非結核性抗酸菌症(NTM)治療指標として呼吸器症状、Vitality、Health Perceptionも重要で心理的特性との関連

実際にNTM治療している側から見ると、女性週刊誌が有益・有害両面の情報垂れ流しているところを見聞きするNTM。変な誤解が広まらないことを願う。

序文から

非結核性抗酸菌症(NTM)、主にMycobacterium avium complex(MAC)は、感染患者の約半数に慢性的で衰弱性の肺疾患を引き起こす可能性があります。この希少疾患の主な症状は、咳、極度の疲労、息切れです。 治療を開始する場合、3〜5種類の抗生物質を18〜24カ月間投与します。治療の目標は、多くの場合、疾患を抑制し、進行を止め、患者の気分を良くすることにあります。ほとんどの患者さんで微生物学的奏効が認められますが、治癒率は低くなっています。日常的な症状や機能の改善は、患者の視点から見た治療の成功の重要な指標であることから、臨床現場でのPROの使用をサポートするデータが必要とされています。さらに、米国食品医薬品局(FDA)は最近、MAC-PDに対する抗マイコバクテリア薬の登録試験において、検証済みのPROを主要評価項目とすべきであると決定しました。気管支拡張症患者で検証されたQOLBronchiectasis(QOL-B)、およびMAC-PD8-10患者で予備的に検証されたNTMモジュールは、呼吸器症状、活力(疲労)、健康知覚、NTM特異的症状など12の領域を含んでいます。この分析では、呼吸器症状尺度の心理測定能力を評価し、MAC治療開始後6ヶ月間の症状反応の軌跡を評価することを主目的としました。

Translated with DeepL

Patient-reported symptom and health-related quality of life validation and responsiveness during the first 6 months of treatment for Mycobacterium avium complex pulmonary disease
Emily Henkle, et al. for theMAC2v3 Investigators
Published:February 16, 2023
DOI:https://doi.org/10.1016/j.chest.2023.02.015

https://journal.chestnet.org/article/S0012-3692(23)00260-X/fulltext

https://journal.chestnet.org/article/S0012-3692(23)00260-X/pdf


【背景】非結核性抗酸菌(NTM)、主にMycobacterium avium complex(MAC)は、慢性肺疾患(MAC-PD)の原因である。症状および健康関連QOLの改善は重要な治療成果であるが、有効な患者報告アウトカム(PRO)指標は存在しない。
【研究課題】MAC-PD 治療開始後 6 ヶ月間の QOL-Bronchiectasis (QOL-B) Respiratory Symptoms スケールおよび主要 HRQoL 指標の妥当性と反応性はどのようなものか?
【試験デザインおよび方法】MAC2v3は、現在進行中の無作為化多施設共同プラグマティック臨床試験である。MAC-PD患者は、アジスロマイシンをベースとした2剤または3剤治療に無作為に割り付けられ、本解析では治療群を組み合わせて実施された。PROは、ベースライン、3ヶ月、6ヶ月で測定されました。QOL-B Respiratory Symptoms, Vitality, Physical Functioning, Health Perceptions, NTM Symptom domain score(0-100で評価、100が最高)は個別に分析した。解析時点で登録されている集団を対象に、心理測定および記述的解析を行い、分布に基づく手法で最小重要度差(MID)を算出した。最後に、解析時までに縦断的調査が完了したサブセットにおいて、ペアのt検定と latent growth curve analysisを用いて反応性を評価した。
【結果】ベースライン集団には228人の患者が含まれ、そのうち144人が長期的な調査を受けた。患者は女性(82%)、気管支拡張症(88%)が多く、50%が70歳以上であった。
呼吸器症状は良好な心理測定特性を示し(no floor/ceiling effects、Cronbach's alpha 0.85)、MIDは6.4-6.9であった。VitalityとHealth Perceptionsは同様の結果であった。
呼吸器症状は3ヵ月後に7.8点(p<0.0001)、7.5点(p<0.0001)、身体機能は3ヵ月後に4.6点(p<0.003)、4.2点(p=0.01)改善された。
Latent growth curve解析により、呼吸器症状および身体機能の3ヶ月までの非線形かつ統計的に有意な改善が確認された。
【結論】MAC-PD患者において、QOL-B呼吸器症状および身体機能尺度は良好な心理測定特性を示した。呼吸器症状のスコアは、治療開始後3ヶ月までにMIDを超えて改善した。



www.DeepL.com/Translator(無料版)で翻訳しました。

clinicaltrials.gov #NCT03672630




ホントかどうか、検証してない ChatGPTとの会話

この訳し方がわかりません、教えて下さい; Respiratory Symptoms had good psychometric properties (no floor/ceiling effects, Cronbach’s alpha 0.85) and an MID of 6.4-6.9. Vitality and Health Perceptions performed similarly.

