18 Juni 2026

Ningkatake intelijensi kesehatan ing ChatGPT

GPT‑5.5 Instant nggawa intelijensi kesehatan tercanggih marang luwih akeh wong, kawangun dening kemajuan model lan evaluasi sing dipimpin dokter.

Lagi dimuat…

Kesehatan minangka salah siji cara paling migunani wong nggunakake ChatGPT. Saben minggu, luwih saka 230 yuta wong nggunakake ChatGPT kanggo njaluk pitulungan babagan pitakonan kesehatan lan kabugaran: mangerteni informasi kesehatan, mangerteni asil laboratorium, nyiapake janji temu, ngurus asuransi, mbangun kabiasaan sing luwih sehat, lan nemtokake apa sing kudu ditakokake sabanjure.

Kanthi GPT‑5.5 Instant, kita ndeleng langkah maju gedhe babagan carane model nangani pitakonan kesehatan, kanthi perbaikan kanggo ngenali kapan perawatan mendesak bisa dibutuhake, takon konteks sing relevan, njlentrehake ketidakpastian, lan nggawe informasi rumit luwih gampang dingerteni. Ing evaluasi kesehatan kita sing paling nantang, GPT‑5.5 Instant saiki nduweni kinerja sing sebandhing karo model Thinking tercanggih kita. Amarga kasedhiya kanggo pangguna gratis ing ChatGPT, luwih akeh wong bisa entuk manfaat saka perbaikan iki. Iki bisa tegesé informasi kesehatan sing luwih gampang dingerteni, pitakonan sing luwih apik kanggo diajokake, lan langkah sabanjure sing cetha.

Kemajuan kuwi nggambarake kemajuan kapabilitas model lan karya sing dipimpin dokter ing balik evaluasi kesehatan kita. Ing kabeh upaya kita, jaringan dokter global mbantu netepake kaya apa sing diarani “apik” ing kahanan kesehatan nyata kanthi mriksa conto tanggapan model, njlentrehake perilaku ideal, lan ngenali pola kegagalan. Makarya bareng dokter menehi kita cara kanggo ngukur kemajuan ing bidang kesehatan lan ningkatake carane ChatGPT nanggapi saka wektu ke wektu.

Ngukur kemajuan ing kesehatan

Ing kesehatan, kemajuan tegese menehi tanggapan sing akurat, gampang dingerteni, lan adhedhasar pertimbangan sing apik: ngenali kapan konteks luwih akeh dibutuhake, njlentrehake ketidakpastian tanpa nggedhekake keyakinan, lan mbantu wong ngerti kapan kudu golek perawatan.

Kanggo ngukur kemajuan kasebut, kita nggunakake evaluasi khusus kesehatan, kalebu HealthBench lan HealthBench Professional. Evaluasi iki nggunakake pacelathon kesehatan sing realistis lan rubrik sing ditulis dokter kanggo ngevaluasi kualitas kayata akurasi, keamanan, komunikasi, kesadaran konteks, kelengkapan, lan eskalasi sing pas.

GPT‑5.5 Instant nggayuh kinerja kesehatan sing mirip karo model tercanggih paling anyar kita ing agregat evaluasi kesehatan, kalebu HealthBench Professional, kanthi perbaikan gedhe saka GPT‑5.3 Instant. 5.5 Instant (dirilis Mei 2026) lan 5.3 Instant (dirilis Maret 2026) kasedhiya kanggo kabeh pangguna gratis ing ChatGPT (miturut watesan), lan kita nggunakake rega API kanggo ngetung biaya kanggo 5.4 Thinking lan 5.5 Thinking.

Minangka perbandingan liyane, kita uga njaluk dokter nulis tanggapan kanggo pacelathon kesehatan sing makili, kanthi wektu tanpa wates lan akses internet (nanging ora AI). Panel dokter kapisah banjur mbandhingake tanggapan dokter iki karo model Instant saka wektu ke wektu, kanthi mriksa kualitas sing penting ing interaksi nyata, kalebu akurasi, komunikasi, kelengkapan, manut instruksi, lan kegunaan kanggo keputusan kesehatan, saka 3500 tanggapan sing dideleng.

