Dubai Telegraph - 'AI doctor' better at predicting patient outcomes, including death

EUR -
AED 3.896782
AFN 71.970942
ALL 98.005181
AMD 410.245014
ANG 1.910392
AOA 969.150107
ARS 1058.535585
AUD 1.625105
AWG 1.911243
AZN 1.804916
BAM 1.952226
BBD 2.140282
BDT 126.668083
BGN 1.954125
BHD 0.39988
BIF 3130.34894
BMD 1.060918
BND 1.418709
BOB 7.350404
BRL 6.098794
BSD 1.060009
BTN 89.509273
BWP 14.421276
BYN 3.468912
BYR 20793.984215
BZD 2.136589
CAD 1.480871
CDF 3043.772641
CHF 0.937002
CLF 0.037907
CLP 1045.969635
CNY 7.661842
COP 4706.760764
CRC 542.432423
CUC 1.060918
CUP 28.114315
CVE 110.062449
CZK 25.385671
DJF 188.763289
DKK 7.459582
DOP 63.876059
DZD 141.570939
EGP 52.207642
ETB 131.000325
FJD 2.400856
GBP 0.832847
GEL 2.906642
GHS 17.277204
GMD 75.853327
GNF 9135.746941
GTQ 8.190926
GYD 221.749817
HKD 8.252734
HNL 26.751282
HTG 139.425239
HUF 411.004238
IDR 16737.512871
ILS 3.989583
INR 89.539798
IQD 1388.583814
IRR 44669.934186
ISK 147.520817
JMD 168.439542
JOD 0.752299
JPY 164.527633
KES 137.06364
KGS 91.448653
KHR 4295.439124
KMF 488.419938
KRW 1493.349953
KWD 0.326234
KYD 0.883299
KZT 526.01683
LAK 23242.540542
LBP 94922.679318
LKR 309.967089
LRD 199.802298
LSL 19.152137
LTL 3.132613
LVL 0.641738
LYD 5.135839
MAD 10.515649
MDL 18.974154
MGA 4955.161109
MKD 61.501816
MMK 3445.818857
MOP 8.49301
MRU 42.123861
MUR 50.064526
MVR 16.402021
MWK 1837.721918
MXN 21.861851
MYR 4.72746
MZN 67.819132
NAD 19.151596
NGN 1778.681478
NIO 39.010598
NOK 11.769899
NPR 143.222523
NZD 1.790898
OMR 0.408483
PAB 1.059939
PEN 4.005911
PGK 4.258364
PHP 62.296049
PKR 294.599601
PLN 4.351472
PYG 8282.226373
QAR 3.864488
RON 4.975918
RSD 116.986352
RUB 103.700317
RWF 1454.705134
SAR 3.986063
SBD 8.859994
SCR 14.916358
SDG 638.142533
SEK 11.580918
SGD 1.420892
SLE 24.18896
SOS 605.819355
SRD 37.381452
STD 21958.851549
SVC 9.275193
SZL 19.142853
THB 36.855747
TJS 11.267165
TMT 3.713211
TND 3.332367
TOP 2.48477
TRY 36.47689
TTD 7.203151
TWD 34.468683
TZS 2825.997726
UAH 43.903187
UGX 3894.795581
USD 1.060918
UYU 44.68818
UZS 13571.98253
VES 47.606636
VND 26894.260197
XAF 654.789004
XCD 2.867183
XDR 0.798576
XOF 654.789004
XPF 119.331742
YER 264.990671
ZAR 19.19911
ZMK 9549.525686
ZMW 28.858523
ZWL 341.615022
  • RBGPF

    59.3400

    59.34

    +100%

  • RYCEF

    -0.0500

    7.11

    -0.7%

  • RIO

    -1.4000

    61.2

    -2.29%

  • AZN

    0.4000

    65.19

    +0.61%

  • GSK

    -0.8300

    35.52

    -2.34%

  • NGG

    -1.2400

    62.9

    -1.97%

  • CMSD

    -0.2100

    24.75

    -0.85%

  • BTI

    0.0900

    35.24

    +0.26%

  • SCS

    0.0200

    13.67

    +0.15%

  • CMSC

    -0.1800

    24.54

    -0.73%

  • RELX

    -1.2100

    46.59

    -2.6%

  • VOD

    -0.8500

    8.47

    -10.04%

  • BCC

    -2.0100

    141.13

    -1.42%

  • BCE

    -0.1600

    27.69

    -0.58%

  • BP

    -0.7600

    28.16

    -2.7%

  • JRI

    -0.3000

    13.22

    -2.27%

'AI doctor' better at predicting patient outcomes, including death
'AI doctor' better at predicting patient outcomes, including death / Photo: JEFF KOWALSKY - AFP/File

'AI doctor' better at predicting patient outcomes, including death

Artificial intelligence has proven itself useful in reading medical imaging and even shown it can pass doctors' licensing exams.

Text size:

Now, a new AI tool has demonstrated the ability to read physicians' notes and accurately anticipate patients' risk of death, readmission to hospital, and other outcomes important to their care.

Designed by a team at NYU Grossman School of Medicine, the software is currently in use at the university's affiliated hospitals throughout New York, with the hope that it will become a standard part of health care.

A study on its predictive value was published Wednesday in the journal Nature.

Lead author Eric Oermann, an NYU neurosurgeon and computer scientist, told AFP that while non-AI predictive models have been around in medicine for a long time, they were hardly used in practice because the data they needed requires cumbersome reorganization and formatting.

But "one thing that's common in medicine everywhere, is physicians write notes about what they've seen in clinic, what they've discussed with patients," he said.

"So our basic insight was, can we start with medical notes as our source of data, and then build predictive models on top of it?"

The large language model, called NYUTron, was trained on millions of clinical notes from the health records of 387,000 people who received care within NYU Langone hospitals between January 2011 and May 2020.

These included any records written by doctors, such as patient progress notes, radiology reports and discharge instructions, resulting in a 4.1-billion-word corpus.

One of the key challenges for the software was interpreting the natural language that physicians write in, which varies greatly among individuals, including in the abbreviations they choose.

By looking back at records of what happened, researchers were able to calculate how often the software's predictions turned out to be accurate.

They also tested the tool in live environments, training it on the records from, for example, a hospital in Manhattan then seeing how it fared in a Brooklyn hospital, with different patient demographics.

- Not a substitute for humans -

Overall, NYUTron identified an unnerving 95 percent of people who died in hospital before they were discharged, and 80 percent of patients who would be readmitted within 30 days.

It outperformed most doctors on its predictions, as well as the non-AI computer models used today.

But, to the team's surprise, "the most senior physician who's actually a very famous physician, he had superhuman performance, better than the model," said Oermann.

"The sweet spot for technology and medicine isn't that it's going to always deliver necessarily superhuman results, but it's going to really bring up that baseline."

NYUTron also correctly estimated 79 percent of patients' actual length of stay, 87 percent of cases where patients were denied coverage by insurance, and 89 percent of cases where a patient's primary disease was accompanied by additional conditions.

AI will never be a substitute for the physician-patient relationship, said Oermann. Rather, they will help "provide more information for physicians seamlessly at the point-of-care so they can make more informed decisions."

T.Jamil--DT