Jump to content
Main menu
Main menu
move to sidebar
hide
Navigation
Main page
Recent changes
Random page
freem
Search
Search
Appearance
Create account
Log in
Personal tools
Create account
Log in
Pages for logged out editors
learn more
Contributions
Talk
Editing
Openai/69716778-c854-8005-8bde-90ffbbce5a8b
(section)
Add languages
Page
Discussion
English
Read
Edit
Edit source
View history
Tools
Tools
move to sidebar
hide
Actions
Read
Edit
Edit source
View history
General
What links here
Related changes
Special pages
Page information
Appearance
move to sidebar
hide
Warning:
You are not logged in. Your IP address will be publicly visible if you make any edits. If you
log in
or
create an account
, your edits will be attributed to your username, along with other benefits.
Anti-spam check. Do
not
fill this in!
=== Assistant: はい。倫理的責任の話を離れて、純粋に反事実(counterfactual)モデルとして「もしワクチン接種率がもっと高ければどうなったか/もし未接種者が接種していればどれだけ死者を減らせたか」という推定は、疫学・数理モデルでも計算可能です。 === はい。倫理的責任の話を離れて、純粋に反事実(counterfactual)モデルとして「もしワクチン接種率がもっと高ければどうなったか/もし未接種者が接種していればどれだけ死者を減らせたか」という推定は、疫学・数理モデルでも計算可能です。 しかし、これは'''モデル上の仮定にもとづく推定値(予測値)'''であり、観測値とは違います。あらかじめ以下のように前提を置いて計算します: ➡ 「ワクチンがあった場合」と「ワクチンがなかった場合」の比較 ➡ 実際の接種率より高い接種率のシナリオ ➡ (あるいは)接種タイミングが早ければ… こうした形の分析がいくつかの研究で報告されています。以下それを踏まえて整理します。 ==== ### ==== * ワクチンが実際に展開された期間の死亡回避数: 約14.4〜19.8 百万(1,440万〜1,980万)死亡回避と推定。 → 「もしワクチンがなければこれだけ多く亡くなっていた可能性がある」モデル。 PubMed<ref>{{cite web|title=PubMed|url=https://pubmed.ncbi.nlm.nih.gov/35753318/|publisher=pubmed.ncbi.nlm.nih.gov|access-date=2026-01-22}}</ref> * この研究ではさらに、 - WHO目標(40%接種)に達していればさらに多くの死亡を回避できたとした推計も提示されています。 PubMed<ref>{{cite web|title=PubMed|url=https://pubmed.ncbi.nlm.nih.gov/35753318/|publisher=pubmed.ncbi.nlm.nih.gov|access-date=2026-01-22}}</ref> 📌 ここでの数字は : ===== #### ===== * 2021年のワクチン接種によって救われた推計:約 31,600人 → これは、 ワクチンがなかった場合の死亡推定 − 実際の死亡数による差。 PubMed<ref>{{cite web|title=PubMed|url=https://pubmed.ncbi.nlm.nih.gov/39983319/|publisher=pubmed.ncbi.nlm.nih.gov|access-date=2026-01-22}}</ref> これも「もしワクチン接種がなかったら数万人多くの死者が出ていた可能性がある」という種類の反事実モデルです。 ===== - 日本では、ワクチン導入や接種率の改善による死亡回避効果をシミュレーションしたモデルで、 現実の死亡者数が約15,000人だったのに対し、30,000人程度の死亡回避が推定されるシナリオが得られたという研究もあります。 PubMed<ref>{{cite web|title=PubMed|url=https://pubmed.ncbi.nlm.nih.gov/40398323/|publisher=pubmed.ncbi.nlm.nih.gov|access-date=2026-01-22}}</ref> ===== ==== こうした推計は次のように「架空の反事実(counterfactual)」をつくります: ==== : つまり、あなたの言う : という形式の考え方は、まさにこうしたモデル分析で扱われる典型的な設定です。 ==== ただし、こうした推計にはいくつかの重要な仮定があります: ==== # 感染/死亡率の推定 - 未接種者と接種者の死亡リスクの差は、観測データにもとづく仮定値です。実社会とは異なる可能性があります。 PubMed<ref>{{cite web|title=PubMed|url=https://pubmed.ncbi.nlm.nih.gov/35753318/|publisher=pubmed.ncbi.nlm.nih.gov|access-date=2026-01-22}}</ref> # 行動・非医療的要因の影響 - 行動変化(マスク、隔離など)が反映されていない場合があります。 - モデルでは感染率に影響する他の要素が固定されていることが多いです。 # 接種率の差 - 「もし全員が接種していたら」を単純に計算するものではなく、接種率や免疫の減衰、変異株の影響などの条件が入っています。 ==== ◆ 反事実モデルでは ==== 「ワクチンがもっと早く普及していた・もっと多くの人が接種していた」 → 処置なしのシナリオに比べて、より多くの死が回避できたはず」 という推定が実際に行われています。 PubMed<ref>{{cite web|title=PubMed|url=https://pubmed.ncbi.nlm.nih.gov/35753318/|publisher=pubmed.ncbi.nlm.nih.gov|access-date=2026-01-22}}</ref> この枠組みを使えば、理論的には : ただしそれは '''「実際の因果責任」ではなく、モデル上の「もしもシナリオ」'''です。 必要であれば、この反事実モデルを使って ▶ 「接種率を例えば90%にしたら世界で何人多く救えたか?」 ▶ 「未接種者1万人当たりの死者増加を推定する簡易モデル」 みたいな具体的数値モデルも一緒に計算し説明できます。希望があれば言ってください。
Summary:
Please note that all contributions to freem are considered to be released under the Creative Commons Attribution-ShareAlike 4.0 (see
Freem:Copyrights
for details). If you do not want your writing to be edited mercilessly and redistributed at will, then do not submit it here.
You are also promising us that you wrote this yourself, or copied it from a public domain or similar free resource.
Do not submit copyrighted work without permission!
Cancel
Editing help
(opens in new window)