この文章は、ある質問紙(もしくはテスト)のいくつかの項目に関する情報を述べています。以下は、その内容を訳したものです。
「Respiratory Symptoms」、「Vitality」、「Health Perceptions」という3つの質問項目について、心理測定の観点から評価した結果、良好な性質を持っていることがわかりました。Respiratory Symptomsには底辺/天井効果がなく、Cronbachのアルファ係数が0.85であったことが確認されました。また、最小重要差(MID)は6.4〜6.9でした。VitalityおよびHealth Perceptionsについても同様の結果が得られました。」
つまり、Respiratory Symptoms、Vitality、Health Perceptionsという質問項目は、心理測定の観点からみて、良好な性質を持っていることが分かったということです。Respiratory Symptomsについては、底辺/天井効果がなく、Cronbachのアルファ係数が高く、MIDが6.4〜6.9であることが分かりました。VitalityおよびHealth Perceptionsについても、同様の結果が得られました。

Cronbachのアルファ係数って何かわかりますか?

Cronbachのアルファ係数(Cronbach's alpha)は、心理学や社会科学の研究で頻繁に使用される、信頼性係数の一つです。Cronbachのアルファ係数は、複数の質問項目がある場合に、それらの項目がどれだけ一貫性を持っているかを評価するために用いられます。
Cronbachのアルファ係数は、0から1の値を取り、値が高いほど質問項目が一貫性を持っていると考えられます。一般的に、Cronbachのアルファ係数が0.7以上であれば、信頼性が高いとされています。また、0.6以下の場合は信頼性が低いとされ、改善が必要と考えられます。
Cronbachのアルファ係数は、質問項目間の相関関係に基づいて計算されます。具体的には、各質問項目の回答の分散を全体の分散で除し、各質問項目間の共分散を全体の分散で除した後に、これらの値を用いてCronbachのアルファ係数を計算します。この値が高ければ高いほど、質問項目間の相関が強く、一貫性が高いと解釈できます。
Cronbachのアルファ係数は、質問項目が連続値である場合にも、多項式アイテムである場合にも適用することができます。Cronbachのアルファ係数は、研究者が信頼性の高い測定を行うために、データの品質を評価する上で重要な指標の一つとされています。


what is latent growth curve analysis?

Latent growth curve analysis (LGCA) is a statistical modeling technique that is used to analyze longitudinal data, that is, data collected over time from the same individuals. It is a type of structural equation modeling that is used to study change in a continuous outcome variable (e.g. academic achievement, weight, or depression) over time, and to estimate the individual differences in the rate and level of change.
In LGCA, the outcome variable is modeled as a function of time, with time being the predictor variable. The model assumes that the observed outcome variable is a composite of two unobserved variables: the growth trajectory and the measurement error. The growth trajectory is the unobserved process that drives the change in the outcome variable over time, and the measurement error is the unobserved variability in the observed outcome variable due to measurement noise.
LGCA can be used to examine questions such as whether individuals differ in their initial level of an outcome variable, whether the rate of change is linear or nonlinear, and whether the individual differences in the rate and level of change are related to other variables, such as demographic characteristics or treatment status. LGCA is widely used in social and behavioral sciences, as well as in health research, to analyze longitudinal data and to test theories of change over time.

which stastical tool is used in latent growth curve analysis?

Latent growth curve analysis (LGCA) is a type of structural equation modeling (SEM), which is a set of statistical tools used for analyzing complex relationships between variables. In LGCA, SEM is used to model the growth trajectory of an outcome variable over time, and to estimate the individual differences in the rate and level of change.
SEM is a multivariate statistical technique that allows for the simultaneous analysis of multiple dependent variables and their underlying factors or latent variables. The SEM framework provides a way to model the relationships between observed variables and latent variables, and to estimate the parameters of the model using maximum likelihood estimation.
In LGCA, SEM is used to model the change in an outcome variable over time, and to estimate the individual differences in the growth trajectory. The model typically includes latent variables for the intercept and slope, representing the starting point and rate of change in the outcome variable, respectively. The model also includes latent variables for the error terms, representing the measurement error in the observed outcomes.
SEM is a flexible tool that can be used to model a wide range of complex relationships, including non-linear relationships and interactions between variables. It is widely used in social and behavioral sciences, as well as in health research, to analyze longitudinal data and to test theories of change over time.

Is Latent growth curve analysis (LGCA) available in R or Python?

Yes, Latent growth curve analysis (LGCA) is available in both R and Python through various libraries and packages.
In R, LGCA can be performed using the "lavaan" package, which is a popular package for structural equation modeling. The "lavaan" package provides a flexible and user-friendly interface for specifying and estimating LGCA models. Other R packages, such as "sem" and "OpenMx", also support LGCA and related techniques.
In Python, LGCA can be performed using the "statsmodels" package, which provides a range of statistical modeling tools, including regression and time series analysis. The "statsmodels" package includes support for linear regression models, which can be used to fit LGCA models. However, the package is not as specialized for structural equation modeling as the R packages mentioned above, and may require more complex modeling code.
Other Python libraries that can be used for LGCA include "semopy" and "lavaanpy", which are Python ports of the R "sem" and "lavaan" packages, respectively. These packages provide similar functionality to their R counterparts and can be used to fit a wide range of structural equation models, including LGCA.
Overall, there are several libraries and packages available in both R and Python that can be used to perform LGCA and related techniques. The choice of package may depend on the user's familiarity with the language, the complexity of the analysis, and the availability of specific modeling features required for the research question.

この記事が気に入ったらサポートをしてみませんか?