Tanggapan GPT‑5.5 Instant diwenehi rating luwih dhuwur tinimbang tanggapan sing ditulis dokter lan tanggapan model lawas ing macem-macem dimensi ing evaluasi iki.

Para dokter menehi rating tanggapan GPT‑5.5 Instant nduweni pola kegagalan luwih sithik tinimbang saka model lawas lan dokter. Contone, GPT 5.5 Instant nduweni luwih sithik kasus sing ora disesuaikan karo konteks layanan kesehatan lokal, luput saka tanda bahaya utawa rujukan perawatan, utawa gagal njaluk konteks tambahan saka pangguna nalika dibutuhake tinimbang model lawas lan dokter.

Amarga skala panggunaan model kita ing kesehatan, cara liya kanggo mangerteni perbaikan model anyar yaiku ngukur lalu lintas produksi. Kita nggunakake pemantau sing njaga privasi ing lalu lintas produksi kanggo nglacak kemungkinan masalah faktualitas ing tanggapan kesehatan. Adhedhasar perbandingan lalu lintas produksi anyar ing kesehatan–miliaran pesen saben minggu–tingkat tanggapan sing duwe paling ora siji masalah faktualitas sing diwenehi tandha wis mudhun 71% sajrone rong wulan pungkasan.

Kaya apa tanggapan sing luwih apik

Mbandhingake tanggapan saka model ing macem-macem wektu kanggo pitakonan kesehatan ing donya nyata nuduhake kepiye ChatGPT wis luwih apik ing perkara sing penting kanggo kesehatan: ngenali kapan sawijining kahanan bisa mbutuhake perhatian mendesak, nangani ketidakpastian kanthi pertimbangan luwih apik, lan menehi pandhuan sing luwih cetha lan luwih migunani babagan apa sing kudu ditindakake sabanjure.

Why might a doctor recommend an MRI before a steroid injection for sciatica?

GPT-5.2 Instant

A doctor may recommend an MRI before a steroid injection for sciatica because the injection is more likely to be useful—and safer—when they know exactly what is compressing or irritating the nerve and where.

Common reasons include:

Confirming the cause of sciatica. Sciatica-like pain can come from a herniated disc, spinal stenosis, foraminal narrowing, spondylolisthesis, tumor, infection, fracture, or sometimes non-spine causes. MRI is the preferred imaging test for seeing discs, nerves, and soft tissue nerve compression. (emedicine.medscape.com)
Choosing the correct injection level and side. If symptoms suggest the L5 nerve root, for example, the MRI can show whether the problem is actually at L4–L5, L5–S1, or another level. This helps decide where to place the epidural or selective nerve-root injection.
Selecting the safest/most appropriate injection approach. Epidural steroid injections can be done by different routes—interlaminar, transforaminal, or caudal. Pre-procedure imaging helps the clinician plan the route and avoid anatomic issues that could increase risk. Many interventionalists consider advanced imaging a prerequisite because it helps optimize medication delivery and reduce risk to neural or vascular structures. (pmc.ncbi.nlm.nih.gov)
Checking for “red flags” or conditions where an injection may not be appropriate. MRI can help identify problems such as infection, cancer, severe stenosis, large disc extrusion, or other findings that might require urgent evaluation or a different treatment.
Determining whether surgery or another treatment should be considered instead. If there is severe nerve compression, progressive weakness, or certain structural problems, an injection may not be the best next step.
Avoiding a low-yield injection. If the MRI does not show nerve-root compression or inflammation that matches your symptoms, the doctor may reconsider whether a steroid injection is likely to help.

That said, MRI is not always required for every case of sciatica. In people without red flags, many cases improve with time, physical therapy, and medication. Some studies have questioned whether routine MRI before lumbar epidural steroid injection always improves outcomes, but guidelines and many clinicians still favor imaging when symptoms persist and an injection or surgery is being considered. (pmc.ncbi.nlm.nih.gov)

You should ask your doctor: “What are you looking for on the MRI, and how would the result change the injection plan?” That usually clarifies whether the MRI is for diagnosis, safety, targeting, or deciding whether an injection is appropriate at all.

