DMFS in stage III BRAF V600-mutated melanoma compared to ICI.

An innovative method to strengthen evidence for potential drug safety signals using Electronic Health Records

Reports from spontaneous reporting systems (SRS) are hypothesis generating. Additional evidence such as more reports is required to determine whether the generated drug-event associations are in fact safety signals. However, underreporting of adverse drug reactions (ADRs) delays signal detection. Through the use of natural language processing, different sources of real-world data can be used to proactively collect additional evidence for potential safety signals. This study aims to explore the feasibility of using Electronic Health Records (EHRs) to identify additional cases based on initial indications from spontaneous ADR reports, with the goal of strengthening the evidence base for potential safety signals. For two confirmed and two potential signals generated by the SRS of the Netherlands Pharmacovigilance Centre Lareb, targeted searches in the EHR of the Leiden University Medical Centre were performed using a text-mining based tool, CTcue. The search for additional cases was done by constructing and running queries in the structured and free-text fields of the EHRs. We identified at least five additional cases for the confirmed signals and one additional case for each potential safety signal. The majority of the identified cases for the confirmed signals were documented in the EHRs before signal detection by the Dutch Medicines Evaluation Board. The identified cases for the potential signals were reported to Lareb as further evidence for signal detection. Our findings highlight the feasibility of performing targeted searches in the EHR based on an underlying hypothesis to provide further evidence for signal generation.

Using an artificial intelligence tool incorporating natural language processing to identify patients with a diagnosis of ANCA-associated vasculitis in electronic health records

BACKGROUND

Because anti-neutrophil cytoplasmatic antibody (ANCA)-associated vasculitis (AAV) is a rare, life-threatening, auto-immune disease, conducting research is difficult but essential. A long-lasting challenge is to identify rare AAV patients within the electronic-health-record (EHR)-system to facilitate real-world research. Artificial intelligence (AI)-search tools using natural language processing (NLP) for text-mining are increasingly postulated as a solution.

METHODS

We employed an AI-tool that combined text-mining with NLP-based exclusion, to accurately identify rare AAV patients within large EHR-systems (>2.000.000 records). We developed an identification method in an academic center with an established AAV-training set (n = 203) and validated the method in a non-academic center with an AAV-validation set (n = 84). To assess accuracy anonymized patient records were manually reviewed.

RESULTS

Based on an iterative process, a text-mining search was developed on disease description, laboratory measurements, medication and specialisms. In the training center, 608 patients were identified with a sensitivity of 97.0 % (95%CI [93.7, 98.9]) and positive predictive value (PPV) of 56.9 % (95%CI [52.9, 60.1]). NLP-based exclusion resulted in 444 patients increasing PPV to 77.9 % (95%CI [73.7, 81.7]) while sensitivity remained 96.3 % (95%CI [93.8, 98.0]). In the validation center, text-mining identified 333 patients (sensitivity 97.6 % (95%CI [91.6, 99.7]), PPV 58.2 % (95%CI [52.8, 63.6])) and NLP-based exclusion resulted in 223 patients, increasing PPV to 86.1 % (95%CI [80.9, 90.4]) with 98.0 % (95%CI [94.9, 99.4]) sensitivity. Our identification method outperformed ICD-10-coding predominantly in identifying MPO+ and organ-limited AAV patients.

CONCLUSIONS

Our study highlights the advantages of implementing AI, notably NLP, to accurately identify rare AAV patients within large EHR-systems and demonstrates the applicability and transportability. Therefore, this method can reduce efforts to identify AAV patients and accelerate real-world research, while avoiding bias by ICD-10-coding.

Discharge from the emergency department and outpatient clinic in cancer patients with acute symptomatic and incidental pulmonary embolism: A multicenter retrospective cohort study

BACKGROUND

It is unclear how often cancer patients with acute pulmonary embolism (PE) are discharged from the emergency department (ED) or outpatient clinic and whether direct discharge is safe. We assessed treatment setting and early safety outcomes in cancer patients with acute symptomatic and incidental PE.

METHODS

Cancer patients diagnosed with PE at the ED or outpatient clinic between August 2017 and May 2021 were included in Four Cities VTE Cancer, a Dutch multicenter retrospective cohort study. The main outcome was direct discharge versus hospitalization. Safety outcomes were cumulative 14-day mortality and PE-related readmission incidences.

RESULTS

We included 602 patients (median age 71 years; 49.5 % female) of whom 285 (47.3 %) were discharged directly and 317 (52.7 %) were hospitalized. The cumulative 14-day mortality incidence was 0.7 % (95 % CI, 0.1-2.4 %) in patients discharged directly and 9.0 % (95 % CI, 6.2-12.5 %) in those hospitalized. The cumulative 14-day PE-related readmission incidence was 1.8 % (95 % CI, 0.7-3.9 %) and 1.4 % (95 % CI, 0.5-3.3 %) in directly discharged and hospitalized patients, respectively. Of the 220 patients with incidental PE, 180 (81.8 %) were discharged directly compared to 105 of 382 (27.5 %) patients with symptomatic PE (P < 0.001). Mortality and readmission incidences in symptomatic and incidental PE were consistent with the main analysis.

CONCLUSIONS

About 28 % and 82 % of cancer patients with symptomatic or incidental PE, respectively, were discharged directly, with low 14-day mortality and PE-related readmission incidences. These data underline the need for PE risk stratification in oncological populations and suggest that clinicians successfully identify a proportion of patients in whom direct discharge is safe.

Endocrine Side Effects in Patients Treated with Immune Checkpoint Inhibitors: A Narrative Review

Checkpoint inhibitors are monoclonal antibodies that elicit an anti-tumor response by stimulating immune system. Their use has improved the treatment of different types of cancer such as melanoma, breast carcinoma, lung, stomach, colon, liver, renal cell carcinoma, and Hodgkin's lymphoma, but several adverse events have been reported. Although the etiology of these effects is not completely understood, an uncontrolled activation of the immune system has been postulated. Indeed, some studies showed a cross reactivity of T cells, which acted against tumor antigens as well as antigens in the tissues of patients who developed immune-related adverse events. Despite the known possibility of developing immune-related adverse events, early diagnosis, monitoring during therapy, and treatment are fundamental for the best supportive care and administration of immune checkpoint inhibitors. The aim of this review is to guide the clinician in early diagnosis, management, and treatment of the endocrinological adverse effects in the major endocrine glands (thyroid, pituitary, adrenal, endocrine pancreas, and parathyroid).