Cited

Lumbosacral Radiculopathy Workup: Imaging Studies, Other Tests, https://emedicine.medscape.com/article/95025-workup⁠(mbukak ing jendhela anyar)
Diagnostic and therapeutic spinal interventions: Epidural injections - PMC, https://pmc.ncbi.nlm.nih.gov/articles/PMC5764532/⁠(mbukak ing jendhela anyar)
Should routine MRI of the lumbar spine be required prior to lumbar epidural steroid injection for sciatica pain? - PMC, https://pmc.ncbi.nlm.nih.gov/articles/PMC4392534/⁠(mbukak ing jendhela anyar)

"
" i don't know. "
" well, you're going to have to find out. "
" i'm not sure i can. "
" you 'll figure it out. "
" i hope so. "
" i'm going to go back to the office and see if i can get some more information on this. "
" okay. "
" i 'll be back in a few hours. "
" okay. "
" bye. "
" bye. "
i hung up the phone and looked at the clock. it was almost eleven o'clock. i had been sitting there for over an hour. i got up and went into the bathroom and washed my face. i didn't want to look like a slob. i put on some clean clothes and went back into the living room. i sat down on the couch and looked at the tv. i watched the news and then i heard a knock on the door. i jumped up and ran to the door.
" hello? " i called out.
" hi, i'm dr. peters. "
" oh, hi. " i smiled. " i'm sorry i

Klik jeneng model kanggo ndeleng tanggapan model tambahan.

Keahlian medis ing balik kemajuan

Kemajuan iki dibentuk dening dokter sing mbantu kita netepake, ngukur, lan ningkatake tanggapan kesehatan ing ChatGPT.

OpenAI makarya bareng jaringan global luwih saka 260 dokter ing 60 negara, 49 basa, lan 26 spesialisasi medis. Umpan balik saka dheweke dadi dasar carane ChatGPT nanggapi pitakonan kesehatan ing macem-macem skenario, saka pitakonan kabugaran saben dina nganti kahanan klinis sing luwih rumit.

Para dokter mriksa conto tanggapan model lan ngevaluasi apa tanggapan kasebut akurat, cetha, lengkap, cukup ngati-ati, lan migunani. Dheweke mbantu ngenali ing ngendi tanggapan bisa luput saka konteks penting, ing ngendi muni kakehan yakin, ing ngendi perlu luwih cetha babagan langkah sabanjure, utawa kudu luwih langsung nyengkuyung wong kanggo golek perawatan medis.

Nganti saiki, para dokter wis mriksa luwih saka 700.000 conto tanggapan model sing nggambarake carane klinisi lan pasien bisa nggunakake ChatGPT ing donya nyata. Saben sawetara menit, ana dokter sing mriksa tanggapan anyar. Umpan balik saka dheweke dadi rubrik lan kriteria evaluasi sing mbantu peneliti ngukur apa tanggapan akurat, aman, cetha, lengkap, cukup ngati-ati, lan migunani ing kahanan kesehatan nyata. Iki menehi kita cara sing luwih cetha kanggo ndeleng ing ngendi model saya apik lan ing ngendi isih perlu didandani.

Nggawa perbaikan kesehatan menyang luwih akeh wong

Karya iki uga ndhukung karya OpenAI sing luwih jembar ing kesehatan, kalebu piranti sing mbantu wong luwih mangerteni lan njelajah informasi kesehatan uga piranti sing digawe kanggo klinisi, kayata ChatGPT kanggo Klinisi⁠ lan OpenAI kanggo Layanan Kesehatan⁠, sing ndhukung profesional medis kanggo tugas kayata dokumentasi, riset, lan konsultasi perawatan.

Ningkatake kesehatan manungsa bakal dadi salah siji dampak AGI sing paling pribadi lan nyata. Nalika model kita terus saya apik, tujuan kita yaiku nggawe ChatGPT luwih akurat, luwih ati-ati, lan luwih migunani ing wektu-wektu kuwi — lan terus nggawa kemajuan kasebut marang luwih akeh wong.

2026

Pangarang

OpenAI

Terus maca

Deleng kabeh

New usage analytics and updated spend controls for enterprises

Produk18 Jun 2026

Ngenalaké OpenAI Partner Network

Produk14 Jun 2026

Better memory for a more helpful ChatGPT

Dhasar sing luwih kuwat kanggo memori ChatGPT

Riset4 Jun